GeoLearnV3.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.6/dist-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.\n",
      "  from ._conv import register_converters as _register_converters\n"
     ]
    }
   ],
   "source": [
    "%matplotlib notebook\n",
    "from skimage.draw import circle, line_aa, set_color, random_shapes\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import tensorflow as tf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "MODEL_PATH = './storage/models/geolearnv3'\n",
    "ZERO_THRESHOLD = 0.001"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "def noise(image, size):\n",
    "    lines = np.round(np.random.rand(30, 2) * size).astype(np.int)\n",
    "    for idx, item in enumerate(lines):\n",
    "        if idx % 2:\n",
    "            line = line_aa(0, item[0], size[0], item[1])\n",
    "        else:\n",
    "            line = line_aa(item[0], 0, item[1], size[1])\n",
    "        rr, cc, val = line\n",
    "        set_color(image, (rr, cc), np.random.rand(3), alpha=val)        \n",
    "\n",
    "def clean_circle(size, coords, radius):\n",
    "    image = np.zeros(size)\n",
    "    rr, cc = circle(coords[0], coords[1], radius)\n",
    "    set_color(image, (rr, cc), 1)\n",
    "    return image\n",
    "\n",
    "        \n",
    "def make_example(size):\n",
    "    circle_coords = np.random.rand(2)\n",
    "    real_coords = circle_coords * size\n",
    "    rr, cc = circle(real_coords[0], real_coords[1], 20)\n",
    "    shapes, _ = random_shapes(size, shape='triangle', min_shapes=4, max_shapes=7, min_size=10)\n",
    "    shapes = shapes / 255.\n",
    "    example = shapes.copy()\n",
    "    #example = np.ones(np.append(size, 3))\n",
    "    noise(example, size)\n",
    "    main_circle_color = np.random.rand(3)\n",
    "    set_color(example, (rr, cc), main_circle_color)\n",
    "    shapes_label = np.rollaxis(shapes, axis=-1)[0]\n",
    "    shapes_label = 1. - shapes_label\n",
    "    shapes_label = shapes_label > ZERO_THRESHOLD\n",
    "    label = np.array([clean_circle(size, real_coords, 20), shapes_label])\n",
    "    label = np.moveaxis(label, 0, 2)\n",
    "    return example, label"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "/* Put everything inside the global mpl namespace */\n",
       "window.mpl = {};\n",
       "\n",
       "\n",
       "mpl.get_websocket_type = function() {\n",
       "    if (typeof(WebSocket) !== 'undefined') {\n",
       "        return WebSocket;\n",
       "    } else if (typeof(MozWebSocket) !== 'undefined') {\n",
       "        return MozWebSocket;\n",
       "    } else {\n",
       "        alert('Your browser does not have WebSocket support.' +\n",
       "              'Please try Chrome, Safari or Firefox ≥ 6. ' +\n",
       "              'Firefox 4 and 5 are also supported but you ' +\n",
       "              'have to enable WebSockets in about:config.');\n",
       "    };\n",
       "}\n",
       "\n",
       "mpl.figure = function(figure_id, websocket, ondownload, parent_element) {\n",
       "    this.id = figure_id;\n",
       "\n",
       "    this.ws = websocket;\n",
       "\n",
       "    this.supports_binary = (this.ws.binaryType != undefined);\n",
       "\n",
       "    if (!this.supports_binary) {\n",
       "        var warnings = document.getElementById(\"mpl-warnings\");\n",
       "        if (warnings) {\n",
       "            warnings.style.display = 'block';\n",
       "            warnings.textContent = (\n",
       "                \"This browser does not support binary websocket messages. \" +\n",
       "                    \"Performance may be slow.\");\n",
       "        }\n",
       "    }\n",
       "\n",
       "    this.imageObj = new Image();\n",
       "\n",
       "    this.context = undefined;\n",
       "    this.message = undefined;\n",
       "    this.canvas = undefined;\n",
       "    this.rubberband_canvas = undefined;\n",
       "    this.rubberband_context = undefined;\n",
       "    this.format_dropdown = undefined;\n",
       "\n",
       "    this.image_mode = 'full';\n",
       "\n",
       "    this.root = $('<div/>');\n",
       "    this._root_extra_style(this.root)\n",
       "    this.root.attr('style', 'display: inline-block');\n",
       "\n",
       "    $(parent_element).append(this.root);\n",
       "\n",
       "    this._init_header(this);\n",
       "    this._init_canvas(this);\n",
       "    this._init_toolbar(this);\n",
       "\n",
       "    var fig = this;\n",
       "\n",
       "    this.waiting = false;\n",
       "\n",
       "    this.ws.onopen =  function () {\n",
       "            fig.send_message(\"supports_binary\", {value: fig.supports_binary});\n",
       "            fig.send_message(\"send_image_mode\", {});\n",
       "            if (mpl.ratio != 1) {\n",
       "                fig.send_message(\"set_dpi_ratio\", {'dpi_ratio': mpl.ratio});\n",
       "            }\n",
       "            fig.send_message(\"refresh\", {});\n",
       "        }\n",
       "\n",
       "    this.imageObj.onload = function() {\n",
       "            if (fig.image_mode == 'full') {\n",
       "                // Full images could contain transparency (where diff images\n",
       "                // almost always do), so we need to clear the canvas so that\n",
       "                // there is no ghosting.\n",
       "                fig.context.clearRect(0, 0, fig.canvas.width, fig.canvas.height);\n",
       "            }\n",
       "            fig.context.drawImage(fig.imageObj, 0, 0);\n",
       "        };\n",
       "\n",
       "    this.imageObj.onunload = function() {\n",
       "        fig.ws.close();\n",
       "    }\n",
       "\n",
       "    this.ws.onmessage = this._make_on_message_function(this);\n",
       "\n",
       "    this.ondownload = ondownload;\n",
       "}\n",
       "\n",
       "mpl.figure.prototype._init_header = function() {\n",
       "    var titlebar = $(\n",
       "        '<div class=\"ui-dialog-titlebar ui-widget-header ui-corner-all ' +\n",
       "        'ui-helper-clearfix\"/>');\n",
       "    var titletext = $(\n",
       "        '<div class=\"ui-dialog-title\" style=\"width: 100%; ' +\n",
       "        'text-align: center; padding: 3px;\"/>');\n",
       "    titlebar.append(titletext)\n",
       "    this.root.append(titlebar);\n",
       "    this.header = titletext[0];\n",
       "}\n",
       "\n",
       "\n",
       "\n",
       "mpl.figure.prototype._canvas_extra_style = function(canvas_div) {\n",
       "\n",
       "}\n",
       "\n",
       "\n",
       "mpl.figure.prototype._root_extra_style = function(canvas_div) {\n",
       "\n",
       "}\n",
       "\n",
       "mpl.figure.prototype._init_canvas = function() {\n",
       "    var fig = this;\n",
       "\n",
       "    var canvas_div = $('<div/>');\n",
       "\n",
       "    canvas_div.attr('style', 'position: relative; clear: both; outline: 0');\n",
       "\n",
       "    function canvas_keyboard_event(event) {\n",
       "        return fig.key_event(event, event['data']);\n",
       "    }\n",
       "\n",
       "    canvas_div.keydown('key_press', canvas_keyboard_event);\n",
       "    canvas_div.keyup('key_release', canvas_keyboard_event);\n",
       "    this.canvas_div = canvas_div\n",
       "    this._canvas_extra_style(canvas_div)\n",
       "    this.root.append(canvas_div);\n",
       "\n",
       "    var canvas = $('<canvas/>');\n",
       "    canvas.addClass('mpl-canvas');\n",
       "    canvas.attr('style', \"left: 0; top: 0; z-index: 0; outline: 0\")\n",
       "\n",
       "    this.canvas = canvas[0];\n",
       "    this.context = canvas[0].getContext(\"2d\");\n",
       "\n",
       "    var backingStore = this.context.backingStorePixelRatio ||\n",
       "\tthis.context.webkitBackingStorePixelRatio ||\n",
       "\tthis.context.mozBackingStorePixelRatio ||\n",
       "\tthis.context.msBackingStorePixelRatio ||\n",
       "\tthis.context.oBackingStorePixelRatio ||\n",
       "\tthis.context.backingStorePixelRatio || 1;\n",
       "\n",
       "    mpl.ratio = (window.devicePixelRatio || 1) / backingStore;\n",
       "\n",
       "    var rubberband = $('<canvas/>');\n",
       "    rubberband.attr('style', \"position: absolute; left: 0; top: 0; z-index: 1;\")\n",
       "\n",
       "    var pass_mouse_events = true;\n",
       "\n",
       "    canvas_div.resizable({\n",
       "        start: function(event, ui) {\n",
       "            pass_mouse_events = false;\n",
       "        },\n",
       "        resize: function(event, ui) {\n",
       "            fig.request_resize(ui.size.width, ui.size.height);\n",
       "        },\n",
       "        stop: function(event, ui) {\n",
       "            pass_mouse_events = true;\n",
       "            fig.request_resize(ui.size.width, ui.size.height);\n",
       "        },\n",
       "    });\n",
       "\n",
       "    function mouse_event_fn(event) {\n",
       "        if (pass_mouse_events)\n",
       "            return fig.mouse_event(event, event['data']);\n",
       "    }\n",
       "\n",
       "    rubberband.mousedown('button_press', mouse_event_fn);\n",
       "    rubberband.mouseup('button_release', mouse_event_fn);\n",
       "    // Throttle sequential mouse events to 1 every 20ms.\n",
       "    rubberband.mousemove('motion_notify', mouse_event_fn);\n",
       "\n",
       "    rubberband.mouseenter('figure_enter', mouse_event_fn);\n",
       "    rubberband.mouseleave('figure_leave', mouse_event_fn);\n",
       "\n",
       "    canvas_div.on(\"wheel\", function (event) {\n",
       "        event = event.originalEvent;\n",
       "        event['data'] = 'scroll'\n",
       "        if (event.deltaY < 0) {\n",
       "            event.step = 1;\n",
       "        } else {\n",
       "            event.step = -1;\n",
       "        }\n",
       "        mouse_event_fn(event);\n",
       "    });\n",
       "\n",
       "    canvas_div.append(canvas);\n",
       "    canvas_div.append(rubberband);\n",
       "\n",
       "    this.rubberband = rubberband;\n",
       "    this.rubberband_canvas = rubberband[0];\n",
       "    this.rubberband_context = rubberband[0].getContext(\"2d\");\n",
       "    this.rubberband_context.strokeStyle = \"#000000\";\n",
       "\n",
       "    this._resize_canvas = function(width, height) {\n",
       "        // Keep the size of the canvas, canvas container, and rubber band\n",
       "        // canvas in synch.\n",
       "        canvas_div.css('width', width)\n",
       "        canvas_div.css('height', height)\n",
       "\n",
       "        canvas.attr('width', width * mpl.ratio);\n",
       "        canvas.attr('height', height * mpl.ratio);\n",
       "        canvas.attr('style', 'width: ' + width + 'px; height: ' + height + 'px;');\n",
       "\n",
       "        rubberband.attr('width', width);\n",
       "        rubberband.attr('height', height);\n",
       "    }\n",
       "\n",
       "    // Set the figure to an initial 600x600px, this will subsequently be updated\n",
       "    // upon first draw.\n",
       "    this._resize_canvas(600, 600);\n",
       "\n",
       "    // Disable right mouse context menu.\n",
       "    $(this.rubberband_canvas).bind(\"contextmenu\",function(e){\n",
       "        return false;\n",
       "    });\n",
       "\n",
       "    function set_focus () {\n",
       "        canvas.focus();\n",
       "        canvas_div.focus();\n",
       "    }\n",
       "\n",
       "    window.setTimeout(set_focus, 100);\n",
       "}\n",
       "\n",
       "mpl.figure.prototype._init_toolbar = function() {\n",
       "    var fig = this;\n",
       "\n",
       "    var nav_element = $('<div/>')\n",
       "    nav_element.attr('style', 'width: 100%');\n",
       "    this.root.append(nav_element);\n",
       "\n",
       "    // Define a callback function for later on.\n",
       "    function toolbar_event(event) {\n",
       "        return fig.toolbar_button_onclick(event['data']);\n",
       "    }\n",
       "    function toolbar_mouse_event(event) {\n",
       "        return fig.toolbar_button_onmouseover(event['data']);\n",
       "    }\n",
       "\n",
       "    for(var toolbar_ind in mpl.toolbar_items) {\n",
       "        var name = mpl.toolbar_items[toolbar_ind][0];\n",
       "        var tooltip = mpl.toolbar_items[toolbar_ind][1];\n",
       "        var image = mpl.toolbar_items[toolbar_ind][2];\n",
       "        var method_name = mpl.toolbar_items[toolbar_ind][3];\n",
       "\n",
       "        if (!name) {\n",
       "            // put a spacer in here.\n",
       "            continue;\n",
       "        }\n",
       "        var button = $('<button/>');\n",
       "        button.addClass('ui-button ui-widget ui-state-default ui-corner-all ' +\n",
       "                        'ui-button-icon-only');\n",
       "        button.attr('role', 'button');\n",
       "        button.attr('aria-disabled', 'false');\n",
       "        button.click(method_name, toolbar_event);\n",
       "        button.mouseover(tooltip, toolbar_mouse_event);\n",
       "\n",
       "        var icon_img = $('<span/>');\n",
       "        icon_img.addClass('ui-button-icon-primary ui-icon');\n",
       "        icon_img.addClass(image);\n",
       "        icon_img.addClass('ui-corner-all');\n",
       "\n",
       "        var tooltip_span = $('<span/>');\n",
       "        tooltip_span.addClass('ui-button-text');\n",
       "        tooltip_span.html(tooltip);\n",
       "\n",
       "        button.append(icon_img);\n",
       "        button.append(tooltip_span);\n",
       "\n",
       "        nav_element.append(button);\n",
       "    }\n",
       "\n",
       "    var fmt_picker_span = $('<span/>');\n",
       "\n",
       "    var fmt_picker = $('<select/>');\n",
       "    fmt_picker.addClass('mpl-toolbar-option ui-widget ui-widget-content');\n",
       "    fmt_picker_span.append(fmt_picker);\n",
       "    nav_element.append(fmt_picker_span);\n",
       "    this.format_dropdown = fmt_picker[0];\n",
       "\n",
       "    for (var ind in mpl.extensions) {\n",
       "        var fmt = mpl.extensions[ind];\n",
       "        var option = $(\n",
       "            '<option/>', {selected: fmt === mpl.default_extension}).html(fmt);\n",
       "        fmt_picker.append(option)\n",
       "    }\n",
       "\n",
       "    // Add hover states to the ui-buttons\n",
       "    $( \".ui-button\" ).hover(\n",
       "        function() { $(this).addClass(\"ui-state-hover\");},\n",
       "        function() { $(this).removeClass(\"ui-state-hover\");}\n",
       "    );\n",
       "\n",
       "    var status_bar = $('<span class=\"mpl-message\"/>');\n",
       "    nav_element.append(status_bar);\n",
       "    this.message = status_bar[0];\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.request_resize = function(x_pixels, y_pixels) {\n",
       "    // Request matplotlib to resize the figure. Matplotlib will then trigger a resize in the client,\n",
       "    // which will in turn request a refresh of the image.\n",
       "    this.send_message('resize', {'width': x_pixels, 'height': y_pixels});\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.send_message = function(type, properties) {\n",
       "    properties['type'] = type;\n",
       "    properties['figure_id'] = this.id;\n",
       "    this.ws.send(JSON.stringify(properties));\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.send_draw_message = function() {\n",
       "    if (!this.waiting) {\n",
       "        this.waiting = true;\n",
       "        this.ws.send(JSON.stringify({type: \"draw\", figure_id: this.id}));\n",
       "    }\n",
       "}\n",
       "\n",
       "\n",
       "mpl.figure.prototype.handle_save = function(fig, msg) {\n",
       "    var format_dropdown = fig.format_dropdown;\n",
       "    var format = format_dropdown.options[format_dropdown.selectedIndex].value;\n",
       "    fig.ondownload(fig, format);\n",
       "}\n",
       "\n",
       "\n",
       "mpl.figure.prototype.handle_resize = function(fig, msg) {\n",
       "    var size = msg['size'];\n",
       "    if (size[0] != fig.canvas.width || size[1] != fig.canvas.height) {\n",
       "        fig._resize_canvas(size[0], size[1]);\n",
       "        fig.send_message(\"refresh\", {});\n",
       "    };\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.handle_rubberband = function(fig, msg) {\n",
       "    var x0 = msg['x0'] / mpl.ratio;\n",
       "    var y0 = (fig.canvas.height - msg['y0']) / mpl.ratio;\n",
       "    var x1 = msg['x1'] / mpl.ratio;\n",
       "    var y1 = (fig.canvas.height - msg['y1']) / mpl.ratio;\n",
       "    x0 = Math.floor(x0) + 0.5;\n",
       "    y0 = Math.floor(y0) + 0.5;\n",
       "    x1 = Math.floor(x1) + 0.5;\n",
       "    y1 = Math.floor(y1) + 0.5;\n",
       "    var min_x = Math.min(x0, x1);\n",
       "    var min_y = Math.min(y0, y1);\n",
       "    var width = Math.abs(x1 - x0);\n",
       "    var height = Math.abs(y1 - y0);\n",
       "\n",
       "    fig.rubberband_context.clearRect(\n",
       "        0, 0, fig.canvas.width, fig.canvas.height);\n",
       "\n",
       "    fig.rubberband_context.strokeRect(min_x, min_y, width, height);\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.handle_figure_label = function(fig, msg) {\n",
       "    // Updates the figure title.\n",
       "    fig.header.textContent = msg['label'];\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.handle_cursor = function(fig, msg) {\n",
       "    var cursor = msg['cursor'];\n",
       "    switch(cursor)\n",
       "    {\n",
       "    case 0:\n",
       "        cursor = 'pointer';\n",
       "        break;\n",
       "    case 1:\n",
       "        cursor = 'default';\n",
       "        break;\n",
       "    case 2:\n",
       "        cursor = 'crosshair';\n",
       "        break;\n",
       "    case 3:\n",
       "        cursor = 'move';\n",
       "        break;\n",
       "    }\n",
       "    fig.rubberband_canvas.style.cursor = cursor;\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.handle_message = function(fig, msg) {\n",
       "    fig.message.textContent = msg['message'];\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.handle_draw = function(fig, msg) {\n",
       "    // Request the server to send over a new figure.\n",
       "    fig.send_draw_message();\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.handle_image_mode = function(fig, msg) {\n",
       "    fig.image_mode = msg['mode'];\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.updated_canvas_event = function() {\n",
       "    // Called whenever the canvas gets updated.\n",
       "    this.send_message(\"ack\", {});\n",
       "}\n",
       "\n",
       "// A function to construct a web socket function for onmessage handling.\n",
       "// Called in the figure constructor.\n",
       "mpl.figure.prototype._make_on_message_function = function(fig) {\n",
       "    return function socket_on_message(evt) {\n",
       "        if (evt.data instanceof Blob) {\n",
       "            /* FIXME: We get \"Resource interpreted as Image but\n",
       "             * transferred with MIME type text/plain:\" errors on\n",
       "             * Chrome.  But how to set the MIME type?  It doesn't seem\n",
       "             * to be part of the websocket stream */\n",
       "            evt.data.type = \"image/png\";\n",
       "\n",
       "            /* Free the memory for the previous frames */\n",
       "            if (fig.imageObj.src) {\n",
       "                (window.URL || window.webkitURL).revokeObjectURL(\n",
       "                    fig.imageObj.src);\n",
       "            }\n",
       "\n",
       "            fig.imageObj.src = (window.URL || window.webkitURL).createObjectURL(\n",
       "                evt.data);\n",
       "            fig.updated_canvas_event();\n",
       "            fig.waiting = false;\n",
       "            return;\n",
       "        }\n",
       "        else if (typeof evt.data === 'string' && evt.data.slice(0, 21) == \"data:image/png;base64\") {\n",
       "            fig.imageObj.src = evt.data;\n",
       "            fig.updated_canvas_event();\n",
       "            fig.waiting = false;\n",
       "            return;\n",
       "        }\n",
       "\n",
       "        var msg = JSON.parse(evt.data);\n",
       "        var msg_type = msg['type'];\n",
       "\n",
       "        // Call the  \"handle_{type}\" callback, which takes\n",
       "        // the figure and JSON message as its only arguments.\n",
       "        try {\n",
       "            var callback = fig[\"handle_\" + msg_type];\n",
       "        } catch (e) {\n",
       "            console.log(\"No handler for the '\" + msg_type + \"' message type: \", msg);\n",
       "            return;\n",
       "        }\n",
       "\n",
       "        if (callback) {\n",
       "            try {\n",
       "                // console.log(\"Handling '\" + msg_type + \"' message: \", msg);\n",
       "                callback(fig, msg);\n",
       "            } catch (e) {\n",
       "                console.log(\"Exception inside the 'handler_\" + msg_type + \"' callback:\", e, e.stack, msg);\n",
       "            }\n",
       "        }\n",
       "    };\n",
       "}\n",
       "\n",
       "// from http://stackoverflow.com/questions/1114465/getting-mouse-location-in-canvas\n",
       "mpl.findpos = function(e) {\n",
       "    //this section is from http://www.quirksmode.org/js/events_properties.html\n",
       "    var targ;\n",
       "    if (!e)\n",
       "        e = window.event;\n",
       "    if (e.target)\n",
       "        targ = e.target;\n",
       "    else if (e.srcElement)\n",
       "        targ = e.srcElement;\n",
       "    if (targ.nodeType == 3) // defeat Safari bug\n",
       "        targ = targ.parentNode;\n",
       "\n",
       "    // jQuery normalizes the pageX and pageY\n",
       "    // pageX,Y are the mouse positions relative to the document\n",
       "    // offset() returns the position of the element relative to the document\n",
       "    var x = e.pageX - $(targ).offset().left;\n",
       "    var y = e.pageY - $(targ).offset().top;\n",
       "\n",
       "    return {\"x\": x, \"y\": y};\n",
       "};\n",
       "\n",
       "/*\n",
       " * return a copy of an object with only non-object keys\n",
       " * we need this to avoid circular references\n",
       " * http://stackoverflow.com/a/24161582/3208463\n",
       " */\n",
       "function simpleKeys (original) {\n",
       "  return Object.keys(original).reduce(function (obj, key) {\n",
       "    if (typeof original[key] !== 'object')\n",
       "        obj[key] = original[key]\n",
       "    return obj;\n",
       "  }, {});\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.mouse_event = function(event, name) {\n",
       "    var canvas_pos = mpl.findpos(event)\n",
       "\n",
       "    if (name === 'button_press')\n",
       "    {\n",
       "        this.canvas.focus();\n",
       "        this.canvas_div.focus();\n",
       "    }\n",
       "\n",
       "    var x = canvas_pos.x * mpl.ratio;\n",
       "    var y = canvas_pos.y * mpl.ratio;\n",
       "\n",
       "    this.send_message(name, {x: x, y: y, button: event.button,\n",
       "                             step: event.step,\n",
       "                             guiEvent: simpleKeys(event)});\n",
       "\n",
       "    /* This prevents the web browser from automatically changing to\n",
       "     * the text insertion cursor when the button is pressed.  We want\n",
       "     * to control all of the cursor setting manually through the\n",
       "     * 'cursor' event from matplotlib */\n",
       "    event.preventDefault();\n",
       "    return false;\n",
       "}\n",
       "\n",
       "mpl.figure.prototype._key_event_extra = function(event, name) {\n",
       "    // Handle any extra behaviour associated with a key event\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.key_event = function(event, name) {\n",
       "\n",
       "    // Prevent repeat events\n",
       "    if (name == 'key_press')\n",
       "    {\n",
       "        if (event.which === this._key)\n",
       "            return;\n",
       "        else\n",
       "            this._key = event.which;\n",
       "    }\n",
       "    if (name == 'key_release')\n",
       "        this._key = null;\n",
       "\n",
       "    var value = '';\n",
       "    if (event.ctrlKey && event.which != 17)\n",
       "        value += \"ctrl+\";\n",
       "    if (event.altKey && event.which != 18)\n",
       "        value += \"alt+\";\n",
       "    if (event.shiftKey && event.which != 16)\n",
       "        value += \"shift+\";\n",
       "\n",
       "    value += 'k';\n",
       "    value += event.which.toString();\n",
       "\n",
       "    this._key_event_extra(event, name);\n",
       "\n",
       "    this.send_message(name, {key: value,\n",
       "                             guiEvent: simpleKeys(event)});\n",
       "    return false;\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.toolbar_button_onclick = function(name) {\n",
       "    if (name == 'download') {\n",
       "        this.handle_save(this, null);\n",
       "    } else {\n",
       "        this.send_message(\"toolbar_button\", {name: name});\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.toolbar_button_onmouseover = function(tooltip) {\n",
       "    this.message.textContent = tooltip;\n",
       "};\n",
       "mpl.toolbar_items = [[\"Home\", \"Reset original view\", \"fa fa-home icon-home\", \"home\"], [\"Back\", \"Back to  previous view\", \"fa fa-arrow-left icon-arrow-left\", \"back\"], [\"Forward\", \"Forward to next view\", \"fa fa-arrow-right icon-arrow-right\", \"forward\"], [\"\", \"\", \"\", \"\"], [\"Pan\", \"Pan axes with left mouse, zoom with right\", \"fa fa-arrows icon-move\", \"pan\"], [\"Zoom\", \"Zoom to rectangle\", \"fa fa-square-o icon-check-empty\", \"zoom\"], [\"\", \"\", \"\", \"\"], [\"Download\", \"Download plot\", \"fa fa-floppy-o icon-save\", \"download\"]];\n",
       "\n",
       "mpl.extensions = [\"eps\", \"jpeg\", \"pdf\", \"png\", \"ps\", \"raw\", \"svg\", \"tif\"];\n",
       "\n",
       "mpl.default_extension = \"png\";var comm_websocket_adapter = function(comm) {\n",
       "    // Create a \"websocket\"-like object which calls the given IPython comm\n",
       "    // object with the appropriate methods. Currently this is a non binary\n",
       "    // socket, so there is still some room for performance tuning.\n",
       "    var ws = {};\n",
       "\n",
       "    ws.close = function() {\n",
       "        comm.close()\n",
       "    };\n",
       "    ws.send = function(m) {\n",
       "        //console.log('sending', m);\n",
       "        comm.send(m);\n",
       "    };\n",
       "    // Register the callback with on_msg.\n",
       "    comm.on_msg(function(msg) {\n",
       "        //console.log('receiving', msg['content']['data'], msg);\n",
       "        // Pass the mpl event to the overridden (by mpl) onmessage function.\n",
       "        ws.onmessage(msg['content']['data'])\n",
       "    });\n",
       "    return ws;\n",
       "}\n",
       "\n",
       "mpl.mpl_figure_comm = function(comm, msg) {\n",
       "    // This is the function which gets called when the mpl process\n",
       "    // starts-up an IPython Comm through the \"matplotlib\" channel.\n",
       "\n",
       "    var id = msg.content.data.id;\n",
       "    // Get hold of the div created by the display call when the Comm\n",
       "    // socket was opened in Python.\n",
       "    var element = $(\"#\" + id);\n",
       "    var ws_proxy = comm_websocket_adapter(comm)\n",
       "\n",
       "    function ondownload(figure, format) {\n",
       "        window.open(figure.imageObj.src);\n",
       "    }\n",
       "\n",
       "    var fig = new mpl.figure(id, ws_proxy,\n",
       "                           ondownload,\n",
       "                           element.get(0));\n",
       "\n",
       "    // Call onopen now - mpl needs it, as it is assuming we've passed it a real\n",
       "    // web socket which is closed, not our websocket->open comm proxy.\n",
       "    ws_proxy.onopen();\n",
       "\n",
       "    fig.parent_element = element.get(0);\n",
       "    fig.cell_info = mpl.find_output_cell(\"<div id='\" + id + \"'></div>\");\n",
       "    if (!fig.cell_info) {\n",
       "        console.error(\"Failed to find cell for figure\", id, fig);\n",
       "        return;\n",
       "    }\n",
       "\n",
       "    var output_index = fig.cell_info[2]\n",
       "    var cell = fig.cell_info[0];\n",
       "\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_close = function(fig, msg) {\n",
       "    var width = fig.canvas.width/mpl.ratio\n",
       "    fig.root.unbind('remove')\n",
       "\n",
       "    // Update the output cell to use the data from the current canvas.\n",
       "    fig.push_to_output();\n",
       "    var dataURL = fig.canvas.toDataURL();\n",
       "    // Re-enable the keyboard manager in IPython - without this line, in FF,\n",
       "    // the notebook keyboard shortcuts fail.\n",
       "    IPython.keyboard_manager.enable()\n",
       "    $(fig.parent_element).html('<img src=\"' + dataURL + '\" width=\"' + width + '\">');\n",
       "    fig.close_ws(fig, msg);\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.close_ws = function(fig, msg){\n",
       "    fig.send_message('closing', msg);\n",
       "    // fig.ws.close()\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.push_to_output = function(remove_interactive) {\n",
       "    // Turn the data on the canvas into data in the output cell.\n",
       "    var width = this.canvas.width/mpl.ratio\n",
       "    var dataURL = this.canvas.toDataURL();\n",
       "    this.cell_info[1]['text/html'] = '<img src=\"' + dataURL + '\" width=\"' + width + '\">';\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.updated_canvas_event = function() {\n",
       "    // Tell IPython that the notebook contents must change.\n",
       "    IPython.notebook.set_dirty(true);\n",
       "    this.send_message(\"ack\", {});\n",
       "    var fig = this;\n",
       "    // Wait a second, then push the new image to the DOM so\n",
       "    // that it is saved nicely (might be nice to debounce this).\n",
       "    setTimeout(function () { fig.push_to_output() }, 1000);\n",
       "}\n",
       "\n",
       "mpl.figure.prototype._init_toolbar = function() {\n",
       "    var fig = this;\n",
       "\n",
       "    var nav_element = $('<div/>')\n",
       "    nav_element.attr('style', 'width: 100%');\n",
       "    this.root.append(nav_element);\n",
       "\n",
       "    // Define a callback function for later on.\n",
       "    function toolbar_event(event) {\n",
       "        return fig.toolbar_button_onclick(event['data']);\n",
       "    }\n",
       "    function toolbar_mouse_event(event) {\n",
       "        return fig.toolbar_button_onmouseover(event['data']);\n",
       "    }\n",
       "\n",
       "    for(var toolbar_ind in mpl.toolbar_items){\n",
       "        var name = mpl.toolbar_items[toolbar_ind][0];\n",
       "        var tooltip = mpl.toolbar_items[toolbar_ind][1];\n",
       "        var image = mpl.toolbar_items[toolbar_ind][2];\n",
       "        var method_name = mpl.toolbar_items[toolbar_ind][3];\n",
       "\n",
       "        if (!name) { continue; };\n",
       "\n",
       "        var button = $('<button class=\"btn btn-default\" href=\"#\" title=\"' + name + '\"><i class=\"fa ' + image + ' fa-lg\"></i></button>');\n",
       "        button.click(method_name, toolbar_event);\n",
       "        button.mouseover(tooltip, toolbar_mouse_event);\n",
       "        nav_element.append(button);\n",
       "    }\n",
       "\n",
       "    // Add the status bar.\n",
       "    var status_bar = $('<span class=\"mpl-message\" style=\"text-align:right; float: right;\"/>');\n",
       "    nav_element.append(status_bar);\n",
       "    this.message = status_bar[0];\n",
       "\n",
       "    // Add the close button to the window.\n",
       "    var buttongrp = $('<div class=\"btn-group inline pull-right\"></div>');\n",
       "    var button = $('<button class=\"btn btn-mini btn-primary\" href=\"#\" title=\"Stop Interaction\"><i class=\"fa fa-power-off icon-remove icon-large\"></i></button>');\n",
       "    button.click(function (evt) { fig.handle_close(fig, {}); } );\n",
       "    button.mouseover('Stop Interaction', toolbar_mouse_event);\n",
       "    buttongrp.append(button);\n",
       "    var titlebar = this.root.find($('.ui-dialog-titlebar'));\n",
       "    titlebar.prepend(buttongrp);\n",
       "}\n",
       "\n",
       "mpl.figure.prototype._root_extra_style = function(el){\n",
       "    var fig = this\n",
       "    el.on(\"remove\", function(){\n",
       "\tfig.close_ws(fig, {});\n",
       "    });\n",
       "}\n",
       "\n",
       "mpl.figure.prototype._canvas_extra_style = function(el){\n",
       "    // this is important to make the div 'focusable\n",
       "    el.attr('tabindex', 0)\n",
       "    // reach out to IPython and tell the keyboard manager to turn it's self\n",
       "    // off when our div gets focus\n",
       "\n",
       "    // location in version 3\n",
       "    if (IPython.notebook.keyboard_manager) {\n",
       "        IPython.notebook.keyboard_manager.register_events(el);\n",
       "    }\n",
       "    else {\n",
       "        // location in version 2\n",
       "        IPython.keyboard_manager.register_events(el);\n",
       "    }\n",
       "\n",
       "}\n",
       "\n",
       "mpl.figure.prototype._key_event_extra = function(event, name) {\n",
       "    var manager = IPython.notebook.keyboard_manager;\n",
       "    if (!manager)\n",
       "        manager = IPython.keyboard_manager;\n",
       "\n",
       "    // Check for shift+enter\n",
       "    if (event.shiftKey && event.which == 13) {\n",
       "        this.canvas_div.blur();\n",
       "        event.shiftKey = false;\n",
       "        // Send a \"J\" for go to next cell\n",
       "        event.which = 74;\n",
       "        event.keyCode = 74;\n",
       "        manager.command_mode();\n",
       "        manager.handle_keydown(event);\n",
       "    }\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.handle_save = function(fig, msg) {\n",
       "    fig.ondownload(fig, null);\n",
       "}\n",
       "\n",
       "\n",
       "mpl.find_output_cell = function(html_output) {\n",
       "    // Return the cell and output element which can be found *uniquely* in the notebook.\n",
       "    // Note - this is a bit hacky, but it is done because the \"notebook_saving.Notebook\"\n",
       "    // IPython event is triggered only after the cells have been serialised, which for\n",
       "    // our purposes (turning an active figure into a static one), is too late.\n",
       "    var cells = IPython.notebook.get_cells();\n",
       "    var ncells = cells.length;\n",
       "    for (var i=0; i<ncells; i++) {\n",
       "        var cell = cells[i];\n",
       "        if (cell.cell_type === 'code'){\n",
       "            for (var j=0; j<cell.output_area.outputs.length; j++) {\n",
       "                var data = cell.output_area.outputs[j];\n",
       "                if (data.data) {\n",
       "                    // IPython >= 3 moved mimebundle to data attribute of output\n",
       "                    data = data.data;\n",
       "                }\n",
       "                if (data['text/html'] == html_output) {\n",
       "                    return [cell, data, j];\n",
       "                }\n",
       "            }\n",
       "        }\n",
       "    }\n",
       "}\n",
       "\n",
       "// Register the function which deals with the matplotlib target/channel.\n",
       "// The kernel may be null if the page has been refreshed.\n",
       "if (IPython.notebook.kernel != null) {\n",
       "    IPython.notebook.kernel.comm_manager.register_target('matplotlib', mpl.mpl_figure_comm);\n",
       "}\n"
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<img src=\"data:image/png;base64,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\" width=\"640\">"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x7fc61b3bef28>"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "image, label = make_example((224, 224))\n",
    "plt.imshow(image)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "def make_examples(size, count):\n",
    "    examples = [make_example(size) for _ in range(count)]\n",
    "    images = np.stack(image for image, _ in examples)\n",
    "    labels = np.stack(label for _, label in examples)\n",
    "    return images, labels"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "def position_model_fn(features, labels, mode, config):\n",
    "    layer = tf.layers.conv2d(features, filters=16, kernel_size=5, activation=tf.nn.relu, padding='same')\n",
    "    layer = tf.layers.max_pooling2d(layer, 2, 2)\n",
    "    \n",
    "    layer = tf.layers.conv2d(layer, filters=16, kernel_size=3, activation=tf.nn.relu, padding='same')\n",
    "    layer = tf.layers.max_pooling2d(layer, 2, 2)    \n",
    "    \n",
    "    layer = tf.layers.conv2d(layer, filters=64, kernel_size=3, activation=tf.nn.relu, padding='same')\n",
    "    layer = tf.layers.max_pooling2d(layer, 2, 2)    \n",
    "\n",
    "    layer = tf.layers.conv2d(layer, filters=64, kernel_size=1, activation=tf.nn.relu)\n",
    "    layer = tf.layers.conv2d(layer, filters=64, kernel_size=1, activation=tf.nn.relu)\n",
    "    \n",
    "    layer = tf.layers.conv2d_transpose(layer, filters=32, kernel_size=2, strides=2, activation=tf.nn.relu)\n",
    "    layer = tf.layers.conv2d_transpose(layer, filters=32, kernel_size=2, strides=2, activation=tf.nn.relu)    \n",
    "    layer = tf.layers.conv2d_transpose(layer, filters=32, kernel_size=2, strides=2, activation=tf.nn.relu) \n",
    "\n",
    "    predictions = tf.layers.conv2d(layer, filters=2, kernel_size=1)\n",
    "    \n",
    "    if mode == tf.estimator.ModeKeys.PREDICT:\n",
    "        spec = tf.estimator.EstimatorSpec(mode, predictions=predictions)     \n",
    "    else:\n",
    "        loss = tf.losses.mean_pairwise_squared_error(labels=labels, predictions=predictions)\n",
    "        optimizer = tf.train.AdamOptimizer()\n",
    "        train_op = optimizer.minimize(loss=loss, global_step=tf.train.get_global_step())\n",
    "        spec = tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op)    \n",
    "    return spec"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "size = np.array([224, 224])\n",
    "batch_size = 100\n",
    "eval_images, eval_labels = make_examples(size, 20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "INFO:tensorflow:Using config: {'_model_dir': './storage/models/geolearnv3', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 1200, '_session_config': None, '_keep_checkpoint_max': 3, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_train_distribute': None, '_device_fn': None, '_service': None, '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x7fc61b31fb38>, '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1}\n"
     ]
    }
   ],
   "source": [
    "position_estimator_config = tf.estimator.RunConfig(\n",
    "    save_checkpoints_secs = 20*60, \n",
    "    keep_checkpoint_max = 3,\n",
    ")\n",
    "\n",
    "position_estimator = tf.estimator.Estimator(\n",
    "    model_fn=position_model_fn,\n",
    "    model_dir=MODEL_PATH,\n",
    "    config=position_estimator_config)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 0\n",
      "Making examples\n",
      "Training\n",
      "INFO:tensorflow:Running training and evaluation locally (non-distributed).\n",
      "INFO:tensorflow:Start train and evaluate loop. The evaluate will happen after every checkpoint. Checkpoint frequency is determined based on RunConfig arguments: save_checkpoints_steps None or save_checkpoints_secs 1200.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Create CheckpointSaverHook.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-500\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Saving checkpoints for 500 into ./storage/models/geolearnv3/model.ckpt.\n",
      "INFO:tensorflow:loss = 0.20592114, step = 500\n",
      "INFO:tensorflow:Saving checkpoints for 505 into ./storage/models/geolearnv3/model.ckpt.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Starting evaluation at 2018-10-13-03:31:08\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-505\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Finished evaluation at 2018-10-13-03:31:09\n",
      "INFO:tensorflow:Saving dict for global step 505: global_step = 505, loss = 0.40019232\n",
      "INFO:tensorflow:Saving 'checkpoint_path' summary for global step 505: ./storage/models/geolearnv3/model.ckpt-505\n",
      "INFO:tensorflow:Loss for final step: 0.215229.\n",
      "Epoch 1\n",
      "Making examples\n",
      "Training\n",
      "INFO:tensorflow:Running training and evaluation locally (non-distributed).\n",
      "INFO:tensorflow:Start train and evaluate loop. The evaluate will happen after every checkpoint. Checkpoint frequency is determined based on RunConfig arguments: save_checkpoints_steps None or save_checkpoints_secs 1200.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Create CheckpointSaverHook.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-505\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Saving checkpoints for 505 into ./storage/models/geolearnv3/model.ckpt.\n",
      "INFO:tensorflow:loss = 0.17541346, step = 505\n",
      "INFO:tensorflow:Saving checkpoints for 510 into ./storage/models/geolearnv3/model.ckpt.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Starting evaluation at 2018-10-13-03:31:38\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-510\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Finished evaluation at 2018-10-13-03:31:39\n",
      "INFO:tensorflow:Saving dict for global step 510: global_step = 510, loss = 0.37797105\n",
      "INFO:tensorflow:Saving 'checkpoint_path' summary for global step 510: ./storage/models/geolearnv3/model.ckpt-510\n",
      "INFO:tensorflow:Loss for final step: 0.32971585.\n",
      "Epoch 2\n",
      "Making examples\n",
      "Training\n",
      "INFO:tensorflow:Running training and evaluation locally (non-distributed).\n",
      "INFO:tensorflow:Start train and evaluate loop. The evaluate will happen after every checkpoint. Checkpoint frequency is determined based on RunConfig arguments: save_checkpoints_steps None or save_checkpoints_secs 1200.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Create CheckpointSaverHook.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-510\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Saving checkpoints for 510 into ./storage/models/geolearnv3/model.ckpt.\n",
      "INFO:tensorflow:loss = 0.1789619, step = 510\n",
      "INFO:tensorflow:Saving checkpoints for 515 into ./storage/models/geolearnv3/model.ckpt.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Starting evaluation at 2018-10-13-03:32:08\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-515\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Finished evaluation at 2018-10-13-03:32:09\n",
      "INFO:tensorflow:Saving dict for global step 515: global_step = 515, loss = 0.45816365\n",
      "INFO:tensorflow:Saving 'checkpoint_path' summary for global step 515: ./storage/models/geolearnv3/model.ckpt-515\n",
      "INFO:tensorflow:Loss for final step: 0.31249526.\n",
      "Epoch 3\n",
      "Making examples\n",
      "Training\n",
      "INFO:tensorflow:Running training and evaluation locally (non-distributed).\n",
      "INFO:tensorflow:Start train and evaluate loop. The evaluate will happen after every checkpoint. Checkpoint frequency is determined based on RunConfig arguments: save_checkpoints_steps None or save_checkpoints_secs 1200.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Create CheckpointSaverHook.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-515\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Saving checkpoints for 515 into ./storage/models/geolearnv3/model.ckpt.\n",
      "INFO:tensorflow:loss = 0.2470038, step = 515\n",
      "INFO:tensorflow:Saving checkpoints for 520 into ./storage/models/geolearnv3/model.ckpt.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Starting evaluation at 2018-10-13-03:32:38\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-520\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Finished evaluation at 2018-10-13-03:32:39\n",
      "INFO:tensorflow:Saving dict for global step 520: global_step = 520, loss = 0.4034104\n",
      "INFO:tensorflow:Saving 'checkpoint_path' summary for global step 520: ./storage/models/geolearnv3/model.ckpt-520\n",
      "INFO:tensorflow:Loss for final step: 0.25522152.\n",
      "Epoch 4\n",
      "Making examples\n",
      "Training\n",
      "INFO:tensorflow:Running training and evaluation locally (non-distributed).\n",
      "INFO:tensorflow:Start train and evaluate loop. The evaluate will happen after every checkpoint. Checkpoint frequency is determined based on RunConfig arguments: save_checkpoints_steps None or save_checkpoints_secs 1200.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Create CheckpointSaverHook.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-520\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Saving checkpoints for 520 into ./storage/models/geolearnv3/model.ckpt.\n",
      "INFO:tensorflow:loss = 0.24129403, step = 520\n",
      "INFO:tensorflow:Saving checkpoints for 525 into ./storage/models/geolearnv3/model.ckpt.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Starting evaluation at 2018-10-13-03:33:07\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-525\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Finished evaluation at 2018-10-13-03:33:08\n",
      "INFO:tensorflow:Saving dict for global step 525: global_step = 525, loss = 0.37355852\n",
      "INFO:tensorflow:Saving 'checkpoint_path' summary for global step 525: ./storage/models/geolearnv3/model.ckpt-525\n",
      "INFO:tensorflow:Loss for final step: 0.22179541.\n",
      "Epoch 5\n",
      "Making examples\n",
      "Training\n",
      "INFO:tensorflow:Running training and evaluation locally (non-distributed).\n",
      "INFO:tensorflow:Start train and evaluate loop. The evaluate will happen after every checkpoint. Checkpoint frequency is determined based on RunConfig arguments: save_checkpoints_steps None or save_checkpoints_secs 1200.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Create CheckpointSaverHook.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-525\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "INFO:tensorflow:Saving checkpoints for 525 into ./storage/models/geolearnv3/model.ckpt.\n",
      "INFO:tensorflow:loss = 0.21799076, step = 525\n",
      "INFO:tensorflow:Saving checkpoints for 530 into ./storage/models/geolearnv3/model.ckpt.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Starting evaluation at 2018-10-13-03:33:37\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-530\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Finished evaluation at 2018-10-13-03:33:38\n",
      "INFO:tensorflow:Saving dict for global step 530: global_step = 530, loss = 0.41538802\n",
      "INFO:tensorflow:Saving 'checkpoint_path' summary for global step 530: ./storage/models/geolearnv3/model.ckpt-530\n",
      "INFO:tensorflow:Loss for final step: 0.12517917.\n",
      "Epoch 6\n",
      "Making examples\n",
      "Training\n",
      "INFO:tensorflow:Running training and evaluation locally (non-distributed).\n",
      "INFO:tensorflow:Start train and evaluate loop. The evaluate will happen after every checkpoint. Checkpoint frequency is determined based on RunConfig arguments: save_checkpoints_steps None or save_checkpoints_secs 1200.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Create CheckpointSaverHook.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-530\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Saving checkpoints for 530 into ./storage/models/geolearnv3/model.ckpt.\n",
      "INFO:tensorflow:loss = 0.21621582, step = 530\n",
      "INFO:tensorflow:Saving checkpoints for 535 into ./storage/models/geolearnv3/model.ckpt.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Starting evaluation at 2018-10-13-03:34:08\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-535\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Finished evaluation at 2018-10-13-03:34:09\n",
      "INFO:tensorflow:Saving dict for global step 535: global_step = 535, loss = 0.39081785\n",
      "INFO:tensorflow:Saving 'checkpoint_path' summary for global step 535: ./storage/models/geolearnv3/model.ckpt-535\n",
      "INFO:tensorflow:Loss for final step: 0.18362197.\n",
      "Epoch 7\n",
      "Making examples\n",
      "Training\n",
      "INFO:tensorflow:Running training and evaluation locally (non-distributed).\n",
      "INFO:tensorflow:Start train and evaluate loop. The evaluate will happen after every checkpoint. Checkpoint frequency is determined based on RunConfig arguments: save_checkpoints_steps None or save_checkpoints_secs 1200.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Create CheckpointSaverHook.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-535\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Saving checkpoints for 535 into ./storage/models/geolearnv3/model.ckpt.\n",
      "INFO:tensorflow:loss = 0.15348956, step = 535\n",
      "INFO:tensorflow:Saving checkpoints for 540 into ./storage/models/geolearnv3/model.ckpt.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Starting evaluation at 2018-10-13-03:34:38\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-540\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Finished evaluation at 2018-10-13-03:34:39\n",
      "INFO:tensorflow:Saving dict for global step 540: global_step = 540, loss = 0.37636638\n",
      "INFO:tensorflow:Saving 'checkpoint_path' summary for global step 540: ./storage/models/geolearnv3/model.ckpt-540\n",
      "INFO:tensorflow:Loss for final step: 0.21809265.\n",
      "Epoch 8\n",
      "Making examples\n",
      "Training\n",
      "INFO:tensorflow:Running training and evaluation locally (non-distributed).\n",
      "INFO:tensorflow:Start train and evaluate loop. The evaluate will happen after every checkpoint. Checkpoint frequency is determined based on RunConfig arguments: save_checkpoints_steps None or save_checkpoints_secs 1200.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Create CheckpointSaverHook.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-540\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Saving checkpoints for 540 into ./storage/models/geolearnv3/model.ckpt.\n",
      "INFO:tensorflow:loss = 0.17556247, step = 540\n",
      "INFO:tensorflow:Saving checkpoints for 545 into ./storage/models/geolearnv3/model.ckpt.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Starting evaluation at 2018-10-13-03:35:08\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-545\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Finished evaluation at 2018-10-13-03:35:09\n",
      "INFO:tensorflow:Saving dict for global step 545: global_step = 545, loss = 0.39854345\n",
      "INFO:tensorflow:Saving 'checkpoint_path' summary for global step 545: ./storage/models/geolearnv3/model.ckpt-545\n",
      "INFO:tensorflow:Loss for final step: 0.15436226.\n",
      "Epoch 9\n",
      "Making examples\n",
      "Training\n",
      "INFO:tensorflow:Running training and evaluation locally (non-distributed).\n",
      "INFO:tensorflow:Start train and evaluate loop. The evaluate will happen after every checkpoint. Checkpoint frequency is determined based on RunConfig arguments: save_checkpoints_steps None or save_checkpoints_secs 1200.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Create CheckpointSaverHook.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-545\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Saving checkpoints for 545 into ./storage/models/geolearnv3/model.ckpt.\n",
      "INFO:tensorflow:loss = 0.18817994, step = 545\n",
      "INFO:tensorflow:Saving checkpoints for 550 into ./storage/models/geolearnv3/model.ckpt.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Starting evaluation at 2018-10-13-03:35:38\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Finished evaluation at 2018-10-13-03:35:39\n",
      "INFO:tensorflow:Saving dict for global step 550: global_step = 550, loss = 0.3670544\n",
      "INFO:tensorflow:Saving 'checkpoint_path' summary for global step 550: ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Loss for final step: 0.16675282.\n"
     ]
    }
   ],
   "source": [
    "for idx in range(10):\n",
    "    print(f\"Epoch {idx}\")\n",
    "    print(\"Making examples\")\n",
    "    train_images, train_labels = make_examples(size, 50)\n",
    "    def train_dataset_fn():\n",
    "        return tf.data.Dataset.from_tensor_slices((train_images, train_labels)).batch(10)\n",
    "    def eval_dataset_fn():\n",
    "        return tf.data.Dataset.from_tensor_slices((eval_images, eval_labels)).batch(25)\n",
    "    train_spec = tf.estimator.TrainSpec(input_fn=train_dataset_fn)\n",
    "    eval_spec = tf.estimator.EvalSpec(input_fn=eval_dataset_fn)\n",
    "    print(\"Training\")\n",
    "    tf.estimator.train_and_evaluate(position_estimator, train_spec, eval_spec)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "CATEGORY_COLORS = [\n",
    "    np.array([1., 0., 0.]),\n",
    "    np.array([0., 1., 0.]),\n",
    "]\n",
    "\n",
    "def label_to_image(label):\n",
    "    image = np.zeros(label.shape[:2] + (3,))\n",
    "    label = np.moveaxis(label, 2, 0)\n",
    "    for index, color in enumerate(CATEGORY_COLORS):\n",
    "        label_layer = np.repeat(label[index][:, :, np.newaxis], 3, axis=2) * color\n",
    "        image += label_layer\n",
    "    return image"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "86999f8a33ce4e8c826d0e0c3e8e9469",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Button(description='Check', style=ButtonStyle())"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-500\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n"
     ]
    },
    {
     "data": {
      "application/javascript": [
       "/* Put everything inside the global mpl namespace */\n",
       "window.mpl = {};\n",
       "\n",
       "\n",
       "mpl.get_websocket_type = function() {\n",
       "    if (typeof(WebSocket) !== 'undefined') {\n",
       "        return WebSocket;\n",
       "    } else if (typeof(MozWebSocket) !== 'undefined') {\n",
       "        return MozWebSocket;\n",
       "    } else {\n",
       "        alert('Your browser does not have WebSocket support.' +\n",
       "              'Please try Chrome, Safari or Firefox ≥ 6. ' +\n",
       "              'Firefox 4 and 5 are also supported but you ' +\n",
       "              'have to enable WebSockets in about:config.');\n",
       "    };\n",
       "}\n",
       "\n",
       "mpl.figure = function(figure_id, websocket, ondownload, parent_element) {\n",
       "    this.id = figure_id;\n",
       "\n",
       "    this.ws = websocket;\n",
       "\n",
       "    this.supports_binary = (this.ws.binaryType != undefined);\n",
       "\n",
       "    if (!this.supports_binary) {\n",
       "        var warnings = document.getElementById(\"mpl-warnings\");\n",
       "        if (warnings) {\n",
       "            warnings.style.display = 'block';\n",
       "            warnings.textContent = (\n",
       "                \"This browser does not support binary websocket messages. \" +\n",
       "                    \"Performance may be slow.\");\n",
       "        }\n",
       "    }\n",
       "\n",
       "    this.imageObj = new Image();\n",
       "\n",
       "    this.context = undefined;\n",
       "    this.message = undefined;\n",
       "    this.canvas = undefined;\n",
       "    this.rubberband_canvas = undefined;\n",
       "    this.rubberband_context = undefined;\n",
       "    this.format_dropdown = undefined;\n",
       "\n",
       "    this.image_mode = 'full';\n",
       "\n",
       "    this.root = $('<div/>');\n",
       "    this._root_extra_style(this.root)\n",
       "    this.root.attr('style', 'display: inline-block');\n",
       "\n",
       "    $(parent_element).append(this.root);\n",
       "\n",
       "    this._init_header(this);\n",
       "    this._init_canvas(this);\n",
       "    this._init_toolbar(this);\n",
       "\n",
       "    var fig = this;\n",
       "\n",
       "    this.waiting = false;\n",
       "\n",
       "    this.ws.onopen =  function () {\n",
       "            fig.send_message(\"supports_binary\", {value: fig.supports_binary});\n",
       "            fig.send_message(\"send_image_mode\", {});\n",
       "            if (mpl.ratio != 1) {\n",
       "                fig.send_message(\"set_dpi_ratio\", {'dpi_ratio': mpl.ratio});\n",
       "            }\n",
       "            fig.send_message(\"refresh\", {});\n",
       "        }\n",
       "\n",
       "    this.imageObj.onload = function() {\n",
       "            if (fig.image_mode == 'full') {\n",
       "                // Full images could contain transparency (where diff images\n",
       "                // almost always do), so we need to clear the canvas so that\n",
       "                // there is no ghosting.\n",
       "                fig.context.clearRect(0, 0, fig.canvas.width, fig.canvas.height);\n",
       "            }\n",
       "            fig.context.drawImage(fig.imageObj, 0, 0);\n",
       "        };\n",
       "\n",
       "    this.imageObj.onunload = function() {\n",
       "        fig.ws.close();\n",
       "    }\n",
       "\n",
       "    this.ws.onmessage = this._make_on_message_function(this);\n",
       "\n",
       "    this.ondownload = ondownload;\n",
       "}\n",
       "\n",
       "mpl.figure.prototype._init_header = function() {\n",
       "    var titlebar = $(\n",
       "        '<div class=\"ui-dialog-titlebar ui-widget-header ui-corner-all ' +\n",
       "        'ui-helper-clearfix\"/>');\n",
       "    var titletext = $(\n",
       "        '<div class=\"ui-dialog-title\" style=\"width: 100%; ' +\n",
       "        'text-align: center; padding: 3px;\"/>');\n",
       "    titlebar.append(titletext)\n",
       "    this.root.append(titlebar);\n",
       "    this.header = titletext[0];\n",
       "}\n",
       "\n",
       "\n",
       "\n",
       "mpl.figure.prototype._canvas_extra_style = function(canvas_div) {\n",
       "\n",
       "}\n",
       "\n",
       "\n",
       "mpl.figure.prototype._root_extra_style = function(canvas_div) {\n",
       "\n",
       "}\n",
       "\n",
       "mpl.figure.prototype._init_canvas = function() {\n",
       "    var fig = this;\n",
       "\n",
       "    var canvas_div = $('<div/>');\n",
       "\n",
       "    canvas_div.attr('style', 'position: relative; clear: both; outline: 0');\n",
       "\n",
       "    function canvas_keyboard_event(event) {\n",
       "        return fig.key_event(event, event['data']);\n",
       "    }\n",
       "\n",
       "    canvas_div.keydown('key_press', canvas_keyboard_event);\n",
       "    canvas_div.keyup('key_release', canvas_keyboard_event);\n",
       "    this.canvas_div = canvas_div\n",
       "    this._canvas_extra_style(canvas_div)\n",
       "    this.root.append(canvas_div);\n",
       "\n",
       "    var canvas = $('<canvas/>');\n",
       "    canvas.addClass('mpl-canvas');\n",
       "    canvas.attr('style', \"left: 0; top: 0; z-index: 0; outline: 0\")\n",
       "\n",
       "    this.canvas = canvas[0];\n",
       "    this.context = canvas[0].getContext(\"2d\");\n",
       "\n",
       "    var backingStore = this.context.backingStorePixelRatio ||\n",
       "\tthis.context.webkitBackingStorePixelRatio ||\n",
       "\tthis.context.mozBackingStorePixelRatio ||\n",
       "\tthis.context.msBackingStorePixelRatio ||\n",
       "\tthis.context.oBackingStorePixelRatio ||\n",
       "\tthis.context.backingStorePixelRatio || 1;\n",
       "\n",
       "    mpl.ratio = (window.devicePixelRatio || 1) / backingStore;\n",
       "\n",
       "    var rubberband = $('<canvas/>');\n",
       "    rubberband.attr('style', \"position: absolute; left: 0; top: 0; z-index: 1;\")\n",
       "\n",
       "    var pass_mouse_events = true;\n",
       "\n",
       "    canvas_div.resizable({\n",
       "        start: function(event, ui) {\n",
       "            pass_mouse_events = false;\n",
       "        },\n",
       "        resize: function(event, ui) {\n",
       "            fig.request_resize(ui.size.width, ui.size.height);\n",
       "        },\n",
       "        stop: function(event, ui) {\n",
       "            pass_mouse_events = true;\n",
       "            fig.request_resize(ui.size.width, ui.size.height);\n",
       "        },\n",
       "    });\n",
       "\n",
       "    function mouse_event_fn(event) {\n",
       "        if (pass_mouse_events)\n",
       "            return fig.mouse_event(event, event['data']);\n",
       "    }\n",
       "\n",
       "    rubberband.mousedown('button_press', mouse_event_fn);\n",
       "    rubberband.mouseup('button_release', mouse_event_fn);\n",
       "    // Throttle sequential mouse events to 1 every 20ms.\n",
       "    rubberband.mousemove('motion_notify', mouse_event_fn);\n",
       "\n",
       "    rubberband.mouseenter('figure_enter', mouse_event_fn);\n",
       "    rubberband.mouseleave('figure_leave', mouse_event_fn);\n",
       "\n",
       "    canvas_div.on(\"wheel\", function (event) {\n",
       "        event = event.originalEvent;\n",
       "        event['data'] = 'scroll'\n",
       "        if (event.deltaY < 0) {\n",
       "            event.step = 1;\n",
       "        } else {\n",
       "            event.step = -1;\n",
       "        }\n",
       "        mouse_event_fn(event);\n",
       "    });\n",
       "\n",
       "    canvas_div.append(canvas);\n",
       "    canvas_div.append(rubberband);\n",
       "\n",
       "    this.rubberband = rubberband;\n",
       "    this.rubberband_canvas = rubberband[0];\n",
       "    this.rubberband_context = rubberband[0].getContext(\"2d\");\n",
       "    this.rubberband_context.strokeStyle = \"#000000\";\n",
       "\n",
       "    this._resize_canvas = function(width, height) {\n",
       "        // Keep the size of the canvas, canvas container, and rubber band\n",
       "        // canvas in synch.\n",
       "        canvas_div.css('width', width)\n",
       "        canvas_div.css('height', height)\n",
       "\n",
       "        canvas.attr('width', width * mpl.ratio);\n",
       "        canvas.attr('height', height * mpl.ratio);\n",
       "        canvas.attr('style', 'width: ' + width + 'px; height: ' + height + 'px;');\n",
       "\n",
       "        rubberband.attr('width', width);\n",
       "        rubberband.attr('height', height);\n",
       "    }\n",
       "\n",
       "    // Set the figure to an initial 600x600px, this will subsequently be updated\n",
       "    // upon first draw.\n",
       "    this._resize_canvas(600, 600);\n",
       "\n",
       "    // Disable right mouse context menu.\n",
       "    $(this.rubberband_canvas).bind(\"contextmenu\",function(e){\n",
       "        return false;\n",
       "    });\n",
       "\n",
       "    function set_focus () {\n",
       "        canvas.focus();\n",
       "        canvas_div.focus();\n",
       "    }\n",
       "\n",
       "    window.setTimeout(set_focus, 100);\n",
       "}\n",
       "\n",
       "mpl.figure.prototype._init_toolbar = function() {\n",
       "    var fig = this;\n",
       "\n",
       "    var nav_element = $('<div/>')\n",
       "    nav_element.attr('style', 'width: 100%');\n",
       "    this.root.append(nav_element);\n",
       "\n",
       "    // Define a callback function for later on.\n",
       "    function toolbar_event(event) {\n",
       "        return fig.toolbar_button_onclick(event['data']);\n",
       "    }\n",
       "    function toolbar_mouse_event(event) {\n",
       "        return fig.toolbar_button_onmouseover(event['data']);\n",
       "    }\n",
       "\n",
       "    for(var toolbar_ind in mpl.toolbar_items) {\n",
       "        var name = mpl.toolbar_items[toolbar_ind][0];\n",
       "        var tooltip = mpl.toolbar_items[toolbar_ind][1];\n",
       "        var image = mpl.toolbar_items[toolbar_ind][2];\n",
       "        var method_name = mpl.toolbar_items[toolbar_ind][3];\n",
       "\n",
       "        if (!name) {\n",
       "            // put a spacer in here.\n",
       "            continue;\n",
       "        }\n",
       "        var button = $('<button/>');\n",
       "        button.addClass('ui-button ui-widget ui-state-default ui-corner-all ' +\n",
       "                        'ui-button-icon-only');\n",
       "        button.attr('role', 'button');\n",
       "        button.attr('aria-disabled', 'false');\n",
       "        button.click(method_name, toolbar_event);\n",
       "        button.mouseover(tooltip, toolbar_mouse_event);\n",
       "\n",
       "        var icon_img = $('<span/>');\n",
       "        icon_img.addClass('ui-button-icon-primary ui-icon');\n",
       "        icon_img.addClass(image);\n",
       "        icon_img.addClass('ui-corner-all');\n",
       "\n",
       "        var tooltip_span = $('<span/>');\n",
       "        tooltip_span.addClass('ui-button-text');\n",
       "        tooltip_span.html(tooltip);\n",
       "\n",
       "        button.append(icon_img);\n",
       "        button.append(tooltip_span);\n",
       "\n",
       "        nav_element.append(button);\n",
       "    }\n",
       "\n",
       "    var fmt_picker_span = $('<span/>');\n",
       "\n",
       "    var fmt_picker = $('<select/>');\n",
       "    fmt_picker.addClass('mpl-toolbar-option ui-widget ui-widget-content');\n",
       "    fmt_picker_span.append(fmt_picker);\n",
       "    nav_element.append(fmt_picker_span);\n",
       "    this.format_dropdown = fmt_picker[0];\n",
       "\n",
       "    for (var ind in mpl.extensions) {\n",
       "        var fmt = mpl.extensions[ind];\n",
       "        var option = $(\n",
       "            '<option/>', {selected: fmt === mpl.default_extension}).html(fmt);\n",
       "        fmt_picker.append(option)\n",
       "    }\n",
       "\n",
       "    // Add hover states to the ui-buttons\n",
       "    $( \".ui-button\" ).hover(\n",
       "        function() { $(this).addClass(\"ui-state-hover\");},\n",
       "        function() { $(this).removeClass(\"ui-state-hover\");}\n",
       "    );\n",
       "\n",
       "    var status_bar = $('<span class=\"mpl-message\"/>');\n",
       "    nav_element.append(status_bar);\n",
       "    this.message = status_bar[0];\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.request_resize = function(x_pixels, y_pixels) {\n",
       "    // Request matplotlib to resize the figure. Matplotlib will then trigger a resize in the client,\n",
       "    // which will in turn request a refresh of the image.\n",
       "    this.send_message('resize', {'width': x_pixels, 'height': y_pixels});\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.send_message = function(type, properties) {\n",
       "    properties['type'] = type;\n",
       "    properties['figure_id'] = this.id;\n",
       "    this.ws.send(JSON.stringify(properties));\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.send_draw_message = function() {\n",
       "    if (!this.waiting) {\n",
       "        this.waiting = true;\n",
       "        this.ws.send(JSON.stringify({type: \"draw\", figure_id: this.id}));\n",
       "    }\n",
       "}\n",
       "\n",
       "\n",
       "mpl.figure.prototype.handle_save = function(fig, msg) {\n",
       "    var format_dropdown = fig.format_dropdown;\n",
       "    var format = format_dropdown.options[format_dropdown.selectedIndex].value;\n",
       "    fig.ondownload(fig, format);\n",
       "}\n",
       "\n",
       "\n",
       "mpl.figure.prototype.handle_resize = function(fig, msg) {\n",
       "    var size = msg['size'];\n",
       "    if (size[0] != fig.canvas.width || size[1] != fig.canvas.height) {\n",
       "        fig._resize_canvas(size[0], size[1]);\n",
       "        fig.send_message(\"refresh\", {});\n",
       "    };\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.handle_rubberband = function(fig, msg) {\n",
       "    var x0 = msg['x0'] / mpl.ratio;\n",
       "    var y0 = (fig.canvas.height - msg['y0']) / mpl.ratio;\n",
       "    var x1 = msg['x1'] / mpl.ratio;\n",
       "    var y1 = (fig.canvas.height - msg['y1']) / mpl.ratio;\n",
       "    x0 = Math.floor(x0) + 0.5;\n",
       "    y0 = Math.floor(y0) + 0.5;\n",
       "    x1 = Math.floor(x1) + 0.5;\n",
       "    y1 = Math.floor(y1) + 0.5;\n",
       "    var min_x = Math.min(x0, x1);\n",
       "    var min_y = Math.min(y0, y1);\n",
       "    var width = Math.abs(x1 - x0);\n",
       "    var height = Math.abs(y1 - y0);\n",
       "\n",
       "    fig.rubberband_context.clearRect(\n",
       "        0, 0, fig.canvas.width, fig.canvas.height);\n",
       "\n",
       "    fig.rubberband_context.strokeRect(min_x, min_y, width, height);\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.handle_figure_label = function(fig, msg) {\n",
       "    // Updates the figure title.\n",
       "    fig.header.textContent = msg['label'];\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.handle_cursor = function(fig, msg) {\n",
       "    var cursor = msg['cursor'];\n",
       "    switch(cursor)\n",
       "    {\n",
       "    case 0:\n",
       "        cursor = 'pointer';\n",
       "        break;\n",
       "    case 1:\n",
       "        cursor = 'default';\n",
       "        break;\n",
       "    case 2:\n",
       "        cursor = 'crosshair';\n",
       "        break;\n",
       "    case 3:\n",
       "        cursor = 'move';\n",
       "        break;\n",
       "    }\n",
       "    fig.rubberband_canvas.style.cursor = cursor;\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.handle_message = function(fig, msg) {\n",
       "    fig.message.textContent = msg['message'];\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.handle_draw = function(fig, msg) {\n",
       "    // Request the server to send over a new figure.\n",
       "    fig.send_draw_message();\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.handle_image_mode = function(fig, msg) {\n",
       "    fig.image_mode = msg['mode'];\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.updated_canvas_event = function() {\n",
       "    // Called whenever the canvas gets updated.\n",
       "    this.send_message(\"ack\", {});\n",
       "}\n",
       "\n",
       "// A function to construct a web socket function for onmessage handling.\n",
       "// Called in the figure constructor.\n",
       "mpl.figure.prototype._make_on_message_function = function(fig) {\n",
       "    return function socket_on_message(evt) {\n",
       "        if (evt.data instanceof Blob) {\n",
       "            /* FIXME: We get \"Resource interpreted as Image but\n",
       "             * transferred with MIME type text/plain:\" errors on\n",
       "             * Chrome.  But how to set the MIME type?  It doesn't seem\n",
       "             * to be part of the websocket stream */\n",
       "            evt.data.type = \"image/png\";\n",
       "\n",
       "            /* Free the memory for the previous frames */\n",
       "            if (fig.imageObj.src) {\n",
       "                (window.URL || window.webkitURL).revokeObjectURL(\n",
       "                    fig.imageObj.src);\n",
       "            }\n",
       "\n",
       "            fig.imageObj.src = (window.URL || window.webkitURL).createObjectURL(\n",
       "                evt.data);\n",
       "            fig.updated_canvas_event();\n",
       "            fig.waiting = false;\n",
       "            return;\n",
       "        }\n",
       "        else if (typeof evt.data === 'string' && evt.data.slice(0, 21) == \"data:image/png;base64\") {\n",
       "            fig.imageObj.src = evt.data;\n",
       "            fig.updated_canvas_event();\n",
       "            fig.waiting = false;\n",
       "            return;\n",
       "        }\n",
       "\n",
       "        var msg = JSON.parse(evt.data);\n",
       "        var msg_type = msg['type'];\n",
       "\n",
       "        // Call the  \"handle_{type}\" callback, which takes\n",
       "        // the figure and JSON message as its only arguments.\n",
       "        try {\n",
       "            var callback = fig[\"handle_\" + msg_type];\n",
       "        } catch (e) {\n",
       "            console.log(\"No handler for the '\" + msg_type + \"' message type: \", msg);\n",
       "            return;\n",
       "        }\n",
       "\n",
       "        if (callback) {\n",
       "            try {\n",
       "                // console.log(\"Handling '\" + msg_type + \"' message: \", msg);\n",
       "                callback(fig, msg);\n",
       "            } catch (e) {\n",
       "                console.log(\"Exception inside the 'handler_\" + msg_type + \"' callback:\", e, e.stack, msg);\n",
       "            }\n",
       "        }\n",
       "    };\n",
       "}\n",
       "\n",
       "// from http://stackoverflow.com/questions/1114465/getting-mouse-location-in-canvas\n",
       "mpl.findpos = function(e) {\n",
       "    //this section is from http://www.quirksmode.org/js/events_properties.html\n",
       "    var targ;\n",
       "    if (!e)\n",
       "        e = window.event;\n",
       "    if (e.target)\n",
       "        targ = e.target;\n",
       "    else if (e.srcElement)\n",
       "        targ = e.srcElement;\n",
       "    if (targ.nodeType == 3) // defeat Safari bug\n",
       "        targ = targ.parentNode;\n",
       "\n",
       "    // jQuery normalizes the pageX and pageY\n",
       "    // pageX,Y are the mouse positions relative to the document\n",
       "    // offset() returns the position of the element relative to the document\n",
       "    var x = e.pageX - $(targ).offset().left;\n",
       "    var y = e.pageY - $(targ).offset().top;\n",
       "\n",
       "    return {\"x\": x, \"y\": y};\n",
       "};\n",
       "\n",
       "/*\n",
       " * return a copy of an object with only non-object keys\n",
       " * we need this to avoid circular references\n",
       " * http://stackoverflow.com/a/24161582/3208463\n",
       " */\n",
       "function simpleKeys (original) {\n",
       "  return Object.keys(original).reduce(function (obj, key) {\n",
       "    if (typeof original[key] !== 'object')\n",
       "        obj[key] = original[key]\n",
       "    return obj;\n",
       "  }, {});\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.mouse_event = function(event, name) {\n",
       "    var canvas_pos = mpl.findpos(event)\n",
       "\n",
       "    if (name === 'button_press')\n",
       "    {\n",
       "        this.canvas.focus();\n",
       "        this.canvas_div.focus();\n",
       "    }\n",
       "\n",
       "    var x = canvas_pos.x * mpl.ratio;\n",
       "    var y = canvas_pos.y * mpl.ratio;\n",
       "\n",
       "    this.send_message(name, {x: x, y: y, button: event.button,\n",
       "                             step: event.step,\n",
       "                             guiEvent: simpleKeys(event)});\n",
       "\n",
       "    /* This prevents the web browser from automatically changing to\n",
       "     * the text insertion cursor when the button is pressed.  We want\n",
       "     * to control all of the cursor setting manually through the\n",
       "     * 'cursor' event from matplotlib */\n",
       "    event.preventDefault();\n",
       "    return false;\n",
       "}\n",
       "\n",
       "mpl.figure.prototype._key_event_extra = function(event, name) {\n",
       "    // Handle any extra behaviour associated with a key event\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.key_event = function(event, name) {\n",
       "\n",
       "    // Prevent repeat events\n",
       "    if (name == 'key_press')\n",
       "    {\n",
       "        if (event.which === this._key)\n",
       "            return;\n",
       "        else\n",
       "            this._key = event.which;\n",
       "    }\n",
       "    if (name == 'key_release')\n",
       "        this._key = null;\n",
       "\n",
       "    var value = '';\n",
       "    if (event.ctrlKey && event.which != 17)\n",
       "        value += \"ctrl+\";\n",
       "    if (event.altKey && event.which != 18)\n",
       "        value += \"alt+\";\n",
       "    if (event.shiftKey && event.which != 16)\n",
       "        value += \"shift+\";\n",
       "\n",
       "    value += 'k';\n",
       "    value += event.which.toString();\n",
       "\n",
       "    this._key_event_extra(event, name);\n",
       "\n",
       "    this.send_message(name, {key: value,\n",
       "                             guiEvent: simpleKeys(event)});\n",
       "    return false;\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.toolbar_button_onclick = function(name) {\n",
       "    if (name == 'download') {\n",
       "        this.handle_save(this, null);\n",
       "    } else {\n",
       "        this.send_message(\"toolbar_button\", {name: name});\n",
       "    }\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.toolbar_button_onmouseover = function(tooltip) {\n",
       "    this.message.textContent = tooltip;\n",
       "};\n",
       "mpl.toolbar_items = [[\"Home\", \"Reset original view\", \"fa fa-home icon-home\", \"home\"], [\"Back\", \"Back to  previous view\", \"fa fa-arrow-left icon-arrow-left\", \"back\"], [\"Forward\", \"Forward to next view\", \"fa fa-arrow-right icon-arrow-right\", \"forward\"], [\"\", \"\", \"\", \"\"], [\"Pan\", \"Pan axes with left mouse, zoom with right\", \"fa fa-arrows icon-move\", \"pan\"], [\"Zoom\", \"Zoom to rectangle\", \"fa fa-square-o icon-check-empty\", \"zoom\"], [\"\", \"\", \"\", \"\"], [\"Download\", \"Download plot\", \"fa fa-floppy-o icon-save\", \"download\"]];\n",
       "\n",
       "mpl.extensions = [\"eps\", \"jpeg\", \"pdf\", \"png\", \"ps\", \"raw\", \"svg\", \"tif\"];\n",
       "\n",
       "mpl.default_extension = \"png\";var comm_websocket_adapter = function(comm) {\n",
       "    // Create a \"websocket\"-like object which calls the given IPython comm\n",
       "    // object with the appropriate methods. Currently this is a non binary\n",
       "    // socket, so there is still some room for performance tuning.\n",
       "    var ws = {};\n",
       "\n",
       "    ws.close = function() {\n",
       "        comm.close()\n",
       "    };\n",
       "    ws.send = function(m) {\n",
       "        //console.log('sending', m);\n",
       "        comm.send(m);\n",
       "    };\n",
       "    // Register the callback with on_msg.\n",
       "    comm.on_msg(function(msg) {\n",
       "        //console.log('receiving', msg['content']['data'], msg);\n",
       "        // Pass the mpl event to the overridden (by mpl) onmessage function.\n",
       "        ws.onmessage(msg['content']['data'])\n",
       "    });\n",
       "    return ws;\n",
       "}\n",
       "\n",
       "mpl.mpl_figure_comm = function(comm, msg) {\n",
       "    // This is the function which gets called when the mpl process\n",
       "    // starts-up an IPython Comm through the \"matplotlib\" channel.\n",
       "\n",
       "    var id = msg.content.data.id;\n",
       "    // Get hold of the div created by the display call when the Comm\n",
       "    // socket was opened in Python.\n",
       "    var element = $(\"#\" + id);\n",
       "    var ws_proxy = comm_websocket_adapter(comm)\n",
       "\n",
       "    function ondownload(figure, format) {\n",
       "        window.open(figure.imageObj.src);\n",
       "    }\n",
       "\n",
       "    var fig = new mpl.figure(id, ws_proxy,\n",
       "                           ondownload,\n",
       "                           element.get(0));\n",
       "\n",
       "    // Call onopen now - mpl needs it, as it is assuming we've passed it a real\n",
       "    // web socket which is closed, not our websocket->open comm proxy.\n",
       "    ws_proxy.onopen();\n",
       "\n",
       "    fig.parent_element = element.get(0);\n",
       "    fig.cell_info = mpl.find_output_cell(\"<div id='\" + id + \"'></div>\");\n",
       "    if (!fig.cell_info) {\n",
       "        console.error(\"Failed to find cell for figure\", id, fig);\n",
       "        return;\n",
       "    }\n",
       "\n",
       "    var output_index = fig.cell_info[2]\n",
       "    var cell = fig.cell_info[0];\n",
       "\n",
       "};\n",
       "\n",
       "mpl.figure.prototype.handle_close = function(fig, msg) {\n",
       "    var width = fig.canvas.width/mpl.ratio\n",
       "    fig.root.unbind('remove')\n",
       "\n",
       "    // Update the output cell to use the data from the current canvas.\n",
       "    fig.push_to_output();\n",
       "    var dataURL = fig.canvas.toDataURL();\n",
       "    // Re-enable the keyboard manager in IPython - without this line, in FF,\n",
       "    // the notebook keyboard shortcuts fail.\n",
       "    IPython.keyboard_manager.enable()\n",
       "    $(fig.parent_element).html('<img src=\"' + dataURL + '\" width=\"' + width + '\">');\n",
       "    fig.close_ws(fig, msg);\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.close_ws = function(fig, msg){\n",
       "    fig.send_message('closing', msg);\n",
       "    // fig.ws.close()\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.push_to_output = function(remove_interactive) {\n",
       "    // Turn the data on the canvas into data in the output cell.\n",
       "    var width = this.canvas.width/mpl.ratio\n",
       "    var dataURL = this.canvas.toDataURL();\n",
       "    this.cell_info[1]['text/html'] = '<img src=\"' + dataURL + '\" width=\"' + width + '\">';\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.updated_canvas_event = function() {\n",
       "    // Tell IPython that the notebook contents must change.\n",
       "    IPython.notebook.set_dirty(true);\n",
       "    this.send_message(\"ack\", {});\n",
       "    var fig = this;\n",
       "    // Wait a second, then push the new image to the DOM so\n",
       "    // that it is saved nicely (might be nice to debounce this).\n",
       "    setTimeout(function () { fig.push_to_output() }, 1000);\n",
       "}\n",
       "\n",
       "mpl.figure.prototype._init_toolbar = function() {\n",
       "    var fig = this;\n",
       "\n",
       "    var nav_element = $('<div/>')\n",
       "    nav_element.attr('style', 'width: 100%');\n",
       "    this.root.append(nav_element);\n",
       "\n",
       "    // Define a callback function for later on.\n",
       "    function toolbar_event(event) {\n",
       "        return fig.toolbar_button_onclick(event['data']);\n",
       "    }\n",
       "    function toolbar_mouse_event(event) {\n",
       "        return fig.toolbar_button_onmouseover(event['data']);\n",
       "    }\n",
       "\n",
       "    for(var toolbar_ind in mpl.toolbar_items){\n",
       "        var name = mpl.toolbar_items[toolbar_ind][0];\n",
       "        var tooltip = mpl.toolbar_items[toolbar_ind][1];\n",
       "        var image = mpl.toolbar_items[toolbar_ind][2];\n",
       "        var method_name = mpl.toolbar_items[toolbar_ind][3];\n",
       "\n",
       "        if (!name) { continue; };\n",
       "\n",
       "        var button = $('<button class=\"btn btn-default\" href=\"#\" title=\"' + name + '\"><i class=\"fa ' + image + ' fa-lg\"></i></button>');\n",
       "        button.click(method_name, toolbar_event);\n",
       "        button.mouseover(tooltip, toolbar_mouse_event);\n",
       "        nav_element.append(button);\n",
       "    }\n",
       "\n",
       "    // Add the status bar.\n",
       "    var status_bar = $('<span class=\"mpl-message\" style=\"text-align:right; float: right;\"/>');\n",
       "    nav_element.append(status_bar);\n",
       "    this.message = status_bar[0];\n",
       "\n",
       "    // Add the close button to the window.\n",
       "    var buttongrp = $('<div class=\"btn-group inline pull-right\"></div>');\n",
       "    var button = $('<button class=\"btn btn-mini btn-primary\" href=\"#\" title=\"Stop Interaction\"><i class=\"fa fa-power-off icon-remove icon-large\"></i></button>');\n",
       "    button.click(function (evt) { fig.handle_close(fig, {}); } );\n",
       "    button.mouseover('Stop Interaction', toolbar_mouse_event);\n",
       "    buttongrp.append(button);\n",
       "    var titlebar = this.root.find($('.ui-dialog-titlebar'));\n",
       "    titlebar.prepend(buttongrp);\n",
       "}\n",
       "\n",
       "mpl.figure.prototype._root_extra_style = function(el){\n",
       "    var fig = this\n",
       "    el.on(\"remove\", function(){\n",
       "\tfig.close_ws(fig, {});\n",
       "    });\n",
       "}\n",
       "\n",
       "mpl.figure.prototype._canvas_extra_style = function(el){\n",
       "    // this is important to make the div 'focusable\n",
       "    el.attr('tabindex', 0)\n",
       "    // reach out to IPython and tell the keyboard manager to turn it's self\n",
       "    // off when our div gets focus\n",
       "\n",
       "    // location in version 3\n",
       "    if (IPython.notebook.keyboard_manager) {\n",
       "        IPython.notebook.keyboard_manager.register_events(el);\n",
       "    }\n",
       "    else {\n",
       "        // location in version 2\n",
       "        IPython.keyboard_manager.register_events(el);\n",
       "    }\n",
       "\n",
       "}\n",
       "\n",
       "mpl.figure.prototype._key_event_extra = function(event, name) {\n",
       "    var manager = IPython.notebook.keyboard_manager;\n",
       "    if (!manager)\n",
       "        manager = IPython.keyboard_manager;\n",
       "\n",
       "    // Check for shift+enter\n",
       "    if (event.shiftKey && event.which == 13) {\n",
       "        this.canvas_div.blur();\n",
       "        event.shiftKey = false;\n",
       "        // Send a \"J\" for go to next cell\n",
       "        event.which = 74;\n",
       "        event.keyCode = 74;\n",
       "        manager.command_mode();\n",
       "        manager.handle_keydown(event);\n",
       "    }\n",
       "}\n",
       "\n",
       "mpl.figure.prototype.handle_save = function(fig, msg) {\n",
       "    fig.ondownload(fig, null);\n",
       "}\n",
       "\n",
       "\n",
       "mpl.find_output_cell = function(html_output) {\n",
       "    // Return the cell and output element which can be found *uniquely* in the notebook.\n",
       "    // Note - this is a bit hacky, but it is done because the \"notebook_saving.Notebook\"\n",
       "    // IPython event is triggered only after the cells have been serialised, which for\n",
       "    // our purposes (turning an active figure into a static one), is too late.\n",
       "    var cells = IPython.notebook.get_cells();\n",
       "    var ncells = cells.length;\n",
       "    for (var i=0; i<ncells; i++) {\n",
       "        var cell = cells[i];\n",
       "        if (cell.cell_type === 'code'){\n",
       "            for (var j=0; j<cell.output_area.outputs.length; j++) {\n",
       "                var data = cell.output_area.outputs[j];\n",
       "                if (data.data) {\n",
       "                    // IPython >= 3 moved mimebundle to data attribute of output\n",
       "                    data = data.data;\n",
       "                }\n",
       "                if (data['text/html'] == html_output) {\n",
       "                    return [cell, data, j];\n",
       "                }\n",
       "            }\n",
       "        }\n",
       "    }\n",
       "}\n",
       "\n",
       "// Register the function which deals with the matplotlib target/channel.\n",
       "// The kernel may be null if the page has been refreshed.\n",
       "if (IPython.notebook.kernel != null) {\n",
       "    IPython.notebook.kernel.comm_manager.register_target('matplotlib', mpl.mpl_figure_comm);\n",
       "}\n"
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<img src=\"data:image/png;base64,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\" width=\"640\">"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.6/dist-packages/matplotlib/cbook/deprecation.py:107: MatplotlibDeprecationWarning: Adding an axes using the same arguments as a previous axes currently reuses the earlier instance.  In a future version, a new instance will always be created and returned.  Meanwhile, this warning can be suppressed, and the future behavior ensured, by passing a unique label to each axes instance.\n",
      "  warnings.warn(message, mplDeprecation, stacklevel=1)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n",
      "INFO:tensorflow:Calling model_fn.\n",
      "INFO:tensorflow:Done calling model_fn.\n",
      "INFO:tensorflow:Graph was finalized.\n",
      "INFO:tensorflow:Restoring parameters from ./storage/models/geolearnv3/model.ckpt-550\n",
      "INFO:tensorflow:Running local_init_op.\n",
      "INFO:tensorflow:Done running local_init_op.\n"
     ]
    }
   ],
   "source": [
    "%matplotlib notebook\n",
    "import ipywidgets as widgets\n",
    "from IPython.display import display\n",
    "\n",
    "def click(*args):\n",
    "    images, labels = make_examples(size, 1)\n",
    "    predictions = position_estimator.predict(lambda: tf.data.Dataset.from_tensor_slices((images, labels)).batch(1))\n",
    "    image, label, prediction = images[0], labels[0], next(predictions)\n",
    "    plt.subplot(3,2,1)\n",
    "    plt.imshow(image)\n",
    "    plt.subplot(3,2,2)\n",
    "    plt.imshow(label_to_image(label))\n",
    "    label_layers = np.moveaxis(label, 2, 0)\n",
    "    prediction_layers = np.moveaxis(prediction, 2, 0)\n",
    "\n",
    "    for idx in range(label_layers.shape[0]):\n",
    "        offset = 3 + idx*2\n",
    "        plt.subplot(3, 2, offset)\n",
    "        plt.imshow(label_layers[idx])\n",
    "        plt.subplot(3, 2, offset+1)\n",
    "        plt.imshow(prediction_layers[idx])\n",
    "\n",
    "\n",
    "button = widgets.Button(description='Check')\n",
    "button.on_click(click)\n",
    "display(button)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}