fix typos (#434)

* fix typos

* fix indentation

lmnet/docs/source/pre_processor.rst

@@ -4,7 +4,7 @@ pre_processor module
 .. currentmodule:: pre_processor
 
 .. automodule:: pre_processor
-    :members: DivideBy255, LetterBoxes, PerImageLinerQuantize, PerImageStandardization, Resize, ResizeWithGtBoxes, ResizeWithMask, per_image_linear_quantize, per_image_standardization, resize, resize_keep_ratio_with_gt_boxes, resize_with_gt_boxes, square
+    :members: DivideBy255, LetterBoxes, PerImageLinearQuantize, PerImageStandardization, Resize, ResizeWithGtBoxes, ResizeWithMask, per_image_linear_quantize, per_image_standardization, resize, resize_keep_ratio_with_gt_boxes, resize_with_gt_boxes, square
     :undoc-members:
     :show-inheritance:
     :member-order: bysource
@@ -19,7 +19,7 @@ pre_processor module
 
         DivideBy255
         LetterBoxes
-        PerImageLinerQuantize
+        PerImageLinearQuantize
         PerImageStandardization
         Resize
         ResizeWithGtBoxes

lmnet/lmnet/blocks.py

@@ -41,7 +41,7 @@ def activation(x): return tf.nn.leaky_relu(x, alpha=0.1, name="leaky_relu")
                       activation=None, use_bias=False, data_format=channel_data_format,
                       kernel_initializer=tf.contrib.layers.variance_scaling_initializer(),)  # he initializer
 
-        # TODO(wakisaka): Should be the same as darknet batrch norm.
+        # TODO(wakisaka): Should be the same as darknet batch norm.
         # https://github.com/tensorflow/tensorflow/blob/r1.1/tensorflow/contrib/layers/python/layers/layers.py
         # https://github.com/pjreddie/darknet/blob/8215a8864d4ad07e058acafd75b2c6ff6600b9e8/src/batchnorm_layer.c#L135
         batch_normed = batch_norm("bn", conv, is_training=is_training, decay=0.99, scale=True, center=True,
@@ -154,7 +154,7 @@ def conv_bn_act(
         is_training (tf.constant): Flag if training or not for batch norm.
         activation (callable): Activation function.
         batch_norm_decay (float): Batch norm decay rate.
-        data_format (string):  Fromat for inputs data. NHWC or NCHW.
+        data_format (string):  Format for inputs data. NHWC or NCHW.
         enable_detail_summary (bool): Flag for summarize feature maps for each operation on tensorboard.
     Returns:
         output (tf.Tensor): Output of this block.
@@ -276,7 +276,7 @@ def densenet_group(
         data_format="NHWC",
         enable_detail_summary=False,
 ):
-    """Group of Densent blocks.
+    """Group of Densenet blocks.
 
     paper: https://arxiv.org/abs/1608.06993
     In the original paper, this method is called `Dense block` which consists of some 1x1 and 3x3 conv blocks
@@ -286,7 +286,7 @@ def densenet_group(
     Args:
         name (str): Block name, as scope name.
         inputs (tf.Tensor): Inputs.
-        num_blocks (int): Number of dense blocks which consits of 1x1 and 3x3 cov.
+        num_blocks (int): Number of dense blocks which consist of 1x1 and 3x3 conv.
         growth_rate (int): How many filters (out channel) to add each layer.
         bottleneck_rate (int): The factor to be calculated bottle-neck 1x1 conv output channel.
             `bottleneck_channel = growth_rate * bottleneck_rate`.
@@ -296,7 +296,7 @@ def densenet_group(
         activation (callable): Activation function.
         batch_norm_decay (float): Batch norm decay rate.
         enable_detail_summary (bool): Flag for summarize feature maps for each operation on tensorboard.
-        data_format (string):  Fromat for inputs data. NHWC or NCHW.
+        data_format (string):  Format for inputs data. NHWC or NCHW.
     Returns:
         tf.Tensor: Output of current  block.
     """

lmnet/lmnet/datasets/dataset_iterator.py

@@ -64,7 +64,7 @@ def _apply_augmentations(dataset, image, label):
     else:
         label = sample['label']
 
-    # FIXME(tokunaga): dataset should not have thier own data format
+    # FIXME(tokunaga): dataset should not have their own data format
     if dataset.data_format == "NCHW":
         image = np.transpose(image, [2, 0, 1])
 
@@ -177,7 +177,7 @@ def __init__(self, dataset, seed, shuffle=True):
         self.data_ids = []
 
     def _gen_ids(self, size):
-        """Generate ids which's length is `size`."""
+        """Generate ids which length is `size`."""
         for _ in range(0, size):
             # when data_ids is empty, fill and shuffle.
             if len(self.data_ids) == 0:

lmnet/lmnet/datasets/open_images_v4.py

@@ -118,7 +118,7 @@ def classes(self):
     @property
     @functools.lru_cache(maxsize=None)
     def _target_labels(self):
-        """Map of {csv raw label name: Be mapped taregt label name}. """
+        """Map of {csv raw label name: Be mapped target label name}. """
 
         target_labels = dict(self._make_target_labels())
         return target_labels

lmnet/lmnet/networks/base.py

@@ -51,7 +51,7 @@ def __init__(
     ):
 
         if data_format not in ["NCHW", "NHWC"]:
-            raise RuntimeError("data format {} shodul be in ['NCHW', 'NHWC]'.".format(data_format))
+            raise RuntimeError("data format {} should be in ['NCHW', 'NHWC]'.".format(data_format))
 
         self.is_debug = is_debug
         self.optimizer_class = optimizer_class

lmnet/lmnet/networks/classification/base.py

@@ -126,7 +126,7 @@ def _heatmaps(self, target_feature_map):
 
         results = []
 
-        # shpae: [batch_size, height, width, num_classes]
+        # shape: [batch_size, height, width, num_classes]
         heatmap = tf.image.resize_images(
             target_feature_map, [self.image_size[0], self.image_size[1]],
             method=tf.image.ResizeMethod.BICUBIC,

lmnet/lmnet/networks/object_detection/yolo_v1.py

@@ -672,10 +672,10 @@ def _gt_boxes_to_cell(self, gt_boxes_list):
         Return:
         cell_gt_boxes: Tensor [batch_size, cell_size, cell_size, 4(center_x, center_y, w, h)].
             copy from non dummy gt boxes coodinate to corresponding cell.
-        object_maskes: Tensor [batch_size, cell_size, cell_size, 1]. the cell that has gt boxes is 1, none is 0.
+        object_masks: Tensor [batch_size, cell_size, cell_size, 1]. the cell that has gt boxes is 1, none is 0.
         """
         cell_gt_boxes = []
-        object_maskes = []
+        object_masks = []
         for batch_index in range(self.batch_size):
             i = tf.constant(0)
             gt_boxes = gt_boxes_list[batch_index, :, :]
@@ -689,12 +689,12 @@ def _gt_boxes_to_cell(self, gt_boxes_list):
             )
 
             cell_gt_boxes.append(result_cell_gt_box)
-            object_maskes.append(result_object_mask)
+            object_masks.append(result_object_mask)
 
         cell_gt_boxes = tf.stack(cell_gt_boxes)
-        object_maskes = tf.stack(object_maskes)
+        object_masks = tf.stack(object_masks)
 
-        return cell_gt_boxes, object_maskes
+        return cell_gt_boxes, object_masks
 
     def __call__(self, predict_classes, predict_confidence, predict_boxes, gt_boxes):
         """Loss function.
@@ -830,7 +830,7 @@ def summary_boxes(tag, images, boxes, image_size, max_outputs=3):
 
 
 def format_XYWH_to_CXCYWH(boxes, axis=1):
-    """Format form (x, y, w, h) to (center_x, center_y, w, h) along specific dimention.
+    """Format form (x, y, w, h) to (center_x, center_y, w, h) along specific dimension.
 
     Args:
     boxes :a Tensor include boxes. [:, 4(x, y, w, h)]
@@ -846,7 +846,7 @@ def format_XYWH_to_CXCYWH(boxes, axis=1):
 
 
 def format_CXCYWH_to_XYWH(boxes, axis=1):
-    """Format form (center_x, center_y, w, h) to (x, y, w, h) along specific dimention.
+    """Format form (center_x, center_y, w, h) to (x, y, w, h) along specific dimension.
 
     Args:
     boxes: A tensor include boxes. [:, 4(x, y, w, h)]
@@ -862,7 +862,7 @@ def format_CXCYWH_to_XYWH(boxes, axis=1):
 
 
 def format_CXCYWH_to_YX(inputs, axis=1):
-    """Format from (x, y, w, h) to (y1, x1, y2, x2) boxes along specific dimention.
+    """Format from (x, y, w, h) to (y1, x1, y2, x2) boxes along specific dimension.
 
     Args:
       inputs: a Tensor include boxes.
@@ -880,7 +880,7 @@ def format_CXCYWH_to_YX(inputs, axis=1):
 
 
 def format_XYWH_to_YX(inputs, axis=1):
-    """Format from (x, y, w, h) to (y1, x1, y2, x2) boxes along specific dimention.
+    """Format from (x, y, w, h) to (y1, x1, y2, x2) boxes along specific dimension.
 
     Args:
       inputs: a Tensor include boxes.