Add yolov8 to SAHI (#833)

Co-authored-by: Your Name <[email protected]>

.github/workflows/ci.yml

@@ -101,6 +101,10 @@ jobs:
         run: >
           pip install pycocotools==2.0.6
 
+      - name: Install ultralytics
+        run: >
+          pip install ultralytics==8.0.43
+
       - name: Unittest for SAHI+YOLOV5/MMDET/Detectron2 on all platforms
         run: |
           python -m unittest

.github/workflows/ci_torch1.10.yml

@@ -108,6 +108,10 @@ jobs:
         run: >
           pip install pycocotools==2.0.6
 
+      - name: Install ultralytics
+        run: >
+          pip install ultralytics==8.0.43
+
       - name: Unittest for SAHI+YOLOV5/MMDET/Detectron2 on all platforms
         run: |
           python -m unittest

.github/workflows/package_testing.yml

@@ -83,6 +83,10 @@ jobs:
         run: >
           pip install pycocotools==2.0.6
 
+      - name: Install ultralytics
+        run: >
+          pip install ultralytics==8.0.43
+
       - name: Install latest SAHI package
         run: >
           pip install --upgrade --force-reinstall sahi

demo/inference_for_yolov5.ipynb

@@ -636,7 +636,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3.8.8 ('sahi')",
+   "display_name": "test",
    "language": "python",
    "name": "python3"
   },
@@ -650,11 +650,11 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.8"
+   "version": "3.8.15"
   },
   "vscode": {
    "interpreter": {
-    "hash": "f2680c47b11e1b3873482f0b7ab37c9292181f84f7b4413a77eb41d52d22c05d"
+    "hash": "244b47d5824a96a4079632e50977464d968e13d2c337f65c905f8da81a0b4f95"
    }
   }
  },

sahi/auto_model.py

@@ -3,6 +3,7 @@
 from sahi.utils.file import import_model_class
 
 MODEL_TYPE_TO_MODEL_CLASS_NAME = {
+    "yolov8": "Yolov8DetectionModel",
     "mmdet": "MmdetDetectionModel",
     "yolov5": "Yolov5DetectionModel",
     "detectron2": "Detectron2DetectionModel",

sahi/models/yolov8.py

@@ -0,0 +1,160 @@
+# OBSS SAHI Tool
+# Code written by AnNT, 2023.
+
+import logging
+from typing import Any, Dict, List, Optional
+
+import numpy as np
+
+logger = logging.getLogger(__name__)
+
+from sahi.models.base import DetectionModel
+from sahi.prediction import ObjectPrediction
+from sahi.utils.compatibility import fix_full_shape_list, fix_shift_amount_list
+from sahi.utils.import_utils import check_requirements
+
+
+class Yolov8DetectionModel(DetectionModel):
+    def check_dependencies(self) -> None:
+        check_requirements(["ultralytics"])
+
+    def load_model(self):
+        """
+        Detection model is initialized and set to self.model.
+        """
+
+        from ultralytics import YOLO
+
+        try:
+            model = YOLO(self.model_path)
+            model.to(self.device)
+            self.set_model(model)
+        except Exception as e:
+            raise TypeError("model_path is not a valid yolov8 model path: ", e)
+
+    def set_model(self, model: Any):
+        """
+        Sets the underlying YOLOv8 model.
+        Args:
+            model: Any
+                A YOLOv8 model
+        """
+
+        # if model.__class__.__module__ not in ["yolov5.models.common", "models.common"]:
+        #     raise Exception(f"Not a yolov5 model: {type(model)}")
+
+        # model.conf = self.confidence_threshold
+        self.model = model
+
+        # set category_mapping
+        if not self.category_mapping:
+            category_mapping = {str(ind): category_name for ind, category_name in enumerate(self.category_names)}
+            self.category_mapping = category_mapping
+
+    def perform_inference(self, image: np.ndarray):
+        """
+        Prediction is performed using self.model and the prediction result is set to self._original_predictions.
+        Args:
+            image: np.ndarray
+                A numpy array that contains the image to be predicted. 3 channel image should be in RGB order.
+        """
+
+        # Confirm model is loaded
+        if self.model is None:
+            raise ValueError("Model is not loaded, load it by calling .load_model()")
+        prediction_result = self.model(image, verbose=False)
+        prediction_result = [
+            result.boxes.boxes[result.boxes.boxes[:, 4] >= self.confidence_threshold] for result in prediction_result
+        ]
+
+        self._original_predictions = prediction_result
+
+    @property
+    def category_names(self):
+        return self.model.names.values()
+
+    @property
+    def num_categories(self):
+        """
+        Returns number of categories
+        """
+        return len(self.model.names)
+
+    @property
+    def has_mask(self):
+        """
+        Returns if model output contains segmentation mask
+        """
+        return False  # fix when yolov5 supports segmentation models
+
+    def _create_object_prediction_list_from_original_predictions(
+        self,
+        shift_amount_list: Optional[List[List[int]]] = [[0, 0]],
+        full_shape_list: Optional[List[List[int]]] = None,
+    ):
+        """
+        self._original_predictions is converted to a list of prediction.ObjectPrediction and set to
+        self._object_prediction_list_per_image.
+        Args:
+            shift_amount_list: list of list
+                To shift the box and mask predictions from sliced image to full sized image, should
+                be in the form of List[[shift_x, shift_y],[shift_x, shift_y],...]
+            full_shape_list: list of list
+                Size of the full image after shifting, should be in the form of
+                List[[height, width],[height, width],...]
+        """
+        original_predictions = self._original_predictions
+
+        # compatilibty for sahi v0.8.15
+        shift_amount_list = fix_shift_amount_list(shift_amount_list)
+        full_shape_list = fix_full_shape_list(full_shape_list)
+
+        # handle all predictions
+        object_prediction_list_per_image = []
+        for image_ind, image_predictions_in_xyxy_format in enumerate(original_predictions):
+            shift_amount = shift_amount_list[image_ind]
+            full_shape = None if full_shape_list is None else full_shape_list[image_ind]
+            object_prediction_list = []
+
+            # process predictions
+            for prediction in image_predictions_in_xyxy_format.cpu().detach().numpy():
+                x1 = prediction[0]
+                y1 = prediction[1]
+                x2 = prediction[2]
+                y2 = prediction[3]
+                bbox = [x1, y1, x2, y2]
+                score = prediction[4]
+                category_id = int(prediction[5])
+                category_name = self.category_mapping[str(category_id)]
+
+                # fix negative box coords
+                bbox[0] = max(0, bbox[0])
+                bbox[1] = max(0, bbox[1])
+                bbox[2] = max(0, bbox[2])
+                bbox[3] = max(0, bbox[3])
+
+                # fix out of image box coords
+                if full_shape is not None:
+                    bbox[0] = min(full_shape[1], bbox[0])
+                    bbox[1] = min(full_shape[0], bbox[1])
+                    bbox[2] = min(full_shape[1], bbox[2])
+                    bbox[3] = min(full_shape[0], bbox[3])
+
+                # ignore invalid predictions
+                if not (bbox[0] < bbox[2]) or not (bbox[1] < bbox[3]):
+                    logger.warning(f"ignoring invalid prediction with bbox: {bbox}")
+                    continue
+
+                object_prediction = ObjectPrediction(
+                    bbox=bbox,
+                    category_id=category_id,
+                    score=score,
+                    bool_mask=None,
+                    category_name=category_name,
+                    shift_amount=shift_amount,
+                    full_shape=full_shape,
+                )
+                object_prediction_list.append(object_prediction)
+            object_prediction_list_per_image.append(object_prediction_list)
+
+        self._object_prediction_list_per_image = object_prediction_list_per_image

sahi/utils/yolov8.py

@@ -0,0 +1,43 @@
+import urllib.request
+from os import path
+from pathlib import Path
+from typing import Optional
+
+
+class Yolov8TestConstants:
+    YOLOV8N_MODEL_URL = "https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt"
+    YOLOV8N_MODEL_PATH = "tests/data/models/yolov8/yolov8n.pt"
+
+    YOLOV8S_MODEL_URL = "https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt"
+    YOLOV8S_MODEL_PATH = "tests/data/models/yolov8/yolov8s.pt"
+
+    YOLOV8M_MODEL_URL = "https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt"
+    YOLOV8M_MODEL_PATH = "tests/data/models/yolov8/yolov8m.pt"
+
+
+def download_yolov8n_model(destination_path: Optional[str] = None):
+
+    if destination_path is None:
+        destination_path = Yolov8TestConstants.YOLOV8N_MODEL_PATH
+
+    Path(destination_path).parent.mkdir(parents=True, exist_ok=True)
+
+    if not path.exists(destination_path):
+        urllib.request.urlretrieve(
+            Yolov8TestConstants.YOLOV8N_MODEL_URL,
+            destination_path,
+        )
+
+
+def download_yolov8s_model(destination_path: Optional[str] = None):
+
+    if destination_path is None:
+        destination_path = Yolov8TestConstants.YOLOV8S_MODEL_PATH
+
+    Path(destination_path).parent.mkdir(parents=True, exist_ok=True)
+
+    if not path.exists(destination_path):
+        urllib.request.urlretrieve(
+            Yolov8TestConstants.YOLOV8S_MODEL_URL,
+            destination_path,
+        )