output0 adjustment

app.py

@@ -46,38 +46,115 @@ class DetectionResult:
             )
         )
 
-def mask_to_min_max(mask):
-    """Convert mask to min and max coordinates of the bounding box."""
+def annotate(image: Union[Image.Image, np.ndarray], detection_results: List[DetectionResult]) -> np.ndarray:
+    image_cv2 = np.array(image) if isinstance(image, Image.Image) else image
+    image_cv2 = cv2.cvtColor(image_cv2, cv2.COLOR_RGB2BGR)
+
+    for detection in detection_results:
+        label = detection.label
+        score = detection.score
+        box = detection.box
+        mask = detection.mask
+        color = np.random.randint(0, 256, size=3).tolist()
+
+        cv2.rectangle(image_cv2, (box.xmin, box.ymin), (box.xmax, box.ymax), color, 2)
+        cv2.putText(image_cv2, f'{label}: {score:.2f}', (box.xmin, box.ymin - 10),
+                    cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)
+
+        if mask is not None:
+            mask_uint8 = (mask * 255).astype(np.uint8)
+            contours, _ = cv2.findContours(mask_uint8, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
+            cv2.drawContours(image_cv2, contours, -1, color, 2)
+
+    return cv2.cvtColor(image_cv2, cv2.COLOR_BGR2RGB)
+
+def plot_detections(image: Union[Image.Image, np.ndarray], detections: List[DetectionResult]) -> np.ndarray:
+    annotated_image = annotate(image, detections)
+    return annotated_image
+
+def load_image(image: Union[str, Image.Image]) -> Image.Image:
+    if isinstance(image, str) and image.startswith("http"):
+        image = Image.open(requests.get(image, stream=True).raw).convert("RGB")
+    elif isinstance(image, str):
+        image = Image.open(image).convert("RGB")
+    else:
+        image = image.convert("RGB")
+    return image
+
+def get_boxes(detection_results: List[DetectionResult]) -> List[List[List[float]]]:
+    boxes = []
+    for result in detection_results:
+        xyxy = result.box.xyxy
+        boxes.append(xyxy)
+    return [boxes]
+
+def mask_to_polygon(mask: np.ndarray) -> np.ndarray:
+    contours, _ = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
+    if len(contours) == 0:
+        return np.array([])
+    largest_contour = max(contours, key=cv2.contourArea)
+    return largest_contour
+
+def refine_masks(masks: torch.BoolTensor, polygon_refinement: bool = False) -> List[np.ndarray]:
+    masks = masks.cpu().float().permute(0, 2, 3, 1).mean(axis=-1).numpy().astype(np.uint8)
+    masks = (masks > 0).astype(np.uint8)
+    if polygon_refinement:
+        for idx, mask in enumerate(masks):
+            shape = mask.shape
+            polygon = mask_to_polygon(mask)
+            masks[idx] = cv2.fillPoly(np.zeros(shape, dtype=np.uint8), [polygon], 1)
+    return list(masks)
+
+@spaces.GPU
+def detect(image: Image.Image, labels: List[str], threshold: float = 0.3, detector_id: Optional[str] = None) -> List[Dict[str, Any]]:
+    detector_id = detector_id if detector_id else "IDEA-Research/grounding-dino-base"
+    object_detector = pipeline(model=detector_id, task="zero-shot-object-detection", device="cuda")
+    labels = [label if label.endswith(".") else label+"." for label in labels]
+    results = object_detector(image, candidate_labels=labels, threshold=threshold)
+    return [DetectionResult.from_dict(result) for result in results]
+
+@spaces.GPU
+def segment(image: Image.Image, detection_results: List[DetectionResult], polygon_refinement: bool = False, segmenter_id: Optional[str] = None) -> List[DetectionResult]:
+    segmenter_id = segmenter_id if segmenter_id else "martintmv/InsectSAM"
+    segmentator = AutoModelForMaskGeneration.from_pretrained(segmenter_id).to("cuda")
+    processor = AutoProcessor.from_pretrained(segmenter_id)
+    boxes = get_boxes(detection_results)
+    inputs = processor(images=image, input_boxes=boxes, return_tensors="pt").to("cuda")
+    outputs = segmentator(**inputs)
+    masks = processor.post_process_masks(masks=outputs.pred_masks, original_sizes=inputs.original_sizes, reshaped_input_sizes=inputs.reshaped_input_sizes)[0]
+    masks = refine_masks(masks, polygon_refinement)
+    for detection_result, mask in zip(detection_results, masks):
+        detection_result.mask = mask
+    return detection_results
+
+def grounded_segmentation(image: Union[Image.Image, str], labels: List[str], threshold: float = 0.3, polygon_refinement: bool = False, detector_id: Optional[str] = None, segmenter_id: Optional[str] = None) -> Tuple[np.ndarray, List[DetectionResult]]:
+    image = load_image(image)
+    detections = detect(image, labels, threshold, detector_id)
+    detections = segment(image, detections, polygon_refinement, segmenter_id)
+    return np.array(image), detections
+
+def mask_to_min_max(mask: np.ndarray) -> Tuple[int, int, int, int]:
     y, x = np.where(mask)
-    xmin, xmax = x.min(), x.max()
-    ymin, ymax = y.min(), y.max()
-    return xmin, ymin, xmax, ymax
+    return x.min(), y.min(), x.max(), y.max()
 
-def extract_and_paste_insect(original_image, detection, background):
+def extract_and_paste_insect(original_image: np.ndarray, detection: DetectionResult, background: np.ndarray) -> None:
     mask = detection.mask
     xmin, ymin, xmax, ymax = mask_to_min_max(mask)
     insect_crop = original_image[ymin:ymax, xmin:xmax]
     mask_crop = mask[ymin:ymax, xmin:xmax]
 
     insect = cv2.bitwise_and(insect_crop, insect_crop, mask=mask_crop)
-    x_offset, y_offset = detection.box.xmin, detection.box.ymin
-    x_end, y_end = x_offset + insect.shape[1], y_offset + insect.shape[0]
 
-    inverse_mask = cv2.bitwise_not(mask_crop)
-    bg_region = background[y_offset:y_end, x_offset:x_end]
-    bg_ready = cv2.bitwise_and(bg_region, bg_region, mask=inverse_mask)
-    combined = cv2.add(insect, bg_ready)
-    background[y_offset:y_end, x_offset:x_end] = combined
+    x_offset, y_offset = xmin, ymin
+    x_end, y_end = x_offset + insect.shape[1], y_offset + insect.shape[0]
 
-def create_yellow_background_with_insects(image, detections):
-    # Create a plain yellow background
-    yellow_background = np.full_like(image, (0, 255, 255), dtype=np.uint8)
+    background[y_offset:y_end, x_offset:x_end] = insect
 
-    # Extract and paste each insect on the background
+def create_yellow_background_with_insects(image: np.ndarray, detections: List[DetectionResult]) -> np.ndarray:
+    yellow_background = np.full((image.shape[0], image.shape[1], 3), (0, 255, 255), dtype=np.uint8)
     for detection in detections:
         if detection.mask is not None:
             extract_and_paste_insect(image, detection, yellow_background)
-
     return yellow_background
 
 def run_length_encoding(mask):