Update app.py

app.py

@@ -6,95 +6,67 @@ import cv2
 from PIL import Image
 from huggingface_hub import hf_hub_download
 
-# Hugging Face model repo
 HF_REPO_ID = "myang4218/cellposemodel"
 
-# Model filename options
 MODEL_OPTIONS = {
     "Hemocytometer Model": "hemocytometermodel.npy",
     "General Model": "generalmodel.npy"
 }
 
-# Cache loaded models
 loaded_models = {}
-print("Gradio version:", gr.__version__)
 
 @spaces.GPU
-def segment_and_count(image, box, model_choice):
-    # Download and load selected model
+def segment_and_count(image_with_crop, model_choice):
+    # Extract image and optional crop region
+    image = image_with_crop["image"]
+    crop_coords = image_with_crop.get("crop")
+
+    if crop_coords:
+        # Crop the image if a region was selected
+        x0, y0, x1, y1 = map(int, crop_coords)
+        image = image.crop((x0, y0, x1, y1))
+
     model_filename = MODEL_OPTIONS[model_choice]
     model_path = hf_hub_download(repo_id=HF_REPO_ID, filename=model_filename)
-    
     if model_filename in loaded_models:
         model = loaded_models[model_filename]
     else:
         model = models.CellposeModel(gpu=True, pretrained_model=model_path)
         loaded_models[model_filename] = model
 
-    # Get ROI coordinates from selection box
-    if box is None:
-        # No box selected – process entire image
-        roi_pil = image
-        x, y = 0, 0
-    else:
-        x, y = int(box["x"]), int(box["y"])
-        w, h = int(box["width"]), int(box["height"])
-        roi_pil = image.crop((x, y, x + w, y + h))
-
-    # Convert cropped region to NumPy
-    roi_np = np.array(roi_pil)
+    image_np = np.array(image)
 
-    # Convert to RGB if needed
-    if len(roi_np.shape) == 2:
-        roi_np = cv2.cvtColor(roi_np, cv2.COLOR_GRAY2RGB)
-    elif roi_np.shape[2] == 4:
-        roi_np = cv2.cvtColor(roi_np, cv2.COLOR_RGBA2RGB)
+    # Convert grayscale or RGBA to RGB
+    if len(image_np.shape) == 2:
+        image_np = cv2.cvtColor(image_np, cv2.COLOR_GRAY2RGB)
+    elif image_np.shape[2] == 4:
+        image_np = cv2.cvtColor(image_np, cv2.COLOR_RGBA2RGB)
 
-    # Run Cellpose on cropped ROI
-    masks, flows, styles = model.eval(roi_np, diameter=None, channels=[0, 0])
-    cell_count = len(np.unique(masks)) - 1  # Exclude background
+    # Run Cellpose
+    masks, flows, styles = model.eval(image_np, diameter=None, channels=[0, 0])
+    cell_count = len(np.unique(masks)) - 1  # exclude background
 
-    # Create colored overlay for ROI
-    overlay_roi = roi_np.copy().astype(np.float32)
+    # Overlay visualization
+    overlay = image_np.copy().astype(np.float32)
     if masks.max() > 0:
         np.random.seed(42)
         colors = np.random.randint(0, 255, size=(masks.max() + 1, 3))
         colors[0] = [0, 0, 0]
         colored_mask = colors[masks]
-        alpha = 0.4
-        overlay_roi = (1 - alpha) * overlay_roi + alpha * colored_mask
+        overlay = (1 - 0.4) * overlay + 0.4 * colored_mask
 
-    overlay_roi = np.clip(overlay_roi, 0, 255).astype(np.uint8)
+    overlay = np.clip(overlay, 0, 255).astype(np.uint8)
+    overlay_image = Image.fromarray(overlay)
 
-    # Prepare final overlay image
-    full_overlay = np.array(image).astype(np.float32)
-    if full_overlay.shape[2] == 4:
-        full_overlay = cv2.cvtColor(full_overlay, cv2.COLOR_RGBA2RGB)
-
-    # Paste the overlay ROI back onto the full image
-    h, w = overlay_roi.shape[:2]
-    full_overlay[y:y + h, x:x + w] = overlay_roi
+    return cell_count, overlay_image
 
-    # Convert back to PIL for output
-    overlay_image = Image.fromarray(full_overlay.astype(np.uint8))
+# Gradio Blocks Interface
+with gr.Blocks() as demo:
+    gr.Markdown("## 🧫 Cell Counter with Cellpose")
 
-    return cell_count, overlay_image
+    with gr.Row():
+        image_input = gr.Image(type="pil", label="Microscopy Image", tool="select")
+        model_dropdown = gr.Dropdown(choices=list(MODEL_OPTIONS.keys()), label="Select Model", value="Hemocytometer Model")
 
+    run_button = gr.Button("
 
-# Gradio interface
-demo = gr.Interface(
-    fn=segment_and_count,
-    inputs=[
-        gr.Image(type="pil", label="Microscopy Image", tool="select"),
-        gr.Dropdown(choices=list(MODEL_OPTIONS.keys()), label="Select Model", value="Hemocytometer Model")
-    ],
-    outputs=[
-        gr.Number(label="Number of Cells"),
-        gr.Image(type="pil", label="Segmented Overlay")
-    ],
-    title="Cell Counter with Cellpose",
-    description="Upload a microscopy image and optionally select a region to segment cells using Cellpose."
-)
-
-if __name__ == "__main__":
-    demo.launch()