a

app.py

@@ -11,6 +11,7 @@ from gradio_image_prompter import ImagePrompter
 from PIL import Image, ImageDraw
 import numpy as np
 from sam2.sam2_image_predictor import SAM2ImagePredictor
+from sam2_mask import create_sam2_tab
 import subprocess
 
 subprocess.run("rm -rf /data-nvme/zerogpu-offload/*", env={}, shell=True)
@@ -557,6 +558,8 @@ with gr.Blocks(css=css, fill_height=True) as demo:
                         use_as_input_button_outpaint = gr.Button("Use as Input Image", visible=False)
                         history_gallery = gr.Gallery(label="History", columns=6, object_fit="contain", interactive=False)
                         preview_image = gr.Image(label="Preview")
+        with gr.TabItem("SAM2 Masking"):
+            input_image, points_map, output_result_mask = create_sam2_tab()
         with gr.TabItem("SAM2 Mask"):
             gr.Markdown("# Object Segmentation with SAM2")
             gr.Markdown(
@@ -571,9 +574,9 @@ with gr.Blocks(css=css, fill_height=True) as demo:
                     upload_image_input = ImagePrompter(show_label=False)
                 with gr.Column():
                     image_output = gr.Image(label="Segmented Image", type="pil", height=400)
-            
+                with gr.Row():
                 # Button to trigger the prediction
-                predict_button = gr.Button("Predict Mask")
+                    predict_button = gr.Button("Predict Mask")
                 
                 # Define the action triggered by the predict button
                 predict_button.click(

sam2_mask.py

@@ -0,0 +1,195 @@
+import spaces
+import gradio as gr
+import os
+os.environ["TORCH_CUDNN_SDPA_ENABLED"] = "1"
+import torch
+import numpy as np
+import cv2
+import matplotlib.pyplot as plt
+from PIL import Image, ImageFilter
+from sam2.build_sam import build_sam2
+from sam2.sam2_image_predictor import SAM2ImagePredictor
+from gradio_image_prompter import ImagePrompter
+
+def preprocess_image(image):
+    return image, gr.State([]), gr.State([]), image
+
+def get_point(point_type, tracking_points, trackings_input_label, first_frame_path, evt: gr.SelectData):
+    print(f"You selected {evt.value} at {evt.index} from {evt.target}")
+    
+    # Extract x, y coordinates from evt.index
+    x, y = evt.index
+    
+    # Add the point as [x, y]
+    tracking_points.append([x, y])
+    print(f"TRACKING POINTS: {tracking_points}")
+    
+    if point_type == "include":
+        trackings_input_label.append(1)
+    elif point_type == "exclude":
+        trackings_input_label.append(0)
+    print(f"TRACKING INPUT LABELS: {trackings_input_label}")
+    
+    # Open the image and get its dimensions
+    transparent_background = Image.open(first_frame_path).convert('RGBA')
+    w, h = transparent_background.size
+    
+    # Define the circle radius as a fraction of the smaller dimension
+    fraction = 0.02  # You can adjust this value as needed
+    radius = int(fraction * min(w, h))
+    
+    # Create a transparent layer to draw on
+    transparent_layer = np.zeros((h, w, 4), dtype=np.uint8)
+    
+    for index, track in enumerate(tracking_points):
+        if trackings_input_label[index] == 1:
+            cv2.circle(transparent_layer, tuple(track), radius, (0, 255, 0, 255), -1)
+        else:
+            cv2.circle(transparent_layer, tuple(track), radius, (255, 0, 0, 255), -1)
+    
+    # Convert the transparent layer back to an image
+    transparent_layer = Image.fromarray(transparent_layer, 'RGBA')
+    selected_point_map = Image.alpha_composite(transparent_background, transparent_layer)
+    
+    return tracking_points, trackings_input_label, selected_point_map
+
+def show_mask(mask, ax, random_color=False, borders=True):
+    if random_color:
+        color = np.concatenate([np.random.random(3), np.array([0.6])], axis=0)
+    else:
+        color = np.array([30/255, 144/255, 255/255, 0.6])
+    h, w = mask.shape[-2:]
+    mask = mask.astype(np.uint8)
+    mask_image = mask.reshape(h, w, 1) * color.reshape(1, 1, -1)
+    if borders:
+        import cv2
+        contours, _ = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
+        # Try to smooth contours
+        contours = [cv2.approxPolyDP(contour, epsilon=0.01, closed=True) for contour in contours]
+        mask_image = cv2.drawContours(mask_image, contours, -1, (1, 1, 1, 0.5), thickness=2)
+    ax.imshow(mask_image)
+
+def show_points(coords, labels, ax, marker_size=375):
+    pos_points = coords[labels == 1]
+    neg_points = coords[labels == 0]
+    ax.scatter(pos_points[:, 0], pos_points[:, 1], color='green', marker='*', s=marker_size, edgecolor='white', linewidth=1.25)
+    ax.scatter(neg_points[:, 0], neg_points[:, 1], color='red', marker='*', s=marker_size, edgecolor='white', linewidth=1.25)
+
+def show_box(box, ax):
+    x0, y0 = box[0], box[1]
+    w, h = box[2] - box[0], box[3] - box[1]
+    ax.add_patch(plt.Rectangle((x0, y0), w, h, edgecolor='green', facecolor=(0, 0, 0, 0), lw=2))
+
+def show_masks(image, masks, scores, point_coords=None, box_coords=None, input_labels=None, borders=True):
+    combined_images = []  # List to store filenames of images with masks overlaid
+    mask_images = []      # List to store filenames of separate mask images
+    for i, (mask, score) in enumerate(zip(masks, scores)):
+        # ---- Original Image with Mask Overlaid ----
+        plt.figure(figsize=(10, 10))
+        plt.imshow(image)
+        show_mask(mask, plt.gca(), borders=borders)  # Draw the mask with borders
+        if box_coords is not None:
+            show_box(box_coords, plt.gca())
+        if len(scores) > 1:
+            plt.title(f"Mask {i+1}, Score: {score:.3f}", fontsize=18)
+        plt.axis('off')
+        # Save the figure as a JPG file
+        combined_filename = f"combined_image_{i+1}.jpg"
+        plt.savefig(combined_filename, format='jpg', bbox_inches='tight')
+        combined_images.append(combined_filename)
+        plt.close()  # Close the figure to free up memory
+        # ---- Separate Mask Image (White Mask on Black Background) ----
+        # Create a black image
+        mask_image = np.zeros_like(image, dtype=np.uint8)
+        # The mask is a binary array where the masked area is 1, else 0.
+        # Convert the mask to a white color in the mask_image
+        mask_layer = (mask > 0).astype(np.uint8) * 255
+        for c in range(3):  # Assuming RGB, repeat mask for all channels
+            mask_image[:, :, c] = mask_layer
+        # Save the mask image
+        mask_filename = f"mask_image_{i+1}.png"
+        Image.fromarray(mask_image).save(mask_filename)
+        mask_images.append(mask_filename)
+        plt.close()  # Close the figure to free up memory
+    return combined_images, mask_images
+
+@spaces.GPU()
+def sam_process(original_image, points, labels):
+    print(f"Points: {points}")
+    print(f"Labels: {labels}")
+    if not points or not labels:
+        print("No points or labels provided, returning None")
+        return None
+    
+    # Convert image to numpy array for SAM2 processing
+    image = np.array(original_image)
+    predictor = SAM2ImagePredictor.from_pretrained("facebook/sam2.1-hiera-large")
+    predictor.set_image(image)
+    
+    input_point = np.array(points)
+    input_label = np.array(labels)
+    
+    try:
+        masks, scores, _ = predictor.predict(input_point, input_label, multimask_output=False)
+    except Exception as e:
+        print(f"Error during prediction: {e}")
+        return None
+    
+    sorted_indices = np.argsort(scores)[::-1]
+    masks = masks[sorted_indices]
+    
+    if masks and len(masks) > 0:
+        mask = masks[0] * 255
+        mask_image = Image.fromarray(mask.astype(np.uint8))
+        return mask_image
+    else:
+        print("No masks generated, returning None")
+        return None
+
+def create_sam2_tab():
+    first_frame = gr.State()  # Tracks original image
+    tracking_points = gr.State([])
+    trackings_input_label = gr.State([])
+    
+    with gr.Column():
+        gr.Markdown("# SAM2 Image Predictor")
+
+        image_input = gr.State()
+        input_image = ImagePrompter(show_label=False)
+        points_map = gr.Image(label="Points Map", type="pil", interactive=True)
+        # image_input = gr.Image(type="pil", visible=False)  # Original image
+        
+        with gr.Row():
+            point_type = gr.Radio(["include", "exclude"], value="include", label="Point Type")
+            clear_button = gr.Button("Clear Points")
+        
+        submit_button = gr.Button("Submit")
+        output_image = gr.Image("Segmented Output")
+        
+        # Event handlers
+        points_map.upload(
+            lambda img: (img, img, [], []),
+            inputs=points_map,
+            outputs=[input_image, first_frame, tracking_points, trackings_input_label]
+        )
+        
+        clear_button.click(
+            lambda img: ([], [], img),
+            inputs=first_frame,
+            outputs=[tracking_points, trackings_input_label, points_map]
+        )
+        
+        points_map.select(
+            get_point,
+            inputs=[point_type, tracking_points, trackings_input_label, first_frame],
+            outputs=[tracking_points, trackings_input_label, points_map]
+        )
+        
+        submit_button.click(
+            sam_process,
+            inputs=[input_image, tracking_points, trackings_input_label],
+            outputs=output_image
+        )
+    
+    return input_image, points_map, output_image
+