Merge branch 'main' of https://huggingface.co/spaces/An-619/FastSAM into main

app.py

@@ -1,288 +1,288 @@
-from ultralytics import YOLO
-import gradio as gr
-import torch
-from tools import fast_process, format_results, box_prompt, point_prompt
-from PIL import ImageDraw
-import numpy as np
-
-# Load the pre-trained model
-model = YOLO('checkpoints/FastSAM.pt')
-
-device = 'cuda' if torch.cuda.is_available() else 'cpu'
-
-# Description
-title = "<center><strong><font size='8'>🏃 Fast Segment Anything 🤗</font></strong></center>"
-
-news = """ # 📖 News
-
-        🔥 2023/06/24: Add the 'Advanced options" in Everything mode to get a more detailed adjustment.
-        
-        🔥 2023/06/26: Support the points mode. (Better and faster interaction will come soon!)
-        
-        """  
-
-description_e = """This is a demo on Github project 🏃 [Fast Segment Anything Model](https://github.com/CASIA-IVA-Lab/FastSAM). Welcome to give a star ⭐️ to it.
-                
-                🎯 Upload an Image, segment it with Fast Segment Anything (Everything mode). The other modes will come soon.
-                
-                ⌛️ It takes about 6~ seconds to generate segment results. The concurrency_count of queue is 1, please wait for a moment when it is crowded.
-                
-                🚀 To get faster results, you can use a smaller input size and leave high_visual_quality unchecked.
-                
-                📣 You can also obtain the segmentation results of any Image through this Colab: [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1oX14f6IneGGw612WgVlAiy91UHwFAvr9?usp=sharing)
-                
-                😚 A huge thanks goes out to the @HuggingFace Team for supporting us with GPU grant.
-                
-                🏠 Check out our [Model Card 🏃](https://huggingface.co/An-619/FastSAM)
-                
-              """
-
-description_p = """ # 🎯 Instructions for points mode
-                This is a demo on Github project 🏃 [Fast Segment Anything Model](https://github.com/CASIA-IVA-Lab/FastSAM). Welcome to give a star ⭐️ to it.
-                
-                1. Upload an image or choose an example.
-                
-                2. Choose the point label ('Add mask' means a positive point. 'Remove' Area means a negative point that is not segmented).
-                
-                3. Add points one by one on the image.
-                
-                4. Click the 'Segemnt with points prompt' button to get the segmentation results.
-                
-                **5. If you get Error, click the 'Clear points' button and try again may help.**
-                
-              """
-
-examples = [["assets/sa_8776.jpg"], ["assets/sa_414.jpg"], ["assets/sa_1309.jpg"], ["assets/sa_11025.jpg"],
-            ["assets/sa_561.jpg"], ["assets/sa_192.jpg"], ["assets/sa_10039.jpg"], ["assets/sa_862.jpg"]]
-
-default_example = examples[0]
-
-css = "h1 { text-align: center } .about { text-align: justify; padding-left: 10%; padding-right: 10%; }"
-
-
-def segment_everything(
-    input,
-    input_size=1024, 
-    iou_threshold=0.7,
-    conf_threshold=0.25,
-    better_quality=False,
-    withContours=True,
-    use_retina=True,
-    mask_random_color=True,
-    ):
-    input_size = int(input_size)  # 确保 imgsz 是整数
-
-    # Thanks for the suggestion by hysts in HuggingFace.
-    w, h = input.size
-    scale = input_size / max(w, h)
-    new_w = int(w * scale)
-    new_h = int(h * scale)
-    input = input.resize((new_w, new_h))
-
-    results = model(input,
-                    device=device,
-                    retina_masks=True,
-                    iou=iou_threshold,
-                    conf=conf_threshold,
-                    imgsz=input_size,)
-    
-    fig = fast_process(annotations=results[0].masks.data,
-                        image=input,
-                        device=device,
-                        scale=(1024 // input_size),
-                        better_quality=better_quality,
-                        mask_random_color=mask_random_color,
-                        bbox=None,
-                        use_retina=use_retina,
-                        withContours=withContours,)
-    return fig
-
-def segment_with_points(
-    input,
-    input_size=1024, 
-    iou_threshold=0.7,
-    conf_threshold=0.25,
-    better_quality=False,
-    withContours=True,
-    mask_random_color=True,
-    use_retina=True,
-    ):    
-    global global_points
-    global global_point_label
-    
-    input_size = int(input_size)  # 确保 imgsz 是整数
-    # Thanks for the suggestion by hysts in HuggingFace.
-    w, h = input.size
-    scale = input_size / max(w, h)
-    new_w = int(w * scale)
-    new_h = int(h * scale)
-    input = input.resize((new_w, new_h))
-    
-    scaled_points = [[int(x * scale) for x in point] for point in global_points]
-
-    results = model(input,
-                    device=device,
-                    retina_masks=True,
-                    iou=iou_threshold,
-                    conf=conf_threshold,
-                    imgsz=input_size,)
-    
-    results = format_results(results[0], 0)
-    
-    annotations, _ = point_prompt(results, scaled_points, global_point_label, new_h, new_w)
-    annotations = np.array([annotations])
-        
-    fig = fast_process(annotations=annotations,
-                        image=input,
-                        device=device,
-                        scale=(1024 // input_size),
-                        better_quality=better_quality,
-                        mask_random_color=mask_random_color,
-                        bbox=None,
-                        use_retina=use_retina,
-                        withContours=withContours,)
-    global_points = []
-    global_point_label = []
-    return fig, None
-
-def get_points_with_draw(image, label, evt: gr.SelectData):
-    x, y = evt.index[0], evt.index[1]
-    point_radius, point_color = 15, (255, 255, 0) if label == 'Add Mask' else (255, 0, 255)
-    global global_points
-    global global_point_label
-    print((x, y))
-    global_points.append([x, y])
-    global_point_label.append(1 if label == 'Add Mask' else 0)
-    
-    # 创建一个可以在图像上绘图的对象
-    draw = ImageDraw.Draw(image)
-    draw.ellipse([(x - point_radius, y - point_radius), (x + point_radius, y + point_radius)], fill=point_color)
-    return image
-    
-
-# input_size=1024
-# high_quality_visual=True
-# inp = 'assets/sa_192.jpg'
-# input = Image.open(inp)
-# device = 'cuda' if torch.cuda.is_available() else 'cpu'
-# input_size = int(input_size)  # 确保 imgsz 是整数
-# results = model(input, device=device, retina_masks=True, iou=0.7, conf=0.25, imgsz=input_size)
-# pil_image = fast_process(annotations=results[0].masks.data,
-#                             image=input, high_quality=high_quality_visual, device=device)
-
-cond_img_e = gr.Image(label="Input", value=default_example[0], type='pil')
-cond_img_p = gr.Image(label="Input with points", value=default_example[0], type='pil')
-
-segm_img_e = gr.Image(label="Segmented Image", interactive=False, type='pil')
-segm_img_p = gr.Image(label="Segmented Image with points", interactive=False, type='pil')
-
-global_points = []
-global_point_label = [] # TODO:Clear points each image
-
-input_size_slider = gr.components.Slider(minimum=512,
-                                         maximum=1024,
-                                         value=1024,
-                                         step=64,
-                                         label='Input_size',
-                                         info='Our model was trained on a size of 1024')
-
-with gr.Blocks(css=css, title='Fast Segment Anything') as demo:
-    with gr.Row():
-            with gr.Column(scale=1):
-                # Title
-                gr.Markdown(title)
-        
-            with gr.Column(scale=1):
-                # News
-                gr.Markdown(news)
-                
-    with gr.Tab("Everything mode"):
-        # Images
-        with gr.Row(variant="panel"):
-            with gr.Column(scale=1):
-                cond_img_e.render()
-
-            with gr.Column(scale=1):
-                segm_img_e.render()
-
-        # Submit & Clear
-        with gr.Row():
-            with gr.Column():
-                input_size_slider.render()
-
-                with gr.Row():
-                    contour_check = gr.Checkbox(value=True, label='withContours', info='draw the edges of the masks')
-
-                    with gr.Column():
-                        segment_btn_e = gr.Button("Segment Everything", variant='primary')
-                        clear_btn_e = gr.Button("Clear", variant="secondary")
-
-                gr.Markdown("Try some of the examples below ⬇️")
-                gr.Examples(examples=examples,
-                            inputs=[cond_img_e],
-                            outputs=segm_img_e,
-                            fn=segment_everything,
-                            cache_examples=True,
-                            examples_per_page=4)
-
-            with gr.Column():
-                with gr.Accordion("Advanced options", open=False):
-                    iou_threshold = gr.Slider(0.1, 0.9, 0.7, step=0.1, label='iou', info='iou threshold for filtering the annotations')
-                    conf_threshold = gr.Slider(0.1, 0.9, 0.25, step=0.05, label='conf', info='object confidence threshold')
-                    with gr.Row():
-                        mor_check = gr.Checkbox(value=False, label='better_visual_quality', info='better quality using morphologyEx')
-                        with gr.Column():
-                            retina_check = gr.Checkbox(value=True, label='use_retina', info='draw high-resolution segmentation masks')
-                    
-                # Description
-                gr.Markdown(description_e)
-
-    with gr.Tab("Points mode"):
-        # Images
-        with gr.Row(variant="panel"):
-            with gr.Column(scale=1):
-                cond_img_p.render()
-
-            with gr.Column(scale=1):
-                segm_img_p.render()
-                
-        # Submit & Clear
-        with gr.Row():
-            with gr.Column():
-                with gr.Row():
-                    add_or_remove = gr.Radio(["Add Mask", "Remove Area"], value="Add Mask", label="Point_label (foreground/background)")
-
-                    with gr.Column():
-                        segment_btn_p = gr.Button("Segment with points prompt", variant='primary')
-                        clear_btn_p = gr.Button("Clear points", variant='secondary')
-
-                gr.Markdown("Try some of the examples below ⬇️")
-                gr.Examples(examples=examples,
-                            inputs=[cond_img_p],
-                            outputs=segm_img_p,
-                            fn=segment_with_points,
-                            # cache_examples=True,
-                            examples_per_page=4)
-
-            with gr.Column():
-                # Description
-                gr.Markdown(description_p)
-        
-    cond_img_p.select(get_points_with_draw, [cond_img_p, add_or_remove], cond_img_p)
-
-    segment_btn_e.click(segment_everything,
-                    inputs=[cond_img_e, input_size_slider, iou_threshold, conf_threshold, mor_check, contour_check, retina_check],
-                    outputs=segm_img_e)
-    
-    segment_btn_p.click(segment_with_points,
-                    inputs=[cond_img_p],
-                    outputs=[segm_img_p, cond_img_p])
-    
-    def clear():
-        return None, None
-    
-    clear_btn_e.click(clear, outputs=[cond_img_e, segm_img_e])
-    clear_btn_p.click(clear, outputs=[cond_img_p, segm_img_p])
-
-demo.queue()
-demo.launch()
+from ultralytics import YOLO
+import gradio as gr
+import torch
+from tools import fast_process, format_results, box_prompt, point_prompt
+from PIL import ImageDraw
+import numpy as np
+
+# Load the pre-trained model
+model = YOLO('checkpoints/FastSAM.pt')
+
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+
+# Description
+title = "<center><strong><font size='8'>🏃 Fast Segment Anything 🤗</font></strong></center>"
+
+news = """ # 📖 News
+
+        🔥 2023/06/24: Add the 'Advanced options" in Everything mode to get a more detailed adjustment.
+        
+        🔥 2023/06/26: Support the points mode. (Better and faster interaction will come soon!)
+        
+        """  
+
+description_e = """This is a demo on Github project 🏃 [Fast Segment Anything Model](https://github.com/CASIA-IVA-Lab/FastSAM). Welcome to give a star ⭐️ to it.
+                
+                🎯 Upload an Image, segment it with Fast Segment Anything (Everything mode). The other modes will come soon.
+                
+                ⌛️ It takes about 6~ seconds to generate segment results. The concurrency_count of queue is 1, please wait for a moment when it is crowded.
+                
+                🚀 To get faster results, you can use a smaller input size and leave high_visual_quality unchecked.
+                
+                📣 You can also obtain the segmentation results of any Image through this Colab: [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1oX14f6IneGGw612WgVlAiy91UHwFAvr9?usp=sharing)
+                
+                😚 A huge thanks goes out to the @HuggingFace Team for supporting us with GPU grant.
+                
+                🏠 Check out our [Model Card 🏃](https://huggingface.co/An-619/FastSAM)
+                
+              """
+
+description_p = """ # 🎯 Instructions for points mode
+                This is a demo on Github project 🏃 [Fast Segment Anything Model](https://github.com/CASIA-IVA-Lab/FastSAM). Welcome to give a star ⭐️ to it.
+                
+                1. Upload an image or choose an example.
+                
+                2. Choose the point label ('Add mask' means a positive point. 'Remove' Area means a negative point that is not segmented).
+                
+                3. Add points one by one on the image.
+                
+                4. Click the 'Segemnt with points prompt' button to get the segmentation results.
+                
+                **5. If you get Error, click the 'Clear points' button and try again may help.**
+                
+              """
+
+examples = [["assets/sa_8776.jpg"], ["assets/sa_414.jpg"], ["assets/sa_1309.jpg"], ["assets/sa_11025.jpg"],
+            ["assets/sa_561.jpg"], ["assets/sa_192.jpg"], ["assets/sa_10039.jpg"], ["assets/sa_862.jpg"]]
+
+default_example = examples[0]
+
+css = "h1 { text-align: center } .about { text-align: justify; padding-left: 10%; padding-right: 10%; }"
+
+
+def segment_everything(
+    input,
+    input_size=1024, 
+    iou_threshold=0.7,
+    conf_threshold=0.25,
+    better_quality=False,
+    withContours=True,
+    use_retina=True,
+    mask_random_color=True,
+    ):
+    input_size = int(input_size)  # 确保 imgsz 是整数
+
+    # Thanks for the suggestion by hysts in HuggingFace.
+    w, h = input.size
+    scale = input_size / max(w, h)
+    new_w = int(w * scale)
+    new_h = int(h * scale)
+    input = input.resize((new_w, new_h))
+
+    results = model(input,
+                    device=device,
+                    retina_masks=True,
+                    iou=iou_threshold,
+                    conf=conf_threshold,
+                    imgsz=input_size,)
+    
+    fig = fast_process(annotations=results[0].masks.data,
+                        image=input,
+                        device=device,
+                        scale=(1024 // input_size),
+                        better_quality=better_quality,
+                        mask_random_color=mask_random_color,
+                        bbox=None,
+                        use_retina=use_retina,
+                        withContours=withContours,)
+    return fig
+
+def segment_with_points(
+    input,
+    input_size=1024, 
+    iou_threshold=0.7,
+    conf_threshold=0.25,
+    better_quality=False,
+    withContours=True,
+    mask_random_color=True,
+    use_retina=True,
+    ):    
+    global global_points
+    global global_point_label
+    
+    input_size = int(input_size)  # 确保 imgsz 是整数
+    # Thanks for the suggestion by hysts in HuggingFace.
+    w, h = input.size
+    scale = input_size / max(w, h)
+    new_w = int(w * scale)
+    new_h = int(h * scale)
+    input = input.resize((new_w, new_h))
+    
+    scaled_points = [[int(x * scale) for x in point] for point in global_points]
+
+    results = model(input,
+                    device=device,
+                    retina_masks=True,
+                    iou=iou_threshold,
+                    conf=conf_threshold,
+                    imgsz=input_size,)
+    
+    results = format_results(results[0], 0)
+    
+    annotations, _ = point_prompt(results, scaled_points, global_point_label, new_h, new_w)
+    annotations = np.array([annotations])
+        
+    fig = fast_process(annotations=annotations,
+                        image=input,
+                        device=device,
+                        scale=(1024 // input_size),
+                        better_quality=better_quality,
+                        mask_random_color=mask_random_color,
+                        bbox=None,
+                        use_retina=use_retina,
+                        withContours=withContours,)
+    global_points = []
+    global_point_label = []
+    return fig, None
+
+def get_points_with_draw(image, label, evt: gr.SelectData):
+    x, y = evt.index[0], evt.index[1]
+    point_radius, point_color = 15, (255, 255, 0) if label == 'Add Mask' else (255, 0, 255)
+    global global_points
+    global global_point_label
+    print((x, y))
+    global_points.append([x, y])
+    global_point_label.append(1 if label == 'Add Mask' else 0)
+    
+    # 创建一个可以在图像上绘图的对象
+    draw = ImageDraw.Draw(image)
+    draw.ellipse([(x - point_radius, y - point_radius), (x + point_radius, y + point_radius)], fill=point_color)
+    return image
+    
+
+# input_size=1024
+# high_quality_visual=True
+# inp = 'assets/sa_192.jpg'
+# input = Image.open(inp)
+# device = 'cuda' if torch.cuda.is_available() else 'cpu'
+# input_size = int(input_size)  # 确保 imgsz 是整数
+# results = model(input, device=device, retina_masks=True, iou=0.7, conf=0.25, imgsz=input_size)
+# pil_image = fast_process(annotations=results[0].masks.data,
+#                             image=input, high_quality=high_quality_visual, device=device)
+
+cond_img_e = gr.Image(label="Input", value=default_example[0], type='pil')
+cond_img_p = gr.Image(label="Input with points", value=default_example[0], type='pil')
+
+segm_img_e = gr.Image(label="Segmented Image", interactive=False, type='pil')
+segm_img_p = gr.Image(label="Segmented Image with points", interactive=False, type='pil')
+
+global_points = []
+global_point_label = [] # TODO:Clear points each image
+
+input_size_slider = gr.components.Slider(minimum=512,
+                                         maximum=1024,
+                                         value=1024,
+                                         step=64,
+                                         label='Input_size',
+                                         info='Our model was trained on a size of 1024')
+
+with gr.Blocks(css=css, title='Fast Segment Anything') as demo:
+    with gr.Row():
+            with gr.Column(scale=1):
+                # Title
+                gr.Markdown(title)
+        
+            with gr.Column(scale=1):
+                # News
+                gr.Markdown(news)
+                
+    with gr.Tab("Everything mode"):
+        # Images
+        with gr.Row(variant="panel"):
+            with gr.Column(scale=1):
+                cond_img_e.render()
+
+            with gr.Column(scale=1):
+                segm_img_e.render()
+
+        # Submit & Clear
+        with gr.Row():
+            with gr.Column():
+                input_size_slider.render()
+
+                with gr.Row():
+                    contour_check = gr.Checkbox(value=True, label='withContours', info='draw the edges of the masks')
+
+                    with gr.Column():
+                        segment_btn_e = gr.Button("Segment Everything", variant='primary')
+                        clear_btn_e = gr.Button("Clear", variant="secondary")
+
+                gr.Markdown("Try some of the examples below ⬇️")
+                gr.Examples(examples=examples,
+                            inputs=[cond_img_e],
+                            outputs=segm_img_e,
+                            fn=segment_everything,
+                            cache_examples=True,
+                            examples_per_page=4)
+
+            with gr.Column():
+                with gr.Accordion("Advanced options", open=False):
+                    iou_threshold = gr.Slider(0.1, 0.9, 0.7, step=0.1, label='iou', info='iou threshold for filtering the annotations')
+                    conf_threshold = gr.Slider(0.1, 0.9, 0.25, step=0.05, label='conf', info='object confidence threshold')
+                    with gr.Row():
+                        mor_check = gr.Checkbox(value=False, label='better_visual_quality', info='better quality using morphologyEx')
+                        with gr.Column():
+                            retina_check = gr.Checkbox(value=True, label='use_retina', info='draw high-resolution segmentation masks')
+                    
+                # Description
+                gr.Markdown(description_e)
+
+    with gr.Tab("Points mode"):
+        # Images
+        with gr.Row(variant="panel"):
+            with gr.Column(scale=1):
+                cond_img_p.render()
+
+            with gr.Column(scale=1):
+                segm_img_p.render()
+                
+        # Submit & Clear
+        with gr.Row():
+            with gr.Column():
+                with gr.Row():
+                    add_or_remove = gr.Radio(["Add Mask", "Remove Area"], value="Add Mask", label="Point_label (foreground/background)")
+
+                    with gr.Column():
+                        segment_btn_p = gr.Button("Segment with points prompt", variant='primary')
+                        clear_btn_p = gr.Button("Clear points", variant='secondary')
+
+                gr.Markdown("Try some of the examples below ⬇️")
+                gr.Examples(examples=examples,
+                            inputs=[cond_img_p],
+                            outputs=segm_img_p,
+                            fn=segment_with_points,
+                            # cache_examples=True,
+                            examples_per_page=4)
+
+            with gr.Column():
+                # Description
+                gr.Markdown(description_p)
+        
+    cond_img_p.select(get_points_with_draw, [cond_img_p, add_or_remove], cond_img_p)
+
+    segment_btn_e.click(segment_everything,
+                    inputs=[cond_img_e, input_size_slider, iou_threshold, conf_threshold, mor_check, contour_check, retina_check],
+                    outputs=segm_img_e)
+    
+    segment_btn_p.click(segment_with_points,
+                    inputs=[cond_img_p],
+                    outputs=[segm_img_p, cond_img_p])
+    
+    def clear():
+        return None, None
+    
+    clear_btn_e.click(clear, outputs=[cond_img_e, segm_img_e])
+    clear_btn_p.click(clear, outputs=[cond_img_p, segm_img_p])
+
+demo.queue()
+demo.launch()

app_debug.py

@@ -1,287 +0,0 @@
-from ultralytics import YOLO
-import numpy as np
-import matplotlib.pyplot as plt
-import gradio as gr
-import cv2
-import torch
-from PIL import Image
-
-# Load the pre-trained model
-model = YOLO('checkpoints/FastSAM.pt')
-
-# Description
-title = "<center><strong><font size='8'>🏃 Fast Segment Anything 🤗</font></strong></center>"
-
-description = """This is a demo on Github project 🏃 [Fast Segment Anything Model](https://github.com/CASIA-IVA-Lab/FastSAM).
-                
-                🎯 Upload an Image, segment it with Fast Segment Anything (Everything mode). The other modes will come soon.
-                
-                ⌛️ It takes about 4~ seconds to generate segment results. The concurrency_count of queue is 1, please wait for a moment when it is crowded.
-                
-                🚀 To get faster results, you can use a smaller input size and leave high_visual_quality unchecked.
-                
-                📣 You can also obtain the segmentation results of any Image through this Colab: [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1oX14f6IneGGw612WgVlAiy91UHwFAvr9?usp=sharing)
-                
-                😚 A huge thanks goes out to the @HuggingFace Team for supporting us with GPU grant.
-                
-                🏠 Check out our [Model Card 🏃](https://huggingface.co/An-619/FastSAM)
-                
-              """
-
-examples = [["assets/sa_8776.jpg"], ["assets/sa_414.jpg"],
-            ["assets/sa_1309.jpg"], ["assets/sa_11025.jpg"],
-            ["assets/sa_561.jpg"], ["assets/sa_192.jpg"],
-            ["assets/sa_10039.jpg"], ["assets/sa_862.jpg"]]
-
-default_example = examples[0]
-
-css = "h1 { text-align: center } .about { text-align: justify; padding-left: 10%; padding-right: 10%; }"
-
-def fast_process(annotations, image, high_quality, device, scale):
-    if isinstance(annotations[0],dict):
-        annotations = [annotation['segmentation'] for annotation in annotations]
-
-    original_h = image.height
-    original_w = image.width
-    if high_quality == True:
-        if isinstance(annotations[0],torch.Tensor):
-            annotations = np.array(annotations.cpu())
-        for i, mask in enumerate(annotations):
-            mask = cv2.morphologyEx(mask.astype(np.uint8), cv2.MORPH_CLOSE, np.ones((3, 3), np.uint8))
-            annotations[i] = cv2.morphologyEx(mask.astype(np.uint8), cv2.MORPH_OPEN, np.ones((8, 8), np.uint8))
-    if device == 'cpu':
-        annotations = np.array(annotations)
-        inner_mask = fast_show_mask(annotations,
-                       plt.gca(),
-                       bbox=None,
-                       points=None,
-                       pointlabel=None,
-                       retinamask=True,
-                       target_height=original_h,
-                       target_width=original_w)
-    else:
-        if isinstance(annotations[0],np.ndarray):
-            annotations = torch.from_numpy(annotations)
-        inner_mask = fast_show_mask_gpu(annotations,
-                           plt.gca(),
-                           bbox=None,
-                           points=None,
-                           pointlabel=None)
-    if isinstance(annotations, torch.Tensor):
-        annotations = annotations.cpu().numpy()
-    
-    if high_quality:
-        contour_all = []
-        temp = np.zeros((original_h, original_w,1))
-        for i, mask in enumerate(annotations):
-            if type(mask) == dict:
-                mask = mask['segmentation']
-            annotation = mask.astype(np.uint8)
-            contours, _ = cv2.findContours(annotation, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
-            for contour in contours:
-                contour_all.append(contour)
-        cv2.drawContours(temp, contour_all, -1, (255, 255, 255), 2 // scale)
-        color = np.array([0 / 255, 0 / 255, 255 / 255, 0.9])
-        contour_mask = temp / 255 * color.reshape(1, 1, -1)
-    image = image.convert('RGBA')
-    
-    overlay_inner = Image.fromarray((inner_mask * 255).astype(np.uint8), 'RGBA')
-    image.paste(overlay_inner, (0, 0), overlay_inner)
-    
-    if high_quality:
-        overlay_contour = Image.fromarray((contour_mask * 255).astype(np.uint8), 'RGBA')
-        image.paste(overlay_contour, (0, 0), overlay_contour)
-        
-    return image
-
-#   CPU post process
-def fast_show_mask(annotation, ax, bbox=None, 
-                   points=None, pointlabel=None,
-                   retinamask=True, target_height=960,
-                   target_width=960):
-    msak_sum = annotation.shape[0]
-    height = annotation.shape[1]
-    weight = annotation.shape[2]
-    # 将annotation 按照面积 排序
-    areas = np.sum(annotation, axis=(1, 2))
-    sorted_indices = np.argsort(areas)[::1]
-    annotation = annotation[sorted_indices]
-
-    index = (annotation != 0).argmax(axis=0)
-    color = np.random.random((msak_sum,1,1,3))
-    transparency = np.ones((msak_sum,1,1,1)) * 0.6
-    visual = np.concatenate([color,transparency],axis=-1)
-    mask_image = np.expand_dims(annotation,-1) * visual
-
-    mask = np.zeros((height,weight,4))
-
-    h_indices, w_indices = np.meshgrid(np.arange(height), np.arange(weight), indexing='ij')
-    indices = (index[h_indices, w_indices], h_indices, w_indices, slice(None))
-    # 使用向量化索引更新show的值
-    mask[h_indices, w_indices, :] = mask_image[indices]
-    if bbox is not None:
-        x1, y1, x2, y2 = bbox
-        ax.add_patch(plt.Rectangle((x1, y1), x2 - x1, y2 - y1, fill=False, edgecolor='b', linewidth=1))
-    # draw point
-    if points is not None:
-        plt.scatter([point[0] for i, point in enumerate(points) if pointlabel[i]==1], [point[1] for i, point in enumerate(points) if pointlabel[i]==1], s=20, c='y')
-        plt.scatter([point[0] for i, point in enumerate(points) if pointlabel[i]==0], [point[1] for i, point in enumerate(points) if pointlabel[i]==0], s=20, c='m')
-    
-    if retinamask==False:
-        mask = cv2.resize(mask, (target_width, target_height), interpolation=cv2.INTER_NEAREST)
-    
-    return mask
-
-
-def fast_show_mask_gpu(annotation, ax,
-                       bbox=None, points=None, 
-                       pointlabel=None):
-    msak_sum = annotation.shape[0]
-    height = annotation.shape[1]
-    weight = annotation.shape[2]
-    areas = torch.sum(annotation, dim=(1, 2))
-    sorted_indices = torch.argsort(areas, descending=False)
-    annotation = annotation[sorted_indices]
-    # 找每个位置第一个非零值下标
-    index = (annotation != 0).to(torch.long).argmax(dim=0)
-    color = torch.rand((msak_sum,1,1,3)).to(annotation.device)
-    transparency = torch.ones((msak_sum,1,1,1)).to(annotation.device) * 0.6
-    visual = torch.cat([color,transparency],dim=-1)
-    mask_image = torch.unsqueeze(annotation,-1) * visual
-    # 按index取数，index指每个位置选哪个batch的数，把mask_image转成一个batch的形式
-    mask = torch.zeros((height,weight,4)).to(annotation.device)
-    h_indices, w_indices = torch.meshgrid(torch.arange(height), torch.arange(weight))
-    indices = (index[h_indices, w_indices], h_indices, w_indices, slice(None))
-    # 使用向量化索引更新show的值
-    mask[h_indices, w_indices, :] = mask_image[indices]
-    mask_cpu = mask.cpu().numpy()
-    if bbox is not None:
-        x1, y1, x2, y2 = bbox
-        ax.add_patch(plt.Rectangle((x1, y1), x2 - x1, y2 - y1, fill=False, edgecolor='b', linewidth=1))
-    # draw point
-    if points is not None:
-        plt.scatter([point[0] for i, point in enumerate(points) if pointlabel[i]==1], [point[1] for i, point in enumerate(points) if pointlabel[i]==1], s=20, c='y')
-        plt.scatter([point[0] for i, point in enumerate(points) if pointlabel[i]==0], [point[1] for i, point in enumerate(points) if pointlabel[i]==0], s=20, c='m')
-    return mask_cpu
-
-
-device = 'cuda' if torch.cuda.is_available() else 'cpu'
-
-def segment_image(input, evt: gr.SelectData=None, input_size=1024, high_visual_quality=True, iou_threshold=0.7, conf_threshold=0.25):
-    point = (evt.index[0],evt.index[1])
-    input_size = int(input_size)  # 确保 imgsz 是整数
-    
-    # Thanks for the suggestion by hysts in HuggingFace.
-    w, h = input.size
-    scale = input_size / max(w, h)
-    new_w = int(w * scale)
-    new_h = int(h * scale)
-    input = input.resize((new_w, new_h))
-    
-    results = model(input, device=device, retina_masks=True, iou=iou_threshold, conf=conf_threshold, imgsz=input_size)
-    fig = fast_process(annotations=results[0].masks.data,
-                        image=input, high_quality=high_visual_quality,
-                        device=device, scale=(1024 // input_size),
-                        points=)
-    return fig
-
-# input_size=1024
-# high_quality_visual=True
-# inp = 'assets/sa_192.jpg'
-# input = Image.open(inp)
-# device = 'cuda' if torch.cuda.is_available() else 'cpu'
-# input_size = int(input_size)  # 确保 imgsz 是整数
-# results = model(input, device=device, retina_masks=True, iou=0.7, conf=0.25, imgsz=input_size)
-# pil_image = fast_process(annotations=results[0].masks.data,
-#                             image=input, high_quality=high_quality_visual, device=device)
-
-cond_img = gr.Image(label="Input", value=default_example[0], type='pil')
-
-segm_img = gr.Image(label="Segmented Image", interactive=False, type='pil')
-
-input_size_slider = gr.components.Slider(minimum=512, maximum=1024, value=1024, step=64, label='Input_size (Our model was trained on a size of 1024)')
-
-with gr.Blocks(css=css, title='Fast Segment Anything') as demo:
-    with gr.Row():
-        # Title
-        gr.Markdown(title)
-    #     # # Description
-    #     # gr.Markdown(description)
-        
-    # Images
-    with gr.Row(variant="panel"):
-        with gr.Column(scale=1):
-            cond_img.render()
-            
-        with gr.Column(scale=1):
-            segm_img.render()
-    
-    # Submit & Clear
-    with gr.Row():
-        with gr.Column():
-            input_size_slider.render()
-            
-            with gr.Row():
-                vis_check = gr.Checkbox(value=True, label='high_visual_quality')
-                
-                with gr.Column():
-                    segment_btn = gr.Button("Segment Anything", variant='primary')
-                    
-                # with gr.Column():
-                    # clear_btn = gr.Button("Clear", variant="primary")
-            
-            gr.Markdown("Try some of the examples below ⬇️")
-            gr.Examples(examples=examples,
-                        inputs=[cond_img],
-                        outputs=segm_img,
-                        fn=segment_image,
-                        cache_examples=True,
-                        examples_per_page=4)
-            # gr.Markdown("Try some of the examples below ⬇️")
-            # gr.Examples(examples=examples,
-            #             inputs=[cond_img, input_size_slider, vis_check, iou_threshold, conf_threshold],
-            #             outputs=output,
-            #             fn=segment_image,
-            #             examples_per_page=4)
-
-        with gr.Column():
-            with gr.Accordion("Advanced options", open=False):
-                iou_threshold = gr.Slider(0.1, 0.9, 0.7, step=0.1, label='iou_threshold')
-                conf_threshold = gr.Slider(0.1, 0.9, 0.25, step=0.05, label='conf_threshold')
-                
-            # Description
-            gr.Markdown(description)
-    
-    cond_img.select(segment_image, [], input_img)
-    
-    segment_btn.click(segment_image,
-                     inputs=[cond_img, input_size_slider, vis_check, iou_threshold, conf_threshold],
-                     outputs=segm_img)  
-    
-    # def clear():
-        # return None, None
-
-    # clear_btn.click(fn=clear, inputs=None, outputs=None)
-
-demo.queue()
-demo.launch()
-
-# app_interface = gr.Interface(fn=predict,
-#                     inputs=[gr.Image(type='pil'),
-#                             gr.components.Slider(minimum=512, maximum=1024, value=1024, step=64, label='input_size'),
-#                             gr.components.Checkbox(value=True, label='high_visual_quality')],
-#                     # outputs=['plot'],
-#                     outputs=gr.Image(type='pil'),
-#                     # examples=[["assets/sa_8776.jpg"]],
-#                     # #    ["assets/sa_1309.jpg", 1024]],
-#                     examples=[["assets/sa_192.jpg"], ["assets/sa_414.jpg"],
-#                               ["assets/sa_561.jpg"], ["assets/sa_862.jpg"],
-#                               ["assets/sa_1309.jpg"], ["assets/sa_8776.jpg"],
-#                               ["assets/sa_10039.jpg"], ["assets/sa_11025.jpg"],],
-#                     cache_examples=True,
-#                     title="Fast Segment Anything (Everything mode)"
-#                     )
-
-
-# app_interface.queue(concurrency_count=1, max_size=20)
-# app_interface.launch()