Add application file

app.py

@@ -0,0 +1,368 @@
+from ultralytics import YOLO
+import gradio as gr
+import torch
+from utils.tools_gradio import fast_process
+from utils.tools import format_results, box_prompt, point_prompt, text_prompt
+from PIL import ImageDraw
+import numpy as np
+
+# Load the pre-trained model
+model = YOLO('./weights/flashsam.pt')
+
+device = torch.device(
+    "cuda"
+    if torch.cuda.is_available()
+    else "mps"
+    if torch.backends.mps.is_available()
+    else "cpu"
+)
+
+# Description
+title = "<center><strong><font size='8'>🏃 FlashSAM 🤗</font></strong></center>"
+
+news = """ # 📖 News
+        🔥 2025/11/16: Release the first demo.     
+        """  
+
+description_e = """This is a demo about FlashSAM.
+                
+                🎯 Upload an Image, segment it with Fast Segment Anything (Everything mode). The other modes will come soon.                                
+              """
+
+description_p = """ # 🎯 Instructions for points mode
+                This is a demo about FlashSAM.
+                
+                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 'Segment 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 = [["examples/sa_8776.jpg"], ["examples/sa_414.jpg"], ["examples/sa_1309.jpg"], ["examples/sa_11025.jpg"],
+            ["examples/sa_561.jpg"], ["examples/sa_192.jpg"], ["examples/sa_10039.jpg"], ["examples/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,
+    text="",
+    wider=False,
+    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,)
+
+    if len(text) > 0:
+        results = format_results(results[0], 0)
+        annotations, _ = text_prompt(results, text, input, device=device, wider=wider)
+        annotations = np.array([annotations])
+    else:
+        annotations = results[0].masks.data
+    
+    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,)
+    return fig
+
+
+def segment_with_points(
+    input,
+    input_size=1024, 
+    iou_threshold=0.7,
+    conf_threshold=0.25,
+    better_quality=False,
+    withContours=True,
+    use_retina=True,
+    mask_random_color=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,)
+
+    return fig
+
+
+def get_points_with_draw(image, label, evt: gr.SelectData):
+    global global_points
+    global global_point_label
+
+    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_points.append([x, y])
+    global_point_label.append(1 if label == 'Add Mask' else 0)
+    
+    print(x, y, label == 'Add Mask')
+    
+    # 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
+
+
+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')
+cond_img_t = gr.Image(label="Input with text", value="examples/dogs.jpg", 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')
+segm_img_t = gr.Image(label="Segmented Image with text", interactive=False, type='pil')
+
+global_points = []
+global_point_label = []
+
+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='FlashSAM') as demo:
+    with gr.Row():
+        with gr.Column(scale=1):
+            # Title
+            gr.Markdown(title)
+
+        with gr.Column(scale=1):
+            # News
+            gr.Markdown(news)
+
+    everything_tab = gr.Tab("Everything mode")
+    points_tab = gr.Tab("Points mode")
+    text_tab = gr.Tab("Text mode")
+
+    with everything_tab:
+        # 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)
+
+    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)
+
+    with points_tab:
+        # 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_p.click(segment_with_points,
+                        inputs=[cond_img_p],
+                        outputs=[segm_img_p])
+
+    with text_tab:
+        # Images
+        with gr.Row(variant="panel"):
+            with gr.Column(scale=1):
+                cond_img_t.render()
+
+            with gr.Column(scale=1):
+                segm_img_t.render()
+
+        # Submit & Clear
+        with gr.Row():
+            with gr.Column():
+                input_size_slider_t = 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.Row():
+                    with gr.Column():
+                        contour_check = gr.Checkbox(value=True, label='withContours', info='draw the edges of the masks')
+                        text_box = gr.Textbox(label="text prompt", value="a yellow dog")
+
+                    with gr.Column():
+                        segment_btn_t = gr.Button("Segment with text", variant='primary')
+                        clear_btn_t = gr.Button("Clear", variant="secondary")
+
+                gr.Markdown("Try some of the examples below ⬇️")
+                gr.Examples(examples=[["examples/dogs.jpg"], ["examples/fruits.jpg"], ["examples/flowers.jpg"]],
+                            inputs=[cond_img_t],
+                            # 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')
+                        retina_check = gr.Checkbox(value=True, label='use_retina', info='draw high-resolution segmentation masks')
+                        wider_check = gr.Checkbox(value=False, label='wider', info='wider result')
+
+                # Description
+                gr.Markdown(description_e)
+    
+    segment_btn_t.click(segment_everything,
+                        inputs=[
+                            cond_img_t,
+                            input_size_slider_t,
+                            iou_threshold,
+                            conf_threshold,
+                            mor_check,
+                            contour_check,
+                            retina_check,
+                            text_box,
+                            wider_check,
+                        ],
+                        outputs=segm_img_t)
+
+    def clear():
+        global global_points
+        global global_point_label
+        global_points = []
+        global_point_label = []
+        return None, None
+
+    def clear_text():
+        return None, None, None
+
+    everything_tab.select(clear, outputs=[cond_img_e, segm_img_e]) # reset when everything tab is selected
+    points_tab.select(clear, outputs=[cond_img_e, segm_img_e]) # reset when points tab is selected
+    text_tab.select(clear, outputs=[cond_img_e, segm_img_e]) # reset when text tab is selected
+    cond_img_p.clear(clear, outputs=[cond_img_e, segm_img_e]) # reset when input image is cleared
+    cond_img_p.input(clear, outputs=[cond_img_e, segm_img_e]) # reset when input image is changed
+    clear_btn_e.click(clear, outputs=[cond_img_e, segm_img_e])
+    clear_btn_p.click(clear, outputs=[cond_img_p, segm_img_p])
+    clear_btn_t.click(clear_text, outputs=[cond_img_p, segm_img_p, text_box])
+
+demo.queue()
+demo.launch(share=True)

requirements.txt

@@ -0,0 +1,95 @@
+aiofiles==24.1.0
+aliyun-python-sdk-core==2.16.0
+aliyun-python-sdk-kms==2.16.5
+annotated-doc==0.0.4
+annotated-types==0.7.0
+anyio==4.11.0
+brotli==1.2.0
+certifi==2025.11.12
+cffi==1.17.1
+charset-normalizer==3.4.3
+click==8.3.1
+clip==1.0
+contourpy==1.3.2
+crcmod==1.7
+cryptography==45.0.7
+cycler==0.12.1
+exceptiongroup==1.3.0
+fastapi==0.121.2
+faster-coco-eval==1.6.7
+ffmpy==1.0.0
+filelock==3.20.0
+fonttools==4.59.2
+fsspec==2025.10.0
+ftfy==6.3.1
+gradio==5.49.1
+gradio-client==1.13.3
+groovy==0.1.2
+h11==0.16.0
+hf-xet==1.2.0
+httpcore==1.0.9
+httpx==0.28.1
+huggingface-hub==1.1.4
+idna==3.11
+jinja2==3.1.6
+jmespath==0.10.0
+kiwisolver==1.4.9
+markdown-it-py==4.0.0
+markupsafe==3.0.3
+matplotlib==3.7.0
+mdurl==0.1.2
+mpmath==1.3.0
+narwhals==2.2.0
+networkx==3.4.2
+numpy==1.26.4
+opencv-python==4.11.0.86
+openxlab==0.1.2
+orjson==3.11.4
+oss2==2.17.0
+packaging==25.0
+pandas==2.3.3
+pillow==11.3.0
+plotly==6.3.0
+polars==1.32.3
+psutil==7.0.0
+py-cpuinfo==9.0.0
+pycocotools==2.0.7
+pycparser==2.22
+pycryptodome==3.23.0
+pydantic==2.11.10
+pydantic-core==2.33.2
+pydub==0.25.1
+pygments==2.19.2
+pyparsing==3.2.3
+python-dateutil==2.9.0.post0
+python-multipart==0.0.20
+pytz==2025.2
+pyyaml==6.0.3
+regex==2025.11.3
+requests==2.28.2
+rich==14.2.0
+ruff==0.14.5
+safehttpx==0.1.7
+scipy==1.15.3
+semantic-version==2.10.0
+setuptools==60.2.0
+shellingham==1.5.4
+six==1.17.0
+sniffio==1.3.1
+starlette==0.49.3
+sympy==1.14.0
+tomlkit==0.13.3
+torch==2.8.0
+torchvision==0.23.0
+tqdm==4.67.1
+typer==0.20.0
+typer-slim==0.20.0
+typing-extensions==4.15.0
+typing-inspection==0.4.2
+tzdata==2025.2
+ultralytics==8.3.191
+ultralytics-thop==2.0.16
+urllib3==1.26.20
+uvicorn==0.38.0
+wcwidth==0.2.14
+websockets==15.0.1

utils/tools.py

@@ -0,0 +1,442 @@
+import numpy as np
+from PIL import Image
+import matplotlib.pyplot as plt
+import cv2
+import torch
+import os
+import sys
+import clip
+
+
+def convert_box_xywh_to_xyxy(box):
+    if len(box) == 4:
+        return [box[0], box[1], box[0] + box[2], box[1] + box[3]]
+    else:
+        result = []
+        for b in box:
+            b = convert_box_xywh_to_xyxy(b)
+            result.append(b)               
+    return result
+
+
+def segment_image(image, bbox):
+    image_array = np.array(image)
+    segmented_image_array = np.zeros_like(image_array)
+    x1, y1, x2, y2 = bbox
+    segmented_image_array[y1:y2, x1:x2] = image_array[y1:y2, x1:x2]
+    segmented_image = Image.fromarray(segmented_image_array)
+    black_image = Image.new("RGB", image.size, (255, 255, 255))
+    # transparency_mask = np.zeros_like((), dtype=np.uint8)
+    transparency_mask = np.zeros(
+        (image_array.shape[0], image_array.shape[1]), dtype=np.uint8
+    )
+    transparency_mask[y1:y2, x1:x2] = 255
+    transparency_mask_image = Image.fromarray(transparency_mask, mode="L")
+    black_image.paste(segmented_image, mask=transparency_mask_image)
+    return black_image
+
+
+def format_results(result, filter=0):
+    annotations = []
+    n = len(result.masks.data)
+    for i in range(n):
+        annotation = {}
+        mask = result.masks.data[i] == 1.0
+
+        if torch.sum(mask) < filter:
+            continue
+        annotation["id"] = i
+        annotation["segmentation"] = mask.cpu().numpy()
+        annotation["bbox"] = result.boxes.data[i]
+        annotation["score"] = result.boxes.conf[i]
+        annotation["area"] = annotation["segmentation"].sum()
+        annotations.append(annotation)
+    return annotations
+
+
+def filter_masks(annotations):  # filter the overlap mask
+    annotations.sort(key=lambda x: x["area"], reverse=True)
+    to_remove = set()
+    for i in range(0, len(annotations)):
+        a = annotations[i]
+        for j in range(i + 1, len(annotations)):
+            b = annotations[j]
+            if i != j and j not in to_remove:
+                # check if
+                if b["area"] < a["area"]:
+                    if (a["segmentation"] & b["segmentation"]).sum() / b[
+                        "segmentation"
+                    ].sum() > 0.8:
+                        to_remove.add(j)
+
+    return [a for i, a in enumerate(annotations) if i not in to_remove], to_remove
+
+
+def get_bbox_from_mask(mask):
+    mask = mask.astype(np.uint8)
+    contours, hierarchy = cv2.findContours(
+        mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE
+    )
+    x1, y1, w, h = cv2.boundingRect(contours[0])
+    x2, y2 = x1 + w, y1 + h
+    if len(contours) > 1:
+        for b in contours:
+            x_t, y_t, w_t, h_t = cv2.boundingRect(b)
+            # 将多个bbox合并成一个
+            x1 = min(x1, x_t)
+            y1 = min(y1, y_t)
+            x2 = max(x2, x_t + w_t)
+            y2 = max(y2, y_t + h_t)
+        h = y2 - y1
+        w = x2 - x1
+    return [x1, y1, x2, y2]
+
+
+def fast_process(
+    annotations, args, mask_random_color, bbox=None, points=None, edges=False
+):
+    if isinstance(annotations[0], dict):
+        annotations = [annotation["segmentation"] for annotation in annotations]
+    result_name = os.path.basename(args.img_path)
+    image = cv2.imread(args.img_path)
+    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+    original_h = image.shape[0]
+    original_w = image.shape[1]
+    if sys.platform == "darwin":
+            plt.switch_backend("TkAgg")
+    plt.figure(figsize=(original_w/100, original_h/100))
+    # Add subplot with no margin.
+    plt.subplots_adjust(top=1, bottom=0, right=1, left=0, hspace=0, wspace=0)
+    plt.margins(0, 0)
+    plt.gca().xaxis.set_major_locator(plt.NullLocator())
+    plt.gca().yaxis.set_major_locator(plt.NullLocator())
+    plt.imshow(image)
+    if args.better_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 args.device == "cpu":
+        annotations = np.array(annotations)
+        fast_show_mask(
+            annotations,
+            plt.gca(),
+            random_color=mask_random_color,
+            bbox=bbox,
+            points=points,
+            point_label=args.point_label,
+            retinamask=args.retina,
+            target_height=original_h,
+            target_width=original_w,
+        )
+    else:
+        if isinstance(annotations[0], np.ndarray):
+            annotations = torch.from_numpy(annotations)
+        fast_show_mask_gpu(
+            annotations,
+            plt.gca(),
+            random_color=args.randomcolor,
+            bbox=bbox,
+            points=points,
+            point_label=args.point_label,
+            retinamask=args.retina,
+            target_height=original_h,
+            target_width=original_w,
+        )
+    if isinstance(annotations, torch.Tensor):
+        annotations = annotations.cpu().numpy()
+    if args.withContours == True:
+        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)
+            if args.retina == False:
+                annotation = cv2.resize(
+                    annotation,
+                    (original_w, original_h),
+                    interpolation=cv2.INTER_NEAREST,
+                )
+            contours, hierarchy = 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)
+        color = np.array([0 / 255, 0 / 255, 255 / 255, 0.8])
+        contour_mask = temp / 255 * color.reshape(1, 1, -1)
+        plt.imshow(contour_mask)
+
+    save_path = args.output
+    if not os.path.exists(save_path):
+        os.makedirs(save_path)
+    plt.axis("off")
+    fig = plt.gcf()
+    plt.draw()
+    
+    try:
+        buf = fig.canvas.tostring_rgb()
+    except AttributeError:
+        fig.canvas.draw()
+        buf = fig.canvas.tostring_rgb()
+    
+    cols, rows = fig.canvas.get_width_height()
+    img_array = np.fromstring(buf, dtype=np.uint8).reshape(rows, cols, 3)
+    cv2.imwrite(os.path.join(save_path, result_name), cv2.cvtColor(img_array, cv2.COLOR_RGB2BGR))
+
+
+# CPU post process
+def fast_show_mask(
+    annotation,
+    ax,
+    random_color=False,
+    bbox=None,
+    points=None,
+    point_label=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)
+    annotation = annotation[sorted_indices]
+
+    index = (annotation != 0).argmax(axis=0)
+    if random_color == True:
+        color = np.random.random((msak_sum, 1, 1, 3))
+    else:
+        color = np.ones((msak_sum, 1, 1, 3)) * np.array(
+            [30 / 255, 144 / 255, 255 / 255]
+        )
+    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
+
+    show = 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
+    show[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 point_label[i] == 1],
+            [point[1] for i, point in enumerate(points) if point_label[i] == 1],
+            s=20,
+            c="y",
+        )
+        plt.scatter(
+            [point[0] for i, point in enumerate(points) if point_label[i] == 0],
+            [point[1] for i, point in enumerate(points) if point_label[i] == 0],
+            s=20,
+            c="m",
+        )
+
+    if retinamask == False:
+        show = cv2.resize(
+            show, (target_width, target_height), interpolation=cv2.INTER_NEAREST
+        )
+    ax.imshow(show)
+
+
+def fast_show_mask_gpu(
+    annotation,
+    ax,
+    random_color=False,
+    bbox=None,
+    points=None,
+    point_label=None,
+    retinamask=True,
+    target_height=960,
+    target_width=960,
+):
+    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)
+    if random_color == True:
+        color = torch.rand((msak_sum, 1, 1, 3)).to(annotation.device)
+    else:
+        color = torch.ones((msak_sum, 1, 1, 3)).to(annotation.device) * torch.tensor(
+            [30 / 255, 144 / 255, 255 / 255]
+        ).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
+    show = torch.zeros((height, weight, 4)).to(annotation.device)
+    h_indices, w_indices = torch.meshgrid(
+        torch.arange(height), torch.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
+    show[h_indices, w_indices, :] = mask_image[indices]
+    show_cpu = show.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 point_label[i] == 1],
+            [point[1] for i, point in enumerate(points) if point_label[i] == 1],
+            s=20,
+            c="y",
+        )
+        plt.scatter(
+            [point[0] for i, point in enumerate(points) if point_label[i] == 0],
+            [point[1] for i, point in enumerate(points) if point_label[i] == 0],
+            s=20,
+            c="m",
+        )
+    if retinamask == False:
+        show_cpu = cv2.resize(
+            show_cpu, (target_width, target_height), interpolation=cv2.INTER_NEAREST
+        )
+    ax.imshow(show_cpu)
+
+
+# clip
+@torch.no_grad()
+def retriev(
+    model, preprocess, elements: [Image.Image], search_text: str, device
+):
+    preprocessed_images = [preprocess(image).to(device) for image in elements]
+    tokenized_text = clip.tokenize([search_text]).to(device)
+    stacked_images = torch.stack(preprocessed_images)
+    image_features = model.encode_image(stacked_images)
+    text_features = model.encode_text(tokenized_text)
+    image_features /= image_features.norm(dim=-1, keepdim=True)
+    text_features /= text_features.norm(dim=-1, keepdim=True)
+    probs = 100.0 * image_features @ text_features.T
+    return probs[:, 0].softmax(dim=0)
+
+
+def crop_image(annotations, image_like):
+    if isinstance(image_like, str):
+        image = Image.open(image_like)
+    else:
+        image = image_like
+    ori_w, ori_h = image.size
+    mask_h, mask_w = annotations[0]["segmentation"].shape
+    if ori_w != mask_w or ori_h != mask_h:
+        image = image.resize((mask_w, mask_h))
+    cropped_boxes = []
+    cropped_images = []
+    not_crop = []
+    origin_id = []
+    for _, mask in enumerate(annotations):
+        if np.sum(mask["segmentation"]) <= 100:
+            continue
+        origin_id.append(_)
+        bbox = get_bbox_from_mask(mask["segmentation"])  # mask 的 bbox
+        cropped_boxes.append(segment_image(image, bbox))  # 保存裁剪的图片
+        # cropped_boxes.append(segment_image(image,mask["segmentation"]))
+        cropped_images.append(bbox)  # 保存裁剪的图片的bbox
+    return cropped_boxes, cropped_images, not_crop, origin_id, annotations
+
+
+def box_prompt(masks, bbox, target_height, target_width):
+    h = masks.shape[1]
+    w = masks.shape[2]
+    if h != target_height or w != target_width:
+        bbox = [
+            int(bbox[0] * w / target_width),
+            int(bbox[1] * h / target_height),
+            int(bbox[2] * w / target_width),
+            int(bbox[3] * h / target_height),
+        ]
+    bbox[0] = round(bbox[0]) if round(bbox[0]) > 0 else 0
+    bbox[1] = round(bbox[1]) if round(bbox[1]) > 0 else 0
+    bbox[2] = round(bbox[2]) if round(bbox[2]) < w else w
+    bbox[3] = round(bbox[3]) if round(bbox[3]) < h else h
+
+    # IoUs = torch.zeros(len(masks), dtype=torch.float32)
+    bbox_area = (bbox[3] - bbox[1]) * (bbox[2] - bbox[0])
+
+    masks_area = torch.sum(masks[:, bbox[1] : bbox[3], bbox[0] : bbox[2]], dim=(1, 2))
+    orig_masks_area = torch.sum(masks, dim=(1, 2))
+
+    union = bbox_area + orig_masks_area - masks_area
+    IoUs = masks_area / union
+    max_iou_index = torch.argmax(IoUs)
+
+    return masks[max_iou_index].cpu().numpy(), max_iou_index
+
+
+def point_prompt(masks, points, point_label, target_height, target_width):  # numpy 处理
+    h = masks[0]["segmentation"].shape[0]
+    w = masks[0]["segmentation"].shape[1]
+    if h != target_height or w != target_width:
+        points = [
+            [int(point[0] * w / target_width), int(point[1] * h / target_height)]
+            for point in points
+        ]
+    onemask = np.zeros((h, w))
+    masks = sorted(masks, key=lambda x: x['area'], reverse=True)
+    for i, annotation in enumerate(masks):
+        if type(annotation) == dict:
+            mask = annotation['segmentation']
+        else:
+            mask = annotation
+        for i, point in enumerate(points):
+            if mask[point[1], point[0]] == 1 and point_label[i] == 1:
+                onemask[mask] = 1
+            if mask[point[1], point[0]] == 1 and point_label[i] == 0:
+                onemask[mask] = 0
+    onemask = onemask >= 1
+    return onemask, 0
+
+
+def text_prompt(annotations, text, img_path, device, wider=False, threshold=0.9):
+    cropped_boxes, cropped_images, not_crop, origin_id, annotations_ = crop_image(
+        annotations, img_path
+    )
+    clip_model, preprocess = clip.load("./weights/CLIP_ViT_B_32.pt", device=device)
+    scores = retriev(
+        clip_model, preprocess, cropped_boxes, text, device=device
+    )
+    max_idx = scores.argsort()
+    max_idx = max_idx[-1]
+    max_idx = origin_id[int(max_idx)]
+
+    # find the biggest mask which contains the mask with max score
+    if wider:
+        mask0 = annotations_[max_idx]["segmentation"]
+        area0 = np.sum(mask0)
+        areas = [(i, np.sum(mask["segmentation"])) for i, mask in enumerate(annotations_) if i in origin_id]
+        areas = sorted(areas, key=lambda area: area[1], reverse=True)
+        indices = [area[0] for area in areas]
+        for index in indices:
+            if index == max_idx or np.sum(annotations_[index]["segmentation"] & mask0) / area0 > threshold:
+                max_idx = index
+                break
+
+    return annotations_[max_idx]["segmentation"], max_idx

utils/tools_gradio.py

@@ -0,0 +1,175 @@
+import numpy as np
+from PIL import Image
+import matplotlib.pyplot as plt
+import cv2
+import torch
+
+
+def fast_process(
+    annotations,
+    image,
+    device,
+    scale,
+    better_quality=False,
+    mask_random_color=True,
+    bbox=None,
+    use_retina=True,
+    withContours=True,
+):
+    if isinstance(annotations[0], dict):
+        annotations = [annotation['segmentation'] for annotation in annotations]
+
+    original_h = image.height
+    original_w = image.width
+    if better_quality:
+        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(),
+            random_color=mask_random_color,
+            bbox=bbox,
+            retinamask=use_retina,
+            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(),
+            random_color=mask_random_color,
+            bbox=bbox,
+            retinamask=use_retina,
+            target_height=original_h,
+            target_width=original_w,
+        )
+    if isinstance(annotations, torch.Tensor):
+        annotations = annotations.cpu().numpy()
+
+    if withContours:
+        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)
+            if use_retina == False:
+                annotation = cv2.resize(
+                    annotation,
+                    (original_w, original_h),
+                    interpolation=cv2.INTER_NEAREST,
+                )
+            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 withContours:
+        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,
+    random_color=False,
+    bbox=None,
+    retinamask=True,
+    target_height=960,
+    target_width=960,
+):
+    mask_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)
+    if random_color:
+        color = np.random.random((mask_sum, 1, 1, 3))
+    else:
+        color = np.ones((mask_sum, 1, 1, 3)) * np.array([30 / 255, 144 / 255, 255 / 255])
+    transparency = np.ones((mask_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))
+
+    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))
+
+    if not retinamask:
+        mask = cv2.resize(mask, (target_width, target_height), interpolation=cv2.INTER_NEAREST)
+
+    return mask
+
+
+def fast_show_mask_gpu(
+    annotation,
+    ax,
+    random_color=False,
+    bbox=None,
+    retinamask=True,
+    target_height=960,
+    target_width=960,
+):
+    device = annotation.device
+    mask_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)
+    if random_color:
+        color = torch.rand((mask_sum, 1, 1, 3)).to(device)
+    else:
+        color = torch.ones((mask_sum, 1, 1, 3)).to(device) * torch.tensor(
+            [30 / 255, 144 / 255, 255 / 255]
+        ).to(device)
+    transparency = torch.ones((mask_sum, 1, 1, 1)).to(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(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
+            )
+        )
+    if not retinamask:
+        mask_cpu = cv2.resize(
+            mask_cpu, (target_width, target_height), interpolation=cv2.INTER_NEAREST
+        )
+    return mask_cpu