start app develop

app.py

@@ -0,0 +1,91 @@
+import gradio as gr
+from demo import automask_image_app, automask_video_app, sahi_autoseg_app
+import argparse
+import cv2
+import time   
+def pause_video():
+    print(time.time())
+def play_video():
+    print("play video")
+    print(time.time)
+
+
+with gr.Blocks() as iface:
+    with gr.Row():
+        with gr.Column(scale=1.0):
+            seg_automask_video_file = gr.Video().style(height=720)
+            gr.Video.g
+            seg_automask_video_file.play(fn=play_video)
+            seg_automask_video_file.pause(fn=pause_video)
+            with gr.Row():
+                with gr.Column():
+                    seg_automask_video_model_type = gr.Dropdown(
+                        choices=[
+                            "vit_h",
+                            "vit_l",
+                            "vit_b",
+                        ],
+                        value="vit_l",
+                        label="Model Type",
+                    )
+                    seg_automask_video_min_area = gr.Number(
+                        value=1000,
+                        label="Min Area",
+                    )
+
+                with gr.Row():
+                    with gr.Column():
+                        seg_automask_video_points_per_side = gr.Slider(
+                            minimum=0,
+                            maximum=32,
+                            step=2,
+                            value=16,
+                            label="Points per Side",
+                        )
+                        
+                        seg_automask_video_points_per_batch = gr.Slider(
+                            minimum=0,
+                            maximum=64,
+                            step=2,
+                            value=64,
+                            label="Points per Batch",
+                        )
+
+            seg_automask_video_predict = gr.Button(value="Generator")
+    
+        
+        # Display the first frame 
+        # with gr.Column():
+            # first_frame = gr.Image(type="pil", interactive=True, elem_id="first_frame")
+            # seg_automask_firstframe = gr.Button(value="Find target")
+            
+            # video_input = gr.inputs.Video(type="mp4")
+
+            # output = gr.outputs.Image(type="pil")
+
+            # gr.Interface(fn=capture_frame, inputs=seg_automask_video_file, outputs=first_frame)
+
+    # seg_automask_video_predict.click(
+    #     fn=automask_video_app,
+    #     inputs=[
+    #         seg_automask_video_file,
+    #         seg_automask_video_model_type,
+    #         seg_automask_video_points_per_side,
+    #         seg_automask_video_points_per_batch,
+    #         seg_automask_video_min_area,
+    #     ],
+    #     outputs=[output_video],
+    # )
+
+
+
+
+
+
+
+
+iface.queue(concurrency_count=1)
+iface.launch(debug=True, enable_queue=True, server_port=12212, server_name="0.0.0.0")
+
+
+    

app_test.py

@@ -0,0 +1,37 @@
+import gradio as gr
+import time
+
+def capture_frame(video):
+    frame = video.get_frame_at_sec(video.current_time)
+    return frame
+
+def capture_time(video):
+    while True:
+        if video.paused:
+            time_paused = video.current_time
+            return time_paused
+
+iface = gr.Interface(fn=capture_frame, 
+                     inputs=[gr.inputs.Video(type="mp4", label="Input video", 
+                                             source="upload")],
+                     outputs=["image"], 
+                     server_port=12212, 
+                     server_name="0.0.0.0",
+                     capture_session=True)
+
+video_player = iface.video[0]
+video_player.pause = False
+
+time_interface = gr.Interface(fn=capture_time,
+                              inputs=[gr.inputs.Video(type="mp4", label="Input video",
+                                                      source="upload", max_duration=10)],
+                              outputs=["text"],
+                              server_port=12212,
+                              server_name="0.0.0.0",
+                              capture_session=True)
+
+time_interface.video[0].play = False
+time_interface.video[0].pause = False
+
+iface.launch()
+time_interface.launch()

demo.py

@@ -0,0 +1,87 @@
+from metaseg import SegAutoMaskPredictor, SegManualMaskPredictor, SahiAutoSegmentation, sahi_sliced_predict
+
+# For image
+
+def automask_image_app(image_path, model_type, points_per_side, points_per_batch, min_area):
+    SegAutoMaskPredictor().image_predict(
+        source=image_path,
+        model_type=model_type,  # vit_l, vit_h, vit_b
+        points_per_side=points_per_side,
+        points_per_batch=points_per_batch,
+        min_area=min_area,
+        output_path="output.png",
+        show=False,
+        save=True,
+    )
+    return "output.png"
+
+
+# For video
+
+def automask_video_app(video_path, model_type, points_per_side, points_per_batch, min_area):
+    SegAutoMaskPredictor().video_predict(
+        source=video_path,
+        model_type=model_type,  # vit_l, vit_h, vit_b
+        points_per_side=points_per_side,
+        points_per_batch=points_per_batch,
+        min_area=min_area,
+        output_path="output.mp4",
+    )
+    return "output.mp4"
+
+
+# For manuel box and point selection
+
+def manual_app(image_path, model_type, input_point, input_label, input_box, multimask_output, random_color):
+    SegManualMaskPredictor().image_predict(
+        source=image_path,
+        model_type=model_type,  # vit_l, vit_h, vit_b
+        input_point=input_point,
+        input_label=input_label,
+        input_box=input_box,
+        multimask_output=multimask_output,
+        random_color=random_color,
+        output_path="output.png",
+        show=False,
+        save=True,
+    )
+    return "output.png"
+
+
+# For sahi sliced prediction
+
+def sahi_autoseg_app(
+    image_path,
+    sam_model_type,
+    detection_model_type,
+    detection_model_path,
+    conf_th,
+    image_size,
+    slice_height,
+    slice_width,
+    overlap_height_ratio,
+    overlap_width_ratio,
+):
+    boxes = sahi_sliced_predict(
+        image_path=image_path,
+        detection_model_type=detection_model_type,  # yolov8, detectron2, mmdetection, torchvision
+        detection_model_path=detection_model_path,
+        conf_th=conf_th,
+        image_size=image_size,
+        slice_height=slice_height,
+        slice_width=slice_width,
+        overlap_height_ratio=overlap_height_ratio,
+        overlap_width_ratio=overlap_width_ratio,
+    )
+
+    SahiAutoSegmentation().predict(
+        source=image_path,
+        model_type=sam_model_type,
+        input_box=boxes,
+        multimask_output=False,
+        random_color=False,
+        show=False,
+        save=True,
+    )
+    
+    return "output.png"

requirements.txt

@@ -12,4 +12,4 @@ pycocotools
 matplotlib
 onnxruntime
 onnx
-
+metaseg