update version

app.py

@@ -1,6 +1,5 @@
 import gradio as gr
-
-from metaseg import SegAutoMaskGenerator
+from metaseg import SegAutoMaskPredictor
 
 
 def image_app():
@@ -37,18 +36,24 @@ def image_app():
                             label="Points per Batch",
                         )
 
+                        seg_automask_image_min_area = gr.Number(
+                            value=0,
+                            label="Min Area",
+                        )
+
                 seg_automask_image_predict = gr.Button(value="Generator")
 
             with gr.Column():
                 output_image = gr.Image()
 
         seg_automask_image_predict.click(
-            fn=SegAutoMaskGenerator().save_image,
+            fn=SegAutoMaskPredictor().image_predict,
             inputs=[
                 seg_automask_image_file,
                 seg_automask_image_model_type,
                 seg_automask_image_points_per_side,
                 seg_automask_image_points_per_batch,
+                seg_automask_image_min_area,
             ],
             outputs=[output_image],
         )
@@ -93,24 +98,18 @@ def video_app():
                                     label="Min Area",
                                 )
 
-                                seg_automask_video_max_area = gr.Number(
-                                    value=10000,
-                                    label="Max Area",
-                                )
-
                 seg_automask_video_predict = gr.Button(value="Generator")
             with gr.Column():
                 output_video = gr.Video()
 
         seg_automask_video_predict.click(
-            fn=SegAutoMaskGenerator().save_video,
+            fn=SegAutoMaskPredictor().video_predict,
             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,
-                seg_automask_video_max_area,
             ],
             outputs=[output_video],
         )
@@ -127,7 +126,7 @@ def metaseg_app():
             <a href='https://twitter.com/kadirnar_ai' target='_blank'>Twitter</a> | <a href='https://github.com/kadirnar' target='_blank'>Github</a> | <a href='https://www.linkedin.com/in/kadir-nar/' target='_blank'>Linkedin</a> |
             </h5>
             """
-        )  
+        )
 
         with gr.Row():
             with gr.Column():
@@ -136,7 +135,7 @@ def metaseg_app():
                 with gr.Tab("Video"):
                     video_app()
 
-    app.queue(concurrency_count=2)
+    app.queue(concurrency_count=1)
     app.launch(debug=True, enable_queue=True)
 
 

demo.py

@@ -0,0 +1,94 @@
+from metaseg import SegAutoMaskPredictor, SegManualMaskPredictor, SahiAutoSegmentation, sahi_sliced_predict
+
+# For image
+
+
+def 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 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",
+        show=False,
+        save=True,
+    )
+    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
+
+from metaseg import SahiAutoSegmentation, sahi_sliced_predict
+
+
+def sahi_app(
+    image_path,
+    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,
+    )
+
+    autoseg = SahiAutoSegmentation().predict(
+        source=image_path,
+        model_type="vit_b",
+        input_box=boxes,
+        multimask_output=False,
+        random_color=False,
+        show=False,
+        save=True,
+    )
+    
+    return "output.png"

requirements.txt

@@ -1,4 +1,4 @@
-metaseg==0.3.0
+metaseg==0.5.2
 
 # code formatting
 black==21.7b0