Add YOLOv12 Gradio app, requirements, and models

app.py

@@ -0,0 +1,166 @@
+# --------------------------------------------------------
+# Based on yolov10
+# https://github.com/THU-MIG/yolov10/app.py
+# --------------------------------------------------------'
+
+import gradio as gr
+import cv2
+import tempfile
+from ultralytics import YOLO
+
+
+def yolov12_inference(image, video, model_id, image_size, conf_threshold):
+    model = YOLO(model_id)
+    if image:
+        results = model.predict(source=image, imgsz=image_size, conf=conf_threshold)
+        annotated_image = results[0].plot()
+        return annotated_image[:, :, ::-1], None
+    else:
+        video_path = tempfile.mktemp(suffix=".webm")
+        with open(video_path, "wb") as f:
+            with open(video, "rb") as g:
+                f.write(g.read())
+
+        cap = cv2.VideoCapture(video_path)
+        fps = cap.get(cv2.CAP_PROP_FPS)
+        frame_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+        frame_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+
+        output_video_path = tempfile.mktemp(suffix=".webm")
+        out = cv2.VideoWriter(output_video_path, cv2.VideoWriter_fourcc(*'vp80'), fps, (frame_width, frame_height))
+
+        while cap.isOpened():
+            ret, frame = cap.read()
+            if not ret:
+                break
+
+            results = model.predict(source=frame, imgsz=image_size, conf=conf_threshold)
+            annotated_frame = results[0].plot()
+            out.write(annotated_frame)
+
+        cap.release()
+        out.release()
+
+        return None, output_video_path
+
+
+def yolov12_inference_for_examples(image, model_path, image_size, conf_threshold):
+    annotated_image, _ = yolov12_inference(image, None, model_path, image_size, conf_threshold)
+    return annotated_image
+
+
+def app():
+    with gr.Blocks():
+        with gr.Row():
+            with gr.Column():
+                image = gr.Image(type="pil", label="Image", visible=True)
+                video = gr.Video(label="Video", visible=False)
+                input_type = gr.Radio(
+                    choices=["Image", "Video"],
+                    value="Image",
+                    label="Input Type",
+                )
+                model_id = gr.Dropdown(
+                    label="Model",
+                    choices=[
+                        "yolov12n.pt",
+                        "yolov12s.pt",
+                        "yolov12m.pt",
+                        "yolov12l.pt",
+                        "yolov12x.pt",
+                        "brain_tumor.pt",
+                    ],
+                    value="yolov12m.pt",
+                )
+                image_size = gr.Slider(
+                    label="Image Size",
+                    minimum=320,
+                    maximum=1280,
+                    step=32,
+                    value=640,
+                )
+                conf_threshold = gr.Slider(
+                    label="Confidence Threshold",
+                    minimum=0.0,
+                    maximum=1.0,
+                    step=0.05,
+                    value=0.25,
+                )
+                yolov12_infer = gr.Button(value="Detect Objects")
+
+            with gr.Column():
+                output_image = gr.Image(type="numpy", label="Annotated Image", visible=True)
+                output_video = gr.Video(label="Annotated Video", visible=False)
+
+        def update_visibility(input_type):
+            image = gr.update(visible=True) if input_type == "Image" else gr.update(visible=False)
+            video = gr.update(visible=False) if input_type == "Image" else gr.update(visible=True)
+            output_image = gr.update(visible=True) if input_type == "Image" else gr.update(visible=False)
+            output_video = gr.update(visible=False) if input_type == "Image" else gr.update(visible=True)
+
+            return image, video, output_image, output_video
+
+        input_type.change(
+            fn=update_visibility,
+            inputs=[input_type],
+            outputs=[image, video, output_image, output_video],
+        )
+
+        def run_inference(image, video, model_id, image_size, conf_threshold, input_type):
+            if input_type == "Image":
+                return yolov12_inference(image, None, model_id, image_size, conf_threshold)
+            else:
+                return yolov12_inference(None, video, model_id, image_size, conf_threshold)
+
+
+        yolov12_infer.click(
+            fn=run_inference,
+            inputs=[image, video, model_id, image_size, conf_threshold, input_type],
+            outputs=[output_image, output_video],
+        )
+
+        gr.Examples(
+            examples=[
+                [
+                    "ultralytics/assets/bus.jpg",
+                    "yolov12s.pt",
+                    640,
+                    0.25,
+                ],
+                [
+                    "ultralytics/assets/zidane.jpg",
+                    "yolov12x.pt",
+                    640,
+                    0.25,
+                ],
+            ],
+            fn=yolov12_inference_for_examples,
+            inputs=[
+                image,
+                model_id,
+                image_size,
+                conf_threshold,
+            ],
+            outputs=[output_image],
+            cache_examples='lazy',
+        )
+
+gradio_app = gr.Blocks()
+with gradio_app:
+    gr.HTML(
+        """
+    <h1 style='text-align: center'>
+    YOLOv12: Attention-Centric Real-Time Object Detectors
+    </h1>
+    """)
+    gr.HTML(
+        """
+        <h3 style='text-align: center'>
+        <a href='https://arxiv.org/abs/2502.12524' target='_blank'>arXiv</a> | <a href='https://github.com/sunsmarterjie/yolov12' target='_blank'>github</a>
+        </h3>
+        """)
+    with gr.Row():
+        with gr.Column():
+            app()
+if __name__ == '__main__':
+    gradio_app.launch(share=True)

brain_tumor.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9e1470b4e7325d868c3d06e3e94970281b418941a9c96b003f6fd025b78d4f3
+size 19184787

requirements.txt

@@ -0,0 +1,21 @@
+torch==2.2.2 
+torchvision==0.17.2
+#flash_attn-2.7.3+cu11torch2.2cxx11abiFALSE-cp311-cp311-linux_x86_64.whl
+timm==1.0.14
+albumentations==2.0.4
+onnx==1.14.0
+onnxruntime==1.15.1
+pycocotools==2.0.7
+PyYAML==6.0.1
+scipy==1.13.0
+onnxslim==0.1.31
+onnxruntime-gpu==1.18.0
+gradio==4.44.1
+opencv-python==4.9.0.80
+psutil==5.9.8
+py-cpuinfo==9.0.0
+huggingface-hub==0.23.2
+safetensors==0.4.3
+numpy==1.26.4
+lap>=0.5.12
+ultralytics

yolo11n-cls.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c62d41bf9625777760018bf914d2e6cd472420ccd01706d97a61cb6c82502bd7
+size 5790624

yolo11n-pose.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:869e83fcdffdc7371fa4e34cd8e51c838cc729571d1635e5141e3075e9319dc0
+size 6255593

yolo11n.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ebbc80d4a7680d14987a577cd21342b65ecfd94632bd9a8da63ae6417644ee1
+size 5613764

yolo11s-seg.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1caa81c0195412efa411b632bcfb8c184939dddb6ae41f6a80c41b211ff257c3
+size 20669228

yolov12l.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0babd8dc8f775bb64bb052debdff3d8b9e9b57efa9d7bfa11c84bb82c3fec336
+size 53699086

yolov12n.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:419ff3dca37d69bacc93a50fa0c186a1c6f9fe62fae0f108b0872829689e9ca6
+size 5595063

yolov12s.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e915c2c4286e3f6f8610ef106fa3f94a7b8c19b30eccede5887e22c33ef75f58
+size 19006455

yolov12x.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:682ce8dadee004dbe964950f1bf3eda451671815a6ed62db80b398916b9b7c6f
+size 119322638