Upload 5 files

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+image_data/IMG_3352.JPG filter=lfs diff=lfs merge=lfs -text
+image_data/IMG_3353.JPG filter=lfs diff=lfs merge=lfs -text
+image_data/IMG_3354.JPG filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,156 @@
+import gradio as gr
+import spaces
+from huggingface_hub import hf_hub_download
+
+
+def download_models(model_id):
+    hf_hub_download("merve/yolov9", filename=f"{model_id}", local_dir=f"./")
+    return f"./{model_id}"
+
+@spaces.GPU
+def yolov9_inference(img_path, model_id, image_size, conf_threshold, iou_threshold):
+	"""
+	Performs object detection using a YOLOv9 model. This function loads a specified YOLOv9 model,
+	configures it based on the provided parameters, and carries out inference on a given image. 
+	Additionally, it allows for optional modification of the input size and the application of 
+	test time augmentation to potentially improve detection accuracy.
+
+	Parameters:
+	    model_path (str): The file path to the pre-trained YOLOv9 model.
+	    conf_threshold (float): The confidence threshold used during Non-Maximum Suppression (NMS)
+		to filter detections. Detections with confidence levels below this threshold are discarded.
+	    iou_threshold (float): The Intersection over Union (IoU) threshold applied in NMS. Detections 
+		with IoU values above this threshold are considered overlapping and are hence merged.
+	    img_path (str): The file path to the image on which inference is to be performed.
+	    size (int, optional): The input size for inference. Altering this may affect the accuracy and 
+		speed of the detection process.
+
+	Returns:
+	    tuple: A tuple containing the detection results. This includes the bounding boxes (boxes),
+	    confidence scores (scores), and detected categories (categories), alongside a results object
+	    for further processing, such as visualization.
+	"""
+	
+    # Import YOLOv9
+    import yolov9
+    
+    # Load the model
+    model_path = download_models(model_id)
+    model = yolov9.load(model_path, device="cuda:0")
+    
+    # Set model parameters
+    model.conf = conf_threshold
+    model.iou = iou_threshold
+    
+    # Perform inference
+    results = model(img_path, size=image_size)
+
+    # Optionally, show detection bounding boxes on image
+    output = results.render()
+    
+    return output[0]
+
+
+def app():
+    with gr.Blocks():
+        with gr.Row():
+            with gr.Column():
+                img_path = gr.Image(type="filepath", label="Image")
+                model_path = gr.Dropdown(
+                    label="Model",
+                    choices=[
+                        "gelan-c.pt",
+                        "gelan-e.pt",
+                        "yolov9-c.pt",
+                        "yolov9-e.pt",
+                    ],
+                    value="gelan-e.pt",
+                )
+                image_size = gr.Slider(
+                    label="Image Size",
+                    minimum=320,
+                    maximum=1280,
+                    step=32,
+                    value=640,
+                )
+                conf_threshold = gr.Slider(
+                    label="Confidence Threshold",
+                    minimum=0.1,
+                    maximum=1.0,
+                    step=0.1,
+                    value=0.4,
+                )
+                iou_threshold = gr.Slider(
+                    label="IoU Threshold",
+                    minimum=0.1,
+                    maximum=1.0,
+                    step=0.1,
+                    value=0.5,
+                )
+                yolov9_infer = gr.Button(value="Inference")
+
+            with gr.Column():
+                output_numpy = gr.Image(type="numpy",label="Output")
+
+        yolov9_infer.click(
+            fn=yolov9_inference,
+            inputs=[
+                img_path,
+                model_path,
+                image_size,
+                conf_threshold,
+                iou_threshold,
+            ],
+            outputs=[output_numpy],
+        )
+        
+        gr.Examples(
+            examples=[
+                [
+                    "image_data/IMG_3352.JPG",
+                    "gelan-e.pt",
+                    640,
+                    0.4,
+                    0.5,
+                ],
+                [
+                    "image_data/IMG_3353.JPG",
+                    "yolov9-c.pt",
+                    640,
+                    0.4,
+                    0.5,
+                ],
+            ],
+            fn=yolov9_inference,
+            inputs=[
+                img_path,
+                model_path,
+                image_size,
+                conf_threshold,
+                iou_threshold,
+            ],
+            outputs=[output_numpy],
+            cache_examples=True,
+        )
+
+# Initialize a Gradio Blocks application.
+gradio_app = gr.Blocks()
+
+with gradio_app:
+    # Display a title using HTML, centered.
+    gr.HTML("""
+        <h1 style='text-align: center; margin-bottom: 20px;'>
+        YOLOv9 from PipYoloV9 on my data
+        </h1>
+    """)
+
+    # Assuming 'app()' represents your main app functionality.
+    # If 'app()' involves Gradio interface components, directly place those components here.
+    # Example: gr.Image() for image input, gr.Button() for a button, etc.
+    # Replace 'app()' with your actual Gradio components or function call.
+    app()
+
+# Launch the Gradio app, enabling debug mode for detailed error logs and server information.
+gradio_app.launch(debug=True)
+
+

requirements.txt

@@ -0,0 +1,2 @@
+yolov9pip==0.0.4
+huggingface_hub