from transformers_js import import_transformers_js, as_url import gradio as gr # Reference: https://huggingface.co/spaces/Xenova/yolov9-web/blob/main/index.js IMAGE_SIZE = 256; transformers = await import_transformers_js() AutoProcessor = transformers.AutoProcessor AutoModel = transformers.AutoModel RawImage = transformers.RawImage processor = await AutoProcessor.from_pretrained('Xenova/yolov9-c') # For this demo, we resize the image to IMAGE_SIZE x IMAGE_SIZE processor.feature_extractor.size = { "width": IMAGE_SIZE, "height": IMAGE_SIZE } model = await AutoModel.from_pretrained('Xenova/yolov9-c') async def detect(image_path): image = await RawImage.read(image_path) processed_input = await processor(image) result = await model(images=processed_input["pixel_values"]) outputs = result["outputs"] # Tensor np_outputs = outputs.to_numpy() # [xmin, ymin, xmax, ymax, score, id][] gradio_labels = [ # List[Tuple[numpy.ndarray | Tuple[int, int, int, int], str]] ( ( int(xmin * image.width / IMAGE_SIZE), int(ymin * image.height / IMAGE_SIZE), int(xmax * image.width / IMAGE_SIZE), int(ymax * image.height / IMAGE_SIZE), ), model.config.id2label[str(int(id))], ) for xmin, ymin, xmax, ymax, score, id in np_outputs ] annotated_image_data = image_path, gradio_labels return annotated_image_data, np_outputs demo = gr.Interface( detect, gr.Image(type="filepath"), [ gr.AnnotatedImage(), gr.JSON(), ], examples=[ ["cats.jpg"], ["city-streets.jpg"], ] ) demo.launch() transformers_js_py