import gradio as gr
import torch
import yolov7


# Images
torch.hub.download_url_to_file('https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg', 'zidane.jpg')
torch.hub.download_url_to_file('https://raw.githubusercontent.com/obss/sahi/main/tests/data/small-vehicles1.jpeg', 'small-vehicles1.jpeg')
    
def yolov7_inference(
    image: gr.inputs.Image = None,
    model_path: gr.inputs.Dropdown = None,
    image_size: gr.inputs.Slider = 640,
    conf_threshold: gr.inputs.Slider = 0.25,
    iou_threshold: gr.inputs.Slider = 0.45,
):

    model = yolov7.load(model_path, device="cpu", hf_model=True, trace=False)
    model.conf = conf_threshold
    model.iou = iou_threshold
    results = model([image], size=image_size)
    return results.render()[0]
        

inputs = [
    gr.inputs.Image(type="pil", label="Input Image"),
    gr.inputs.Dropdown(
        choices=[
            "StarAtNyte1/yolov7_custom",

        ],
        default="StarAtNyte1/yolov7_custom",
        label="Model",
    ),
]

outputs = gr.outputs.Image(type="filepath", label="Output Image")
title = "Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors"

examples = [['small-vehicles1.jpeg', 'kadirnar/yolov7-tiny-v0.1', 640, 0.25, 0.45], ['zidane.jpg', 'kadirnar/yolov7-v0.1', 640, 0.25, 0.45]]
demo_app = gr.Interface(
    fn=yolov7_inference,
    inputs=inputs,
    outputs=outputs,
    title=title,
    examples=examples,
    cache_examples=True,
    theme='huggingface',
)
demo_app.launch(debug=True, enable_queue=True)