import torch
import torchvision
import TractionModel as plup
import gradio as gr


def init_model(path):
    model = plup.create_model()
    model = plup.load_weights(model, path)
    model.eval()
    return model


def inference(image):
    image = vanilla_transform(image).to(device).unsqueeze(0)
    with torch.no_grad():
        pred = model(image)
    res = float(torch.sigmoid(pred[1].to("cpu")).numpy()[0])
    return {'pull-up': res, 'no pull-up': 1 - res}


norm_mean = [0.485, 0.456, 0.406]
norm_std = [0.229, 0.224, 0.225]
vanilla_transform = torchvision.transforms.Compose([
                                                    torchvision.transforms.Resize(224),
                                                    torchvision.transforms.ToTensor(),
                                                    torchvision.transforms.Normalize(norm_mean, norm_std)])

model = init_model("model-score0.96-f1_10.9-f1_20.99.pt")
if torch.cuda.is_available():
    device = torch.device("cuda")
else:
    device = torch.device("cpu")
model = model.to(device)


examples = [['tibo.png'], ['tibo2.png'], ['real_pull_up.png'], ['no_pull_up.png'], ['doge.jpg']]
iface = gr.Interface(inference, live=True, inputs=gr.inputs.Image(source="upload", type='pil'),
                     outputs=gr.outputs.Label(),
                     examples=examples,
                     enable_queue=True)

iface.test_launch()
if __name__ == "__main__":
    iface.launch(share=True, enable_queue=True)