from huggingface_hub import from_pretrained_fastai
import gradio as gr
from fastai.vision.all import *

import PIL
import torchvision.transforms as transforms
def transform_image(image):
    my_transforms = transforms.Compose([transforms.ToTensor(),
                                        transforms.Normalize(
                                            [0.485, 0.456, 0.406],
                                            [0.229, 0.224, 0.225])])
    image_aux = image
    return my_transforms(image_aux).unsqueeze(0).to(device)

repo_id = "Ignaciobfp/segmentacion-dron-marras"

learner = from_pretrained_fastai(repo_id)

device = torch.device("cuda" if torch.cuda.is_available() else "cpu") 
model = learner.model
model = model.cpu()



# Definimos una función que se encarga de llevar a cabo las predicciones
def predict(img):
    #img = PILImage.create(img)
    image = transforms.Resize((400,400))(img)
    tensor = transform_image(image=image)
    model.to(device)
    with torch.no_grad():
        outputs = model(tensor)
    outputs = torch.argmax(outputs,1)
    mask = np.array(outputs.cpu())
    mask[mask==1]=255
    mask=np.reshape(mask,(400,400))
    return mask
    
# Creamos la interfaz y la lanzamos. 
gr.Interface(fn=predict, inputs=gr.inputs.Image(shape=(400, 400)), outputs="image", examples=['examples/1CA SUR_1200_800.png', 'examples/1CA SUR_4000_1200.png', 'examples/1CA SUR_4800_2000.png']).launch(share=False)