import gradio as gr

from fastai.basics import *
from fastai.vision import models
from fastai.vision.all import *
from fastai.metrics import *
from fastai.data.all import *
from fastai.callback import *

import PIL
import torchvision.transforms as transforms

# direct download

from huggingface_hub import hf_hub_download
hf_hub_download(repo_id="Alesteba/deep_model_03", filename="unet.pth")

# load model

device = torch.device("cuda" if torch.cuda.is_available() else "cpu") 
model = torch.jit.load("unet.pth")
model = model.cpu()

def transform_image(image):
    
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    
    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)

# Definimos una función que se encarga de llevar a cabo las predicciones

def predict(img):
    img = PIL.Image.fromarray(img, "RGB")
    image = transforms.Resize((480,640))(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[mask==2]=150
    mask[mask==3]=76
    mask[mask==4]=29
    mask=np.reshape(mask,(480,640))
    return Image.fromarray(mask.astype('uint8'))

gr.Interface(
    fn=predict, 
    inputs=gr.inputs.Image(shape=(128, 128)), 
    outputs=[gr.outputs.Image(type="pil", label="Prediction")], 
    examples=['color_154.jpg','color_155.jpg']
).launch(share=False)