app.py

#
from huggingface_hub import from_pretrained_fastai
import gradio as gr
from fastai.vision.all import *
from fastai.learner import load_learner
from PIL import Image

from albumentations import (
    Compose,
    OneOf,
    ElasticTransform,
    GridDistortion,
    OpticalDistortion,
    HorizontalFlip,
    Rotate,
    Transpose,
    CLAHE,
    ShiftScaleRotate
)

def get_y_fn (x):
    return Path(str(x).replace("Images","Labels").replace("color","gt").replace(".jpg",".png"))

class SegmentationAlbumentationsTransform(ItemTransform):
    split_idx = 0

    def __init__(self, aug):
        self.aug = aug

    def encodes(self, x):
        img,mask = x
        aug = self.aug(image=np.array(img), mask=np.array(mask))
        return PILImage.create(aug["image"]), PILMask.create(aug["mask"])

class TargetMaskConvertTransform(ItemTransform):
    def __init__(self):
        pass
    def encodes(self, x):
        img,mask = x

        #Convert to array
        mask = np.array(mask)

        # mask[mask!=255]=0
        # Change 255 for 1
        mask[mask==255]=1
        mask[mask==150]=2
        mask[mask==74]=3
        mask[mask==76]=3
        mask[mask==29]=4
        mask[mask==25]=4
# mask[mask==255]=1

        # Back to PILMask
        mask = PILMask.create(mask)
        return img, mask

# Carga el modelo después de definir la clase
repo_id = "LuisCe/Practica03"
learner = from_pretrained_fastai(repo_id)


# Carga el modelo previamente entrenado
model = learner.model
model = model.cpu()
model.eval()

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)

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


def prediccion(img):
  img = Image.fromarray(img)
  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]=74
  mask[mask==4]=29

  mask=np.reshape(mask,(480,640))

  return(mask)

# Crea la interfaz Gradio
gr.Interface(prediccion,
              inputs="image",
              outputs="image",
              title="Grape Segmentation",
              description="Segment grapes in the image.",
              theme="compact",
              allow_flagging=False).launch(debug=True)