app.py

from huggingface_hub import from_pretrained_fastai
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 *


from pathlib import Path
import random
import PIL
import torchvision.transforms as transformss
from albumentations import *

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

def ParentSplitter(x):
    return Path(x).parent.name==test_name

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"])

transforms=Compose([HorizontalFlip(p=0.5),
                    Rotate(p=0.40,limit=10),GridDistortion()
                    ],p=1)
transformPipeline=SegmentationAlbumentationsTransform(transforms)

class TargetMaskConvertTransform(ItemTransform):
    def __init__(self): 
        pass
    def encodes(self, x):
        img,mask = x
        
        #Convert to array
        mask = np.array(mask)
        
        # Aquí definimos cada clase en la máscara
        # uva:
        mask[mask==255]=1
        # hojas:
        mask[mask==150]=2
        # conductores:
        mask[mask==76]=3
        mask[mask==74]=3
        # madera:
        mask[mask==29]=4
        mask[mask==25]=4
        
        # Back to PILMask
        mask = PILMask.create(mask)
        return img, mask

repo_id = "paascorb/practica3_Segmentation"

learner = from_pretrained_fastai(repo_id)

def transform_image(image):
    my_transforms = transformss.Compose([transformss.ToTensor(),
                                        transformss.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)

def predict(img):
    img = PIL.Image.fromarray(img, "RGB")
    image = transformss.Resize((480,640))(img)
    tensor = transform_image(image=img) 

    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    learner.to(device)
    with torch.no_grad():
        outputs = learner(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="Predicción")], examples=['color_155.jpg','color_154.jpg']).launch(share=False)