app.py

import torchvision.transforms as transforms
import random 
import gradio as gr
import PIL




from fastai.vision.all import *
from huggingface_hub import from_pretrained_fastai
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 numpy as np
from pathlib import Path

try:
    import albumentations
except ImportError:
    os.system('pip install albumentations')
    import albumentations

try:
    import toml
except ImportError:
    os.system('pip install toml')
    import toml

os.system('pip install -U gradio')

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

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


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)

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

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

        mask[mask==255]=1
        mask[mask==150]=2
        mask[mask==76]=3
        mask[mask==74]=3
        mask[mask==29]=4
        mask[mask==25]=4

        mask[((mask!=1)&(mask!=2)&(mask!=3)&(mask!=4))]=0

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

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

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"])


# repo_id = "YOUR_USERNAME/YOUR_LEARNER_NAME"
repo_id = "lauragordo/model3"

#path_images = path/"Images"
#trainDLS = trainDB.dataloaders(path_images,bs=bs)
#learn = unet_learner(trainDLS,resnet50,metrics=[DiceMulti(), JaccardCoeff()]).to_fp16()
learn = from_pretrained_fastai(repo_id)
model=learn.model
model=model.cpu()
#labels = learner.dls.vocab
#classes = learner.dls.vocab[1]




def predict(img):
    img = PILImage.create(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==0]=255
    mask[mask==1]=150
    mask[mask==2]=76
    mask[mask==3]=25
    mask[mask==4]=0

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

    return Image.fromarray(mask.astype('uint8'))

# Creamos la interfaz y la lanzamos. 
gr.Interface(fn=predict, inputs=["image"], outputs=["image"],examples=['color_184.jpg','color_154.jpg']).launch(share=True)