Raise self.exc_type(msg) ValueError: Caught ValueError in DataLoader worker process 0

1

Hello, I am training a UNet, and the input and output images are grayscale.
When I run it, I don’t know how to fixed the error

import torch
import torch.nn as nn
import torchvision.transforms.functional as TF


class DoubleConv(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(DoubleConv, self).__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(in_channels, out_channels, 3, 1, 1, bias=False),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True),
            nn.Conv2d(out_channels, out_channels, 3, 1, 1, bias=False),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True),
        )

    def forward(self, x):
        return self.conv(x)


class UNET(nn.Module):
    def __init__(self, in_channels=3, out_channels=1, features=[64, 128, 256, 512]):
        super(UNET, self).__init__()
        self.ups = nn.ModuleList()
        self.downs = nn.ModuleList()
        self.pool = nn.MaxPool2d(kernel_size=2, stride=2)

        # Down part of UNET
        for feature in features:
            self.downs.append(DoubleConv(in_channels, feature))
            in_channels = feature

        # Up part of UNET
        for feature in reversed(features):
            self.ups.append(
                nn.ConvTranspose2d(feature * 2, feature, kernel_size=2, stride=2),
            )
            self.ups.append(DoubleConv(feature * 2, feature))

            self.bottleneck = DoubleConv(features[-1], features[-1] * 2)
            self.final_conv = nn.Conv2d(features[0], out_channels, kernel_size=1)

    def forward(self, x):
        skip_connections = []

        for down in self.downs:
            x = down(x)
            skip_connections.append(x)
            x = self.pool(x)

        x = self.bottleneck(x)
        skip_connections = skip_connections[::-1]  # reverse sort
        for idx in range(0, len(self.ups), 2):
            x = self.ups[idx](x)
            skip_connection = skip_connections[idx // 2]  # floor division
            if x.shape != skip_connection.shape:
                x = TF.resize(x, size=skip_connection.shape[2:])

            concat_skip = torch.cat((skip_connection, x), dim=1)
            x = self.ups[idx + 1](concat_skip)

        return self.final_conv(x)


def test():
    x = torch.randn((3, 1, 600, 600))
    model = UNET(in_channels=1, out_channels=1)
    preds = model(x)
    print(x.shape)
    assert preds.shape == x.shape


if __name__ == "__main__":
    test()

It gives the error:


`Traceback (most recent call last):`
  File "C:/DeepLearning/UNet/train.py", line 120, in <module>
    main()
  File "C:/DeepLearning/UNet/train.py", line 98, in main
    check_accuracy(val_loader, model, device=DEVICE)
  File "C:\DeepLearning\UNet\utils.py", line 62, in check_accuracy
    for x, y in loader:
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\torch\utils\data\dataloader.py", line 517, in __next__
    data = self._next_data()
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\torch\utils\data\dataloader.py", line 1199, in _next_data
    return self._process_data(data)
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\torch\utils\data\dataloader.py", line 1225, in _process_data
    data.reraise()
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\torch\_utils.py", line 429, in reraise
    raise self.exc_type(msg)
ValueError: Caught ValueError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\torch\utils\data\_utils\worker.py", line 202, in _worker_loop
    data = fetcher.fetch(index)
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\torch\utils\data\_utils\fetch.py", line 44, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\torch\utils\data\_utils\fetch.py", line 44, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "C:\DeepLearning\UNet\dataset.py", line 24, in __getitem__
    augmentations = self.transform(image=image, mask=mask)
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\albumentations\core\composition.py", line 182, in __call__
    data = t(force_apply=force_apply, **data)
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\albumentations\core\transforms_interface.py", line 89, in __call__
    return self.apply_with_params(params, **kwargs)
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\albumentations\core\transforms_interface.py", line 102, in apply_with_params
    res[key] = target_function(arg, **dict(params, **target_dependencies))
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\albumentations\augmentations\transforms.py", line 1496, in apply
    return F.normalize(image, self.mean, self.std, self.max_pixel_value)
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\albumentations\augmentations\functional.py", line 141, in normalize
    img -= mean
ValueError: operands could not be broadcast together with shapes (600,600,2) (3,) (600,600,2)
1 Like
2

The error source utils.py:

import torch
import torchvision
from dataset import CarvanaDataset
from torch.utils.data import DataLoader

def save_checkpoint(state, filename="my_checkpoint.pth.tar"):
    print("=> Saving checkpoint")
    torch.save(state, filename)

def load_checkpoint(checkpoint, model):
    print("=> Loading checkpoint")
    model.load_state_dict(checkpoint["state_dict"])

def get_loaders(
    train_dir,
    train_maskdir,
    val_dir,
    val_maskdir,
    batch_size,
    train_transform,
    val_transform,
    num_workers=4,
    pin_memory=True,
):
    train_ds = CarvanaDataset(
        image_dir=train_dir,
        mask_dir=train_maskdir,
        transform=train_transform,
    )

    train_loader = DataLoader(
        train_ds,
        batch_size=batch_size,
        num_workers=num_workers,
        pin_memory=pin_memory,
        shuffle=True,
    )

    val_ds = CarvanaDataset(
        image_dir=val_dir,
        mask_dir=val_maskdir,
        transform=val_transform,
    )

    val_loader = DataLoader(
        val_ds,
        batch_size=batch_size,
        num_workers=num_workers,
        pin_memory=pin_memory,
        shuffle=False,
    )

    return train_loader, val_loader

def check_accuracy(loader, model, device="cuda"):
    num_correct = 0
    num_pixels = 0
    dice_score = 0
    model.eval()

    with torch.no_grad():
        for x, y in loader:
            x = x.to(device)
            y = y.to(device).unsqueeze(1)
            preds = torch.sigmoid(model(x))
            preds = (preds > 0.5).float()  # 0, 1 matrix
            num_correct += (preds == y).sum()
            num_pixels += torch.numel(preds)
            dice_score += (2 * (preds * y).sum())/(
                (preds+y).sum() + 1e-8
            )

        print(
            f"Got {num_correct}/{num_pixels} with acc {num_correct/num_pixels*100:.2f}"
            )
        print(f"Dice score: {dice_score/len(loader)}")
        model.train()

def save_predictions_as_imgs(
        loader, model, folder="saved_images/", device="cuda"
):
    model.eval()
    for idx, (x, y) in enumerate(loader):
        x = x.to(device=device)
        with torch.no_grad():
            preds = torch.sigmoid(model(x))
            preds = (preds > 0.5).float()
        torchvision.utils.save_image(
            preds, f"{folder}/pred_{idx}.png"
        )
        torchvision.utils.save_image(y.unsqueeze(1), f"{folder}{idx}.png")

    model.train()
3

The error has already been printed out. Can you please check your transform function?

4

@ejguan I have no idea how to adjust it.
Hello, here is my Dataset class:

from PIL import Image
from torch.utils.data import Dataset
import numpy as np
import os

class CarvanaDataset(Dataset):
    def __init__(self, image_dir, mask_dir, transform=None):
        self.image_dir = image_dir
        self.mask_dir = mask_dir
        self.transform = transform
        self.images = os.listdir(image_dir)

    def __len__(self):
        return len(self.images)

    def __getitem__(self, index):
        img_path = os.path.join(self.image_dir, self.images[index])
        mask_path = os.path.join(self.mask_dir, self.images[index].replace(".jpq", "_mask.gif"))
        image = np.array(Image.open(img_path).convert("L"))
        mask = np.array(Image.open(mask_path).convert("L"), dtype=np.float32)
        mask[mask == 255.0] = 1.0

        if self.transform is not None:
            augmentations = self.transform(image=image, mask=mask)
            image = augmentations["image"]
            mask = augmentations["mask"]

        return image, mask
5

Can you share your transform? The error comes from it.
And, can you print out your the shape of image and mask?

6 
import torch
import albumentations as A
from albumentations.pytorch import ToTensorV2
from tqdm import tqdm
import torch.nn as nn
import torch.optim as optim
from model import UNET
from utils import (
    load_checkpoint,
    save_checkpoint,
    get_loaders,
    check_accuracy,
    save_predictions_as_imgs,
)

# Hyperparameters etc.
LEARNING_RATE = 1e-4
DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
BATCH_SIZE = 16
NUM_EPOCHS = 3
NUM_WORKERS = 2
IMAGE_HEIGHT = 600  # 1280 originally
IMAGE_WIDTH = 600  # 1918 originally
PIN_MEMORY = True
LOAD_MODEL = False
TRAIN_IMG_DIR = "C:\DeepLearning\\train\img"
TRAIN_MASK_DIR = "C:\DeepLearning\\train\mask"
VAL_IMG_DIR = "C:\DeepLearning\\test\img"
VAL_MASK_DIR = "C:\DeepLearning\\test\mask"

def train_fn(loader, model, optimizer, loss_fn, scalar):
    loop = tqdm(loader)

    for batch_idx, (data, targets) in enumerate(loop):
        data = data.to(DEVICE)
        targets = targets.float().unsqueeze(1).to(DEVICE)

        # forward
        with torch.cuda.amp.autocast():
            predictions = model(data)
            loss = loss_fn(predictions, targets)

        # backward
        optimizer.zero_grad()
        scalar.scale(loss).backward()
        scalar.step(optimizer)
        scaler.update()

        # update tqdm loop
        loop.set_postfix(loss=loss.item())

def main():
    train_transform = A.Compose(
        [
            A.Resize(height=IMAGE_HEIGHT, width=IMAGE_WIDTH),
            A.Rotate(limit=35, p=1.0),
            A.HorizontalFlip(p=0.5),
            A.Normalize(
                mean=[0.0, 0.0, 0.0],
                std=[1.0, 1.0, 1.0],
                max_pixel_value=255.0,
            ),
            ToTensorV2(),
        ]
    )
    val_transforms = A.Compose(
        [
            A.Resize(height=IMAGE_HEIGHT, width=IMAGE_WIDTH),
            A.Normalize(
                mean=[0.0, 0.0, 0.0],
                std=[1.0, 1.0, 1.0],
                max_pixel_value=255.0,
            ),
            ToTensorV2(),
        ],
    )


    model = UNET(in_channels=1, out_channels=1).to(DEVICE)
    loss_fn = nn.BCEWithLogitsLoss()  # This loss combines a Sigmoid layer and the BCELoss in one single class
    opimizer = optim.Adam(model.parameters(), lr=LEARNING_RATE)

    train_loader, val_loader = get_loaders(
        TRAIN_IMG_DIR,
        TRAIN_MASK_DIR,
        VAL_IMG_DIR,
        VAL_MASK_DIR,
        BATCH_SIZE,
        train_transform,
        val_transforms,
        NUM_WORKERS,
        PIN_MEMORY,
    )

    if LOAD_MODEL:
        load_checkpoint(torch.load("my_checkpoint.pth.tar"), model)

    check_accuracy(val_loader, model, device=DEVICE)
    scaler = torch.cuda.amp.GradScaler()

    for epoch in range(NUM_EPOCHS):
        train_fn(train_loader, model, opimizer, loss_fn, scaler)

        # save model
        checkpoint = {
            "state_dict": model.state_dict(),
            "optimizer": optimizer.state_dict(),
        }
        save_checkpoint(checkpoint)

        # check accuracy
        check_accuracy(val_loader, model, device=DEVICE)

        # print some examplea to a folder
        save_predictions_as_imgs(
            val_loader, model, folder="saved_images/", device=DEVICE
        )

if __name__ == "__main__":
    main()


from PIL import Image
from torch.utils.data import Dataset
import numpy as np
import os

class CarvanaDataset(Dataset):
    def __init__(self, image_dir, mask_dir, transform=None):
        self.image_dir = image_dir
        self.mask_dir = mask_dir
        self.transform = transform
        self.images = os.listdir(image_dir)
        self.masks = os.listdir(mask_dir)
    def __len__(self):
        return len(self.images)

    def __getitem__(self, index):
        img_path = os.path.join(self.image_dir, self.images[index])
        mask_path = os.path.join(self.mask_dir, self.masks[index])
        image = np.array(Image.open(img_path).convert("L"))
        mask = np.array(Image.open(mask_path).convert("L"), dtype=np.float32)
        mask[mask == 255.0] = 1.0

        if self.transform is not None:
            augmentations = self.transform(image=image, mask=mask)
            image = augmentations["image"]
            mask = augmentations["mask"]

        return image, mask

if __name__ == "__main__":
    data = CarvanaDataset('C:\DeepLearning\\train\img', 'C:\DeepLearning\\train\mask')
    image, mask = data.__getitem__(0)
    print(image.shape)
    print(mask.shape)

print(image.shape)
7

You image has single channel.

But you transform function expects three channel inputs. You should either change your image or your transform function.

8

After your advise, the result of the shapes become:

from PIL import Image
from torch.utils.data import Dataset
import numpy as np
import os

class CarvanaDataset(Dataset):
    def __init__(self, image_dir, mask_dir, transform=None):
        self.image_dir = image_dir
        self.mask_dir = mask_dir
        self.transform = transform
        self.images = os.listdir(image_dir)
        self.masks = os.listdir(mask_dir)
    def __len__(self):
        return len(self.images)

    def __getitem__(self, index):
        img_path = os.path.join(self.image_dir, self.images[index])
        mask_path = os.path.join(self.mask_dir, self.masks[index])
        image = np.array(Image.open(img_path).convert("L"))
        image = np.expand_dims(image, axis=0)
        mask = np.array(Image.open(mask_path).convert("L"), dtype=np.float32)
        mask = np.expand_dims(mask, axis=0)
        mask[mask == 255.0] = 1.0

        if self.transform is not None:
            augmentations = self.transform(image=image, mask=mask)
            image = augmentations["image"]
            mask = augmentations["mask"]

        return image, mask

if __name__ == "__main__":
    data = CarvanaDataset('C:\DeepLearning\\train\img', 'C:\DeepLearning\\train\mask')
    image, mask = data.__getitem__(0)
    print(image.shape)
    print(mask.shape)
-->
(1, 600, 600)
(1, 600, 600)

Another new error comes here when run train.py:

Traceback (most recent call last):
  File "C:/DeepLearning/UNet/train.py", line 120, in <module>
    main()
  File "C:/DeepLearning/UNet/train.py", line 98, in main
    check_accuracy(val_loader, model, device=DEVICE)
  File "C:\DeepLearning\UNet\utils.py", line 62, in check_accuracy
    for x, y in loader:
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\torch\utils\data\dataloader.py", line 517, in __next__
    data = self._next_data()
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\torch\utils\data\dataloader.py", line 1199, in _next_data
    return self._process_data(data)
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\torch\utils\data\dataloader.py", line 1225, in _process_data
    data.reraise()
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\torch\_utils.py", line 429, in reraise
    raise self.exc_type(msg)
ValueError: Caught ValueError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\torch\utils\data\_utils\worker.py", line 202, in _worker_loop
    data = fetcher.fetch(index)
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\torch\utils\data\_utils\fetch.py", line 44, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\torch\utils\data\_utils\fetch.py", line 44, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "C:\DeepLearning\UNet\dataset.py", line 26, in __getitem__
    augmentations = self.transform(image=image, mask=mask)
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\albumentations\core\composition.py", line 182, in __call__
    data = t(force_apply=force_apply, **data)
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\albumentations\core\transforms_interface.py", line 89, in __call__
    return self.apply_with_params(params, **kwargs)
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\albumentations\core\transforms_interface.py", line 102, in apply_with_params
    res[key] = target_function(arg, **dict(params, **target_dependencies))
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\albumentations\augmentations\transforms.py", line 1496, in apply
    return F.normalize(image, self.mean, self.std, self.max_pixel_value)
  File "C:\Users\Tsai\anaconda3\envs\tf\lib\site-packages\albumentations\augmentations\functional.py", line 141, in normalize
    img -= mean
ValueError: operands could not be broadcast together with shapes (600,600,600) (3,) (600,600,600)

How should I adjust my input or transform content? Thanks

9

Emmm. You were changing the wrong part.
Two options for you, you should choose ONE of them depending on your use case:

  1. Change image to three-channel (RGB rather than L mode)
        image = np.array(Image.open(img_path).convert("RGB"))
  1. Change transform to single-channel
train_transform = A.Compose(
        [
            A.Resize(height=IMAGE_HEIGHT, width=IMAGE_WIDTH),
            A.Rotate(limit=35, p=1.0),
            A.HorizontalFlip(p=0.5),
            A.Normalize(
                mean=[0.0],
                std=[1.0],
                max_pixel_value=255.0,
            ),
            ToTensorV2(),
        ]
    )