RuntimeError: output with shape doesn't match the broadcast shape

vision
1

I want to train RGB images on ResNet50 using transfer learning method.
I was resized images to 224x224 and I got error using GPU:

RuntimeError: output with shape [1, 224, 224] doesn't match the broadcast shape [3, 224, 224]

On CPU all works fine.

How to deal with it?

2

Could you post the line of code throwing this error?
It seems strange that your code is running fine on the CPU.

3

I get error on filepath line and image = self.transform

    def __getitem__(self, index):
        """Generate one sample of data."""
        filepath = os.path.join(self.root + "/img/" + self.filenames[index])
        bbox = self.bbox[index]
        image = cv2.imread(filepath, cv2.IMREAD_COLOR)
        image = image[bbox[1]:bbox[3], bbox[0]:bbox[2]]
        image = cv2.copyMakeBorder(image, bbox[1], bbox[3], bbox[0], bbox[2], cv2.BORDER_CONSTANT, value=[255, 255, 255])
        attribute_label = self.attributes[index]
        #category_label = self.categories[index]

        if self.transform is not None:
            image = self.transform(image)

        return image, attribute_label
4

This line of code should also throw this error if you run the code in the CPU, so that’s a bit strange.
Anyway, how did you define self.transform?

5

My transform:

transform = transforms.Compose([
    transforms.ToPILImage(),
    transforms.Resize(size=(224, 224)),
    transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
6

Could you print the shape of the image before passing it to the transformation.
I’m not sure, if OpenCV creates pseudo-color channels if you are loading a grayscale image, but if not that could yield this error.
If that’s the case, you could extend your tensor in that dimension to create 3 identical color channels.

7

Few examples:

(432, 512, 3)
(346, 212, 3)
(600, 596, 3)
(298, 454, 3)
(472, 348, 3)
(516, 380, 3)
(458, 362, 3)
(530, 598, 3)
(478, 384, 3)

8

@ptrblck Here is all errors

08
08701×308 14.5 KB

9

This error was usually thrown, if you’ve passed a grayscale image to the normalization with three values.
Could you add a check to see, if all images contain three channels?

10

I was checked, and I don’t have images with single channels…

11

Let me clarify, if the img has three channels, you should have three number for mean, just for example, img is RGB, mean is [0.5, 0.5, 0.5], the normalize result is R * 0.5, G * 0.5, B * 0.5. If img is gray type that only one channel, so mean should be [0.5], the normalize result is R * 0.5

1 Like
12

I’m working on Ubuntu 16.04 version and using torch version 1.3.1
It’s that MNIST data set consists of grey images.

transform = transforms.Compose([ transforms.ToTensor(), transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5)), ])

can be changed to

transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))])