Value error in random crop transform

I have modified the custom RandomCrop transform given in this tutorial - https://pytorch.org/tutorials/beginner/data_loading_tutorial.html as follows:

class RandomCrop(object):
    """Crop randomly the image in a sample.

    Args:
        output_size (tuple or int): Desired output size. If int, square crop
            is made.
    """

    def __init__(self, output_size):
        assert isinstance(output_size, (int, tuple))
        if isinstance(output_size, int):
            self.output_size = (output_size, output_size)
        else:
            assert len(output_size) == 2
            self.output_size = output_size

    def __call__(self, sample):
        image,image_id,label_id = sample['image'], sample['image_id'], sample['label_id']

        h, w = image.shape[:2]
        new_h, new_w = self.output_size

        top = np.random.randint(0, h - new_h)
        left = np.random.randint(0, w - new_w)

        image = image[top: top + new_h,
                      left: left + new_w]


        return {'image': image, 'image_id':image_id,'label_id':label_id}

When I run this, I get the following Value error after a few iterations:

ValueError: Traceback (most recent call last):
  File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 55, in _worker_loop
    samples = collate_fn([dataset[i] for i in batch_indices])
  File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 55, in <listcomp>
    samples = collate_fn([dataset[i] for i in batch_indices])
  File "<ipython-input-20-17b45e03499d>", line 39, in __getitem__
    sample = self.transform(sample)
  File "/usr/local/lib/python3.6/dist-packages/torchvision/transforms/transforms.py", line 42, in __call__
    img = t(img)
  File "<ipython-input-23-f3687176a1f2>", line 23, in __call__
    top = np.random.randint(0, h - new_h)
  File "mtrand.pyx", line 993, in mtrand.RandomState.randint
ValueError: low >= hig

Can anyone help me in identifying the issue and how I go about resolving it ?

The error message says that low >= high, given that in your function call, low=0 and high=h-new_h, then the problem is that the new_h is larger that h, Meaning that the size of the random crop you want is actually bigger than the original image.

Thanks @albanD for pointing that. I rescaled my images and then took a random crop.