juju-w / image-denoise-using-wasserstein-gan Goto Github PK

Using progressbar==2.5 raised the following error:

TypeError: 'NoneType' object is not an iterator

Using progressbar2 gave me another error.

I ended up using tqdm==4.64.1 instead. It is available in PyPI and GitHub.

When working with multichannel images the channel_axis parameter needs to be set to -1 (or 2). Without it, the following line of code:

Raises a the following error when invoking structural_similarity from scikit-image==0.21.0:

ValueError: win_size exceeds image extent. Either ensure that your images are at least 7x7; or pass win_size explicitly in the function call, with an odd value less than or equal to the smaller side of your images. If your images are multichannel (with color channels), set channel_axis to the axis number corresponding to the channels.

Suggested change:

# ssim calculation
ssim_values = [
    structural_similarity(
        imgraw[n], 
        fake_img[n], 
        multichannel=True, 
        data_range=1, 
        channel_axis=-1
    ) 
    for n in range(n_val)
]
ssim = np.mean(np.array(ssim_values))

My dependency versions are:

tensorflow<2.11
wget==3.2
tqdm==4.64.1
opencv-python-headless==4.8.0.76
opencv-python==4.8.0.76
scikit-image==0.21.0
numpy==1.25.2
pandas==2.0.3

This issue can occurs here:

It can be resolved by:

1. Specifying axis=0 to expand the dimensions of val_image and make it 4-dimensional.
2. Returning to 3-dimensions by using np.squeeze to squeeze out the extra dimension.

Suggested change:

fake_img = [np.squeeze(generator(tf.expand_dims(tf.convert_to_tensor(val_image), axis=0)).numpy()) for val_image in batch_val_noise]

My dependency versions are:

tensorflow<2.11
wget==3.2
tqdm==4.64.1
opencv-python-headless==4.8.0.76
opencv-python==4.8.0.76
scikit-image==0.21.0
numpy==1.25.2
pandas==2.0.3

The call to range(5) produces a sequence of numbers from 0 to 4. This results in a division by zero on the following line:

Maybe what was intended was range(1, 5) for a sequence from 1 to 4 or range(1, 6) for a sequence from 1 to 5?

My dependency versions are:

tensorflow<2.11
wget==3.2
tqdm==4.64.1
opencv-python-headless==4.8.0.76
opencv-python==4.8.0.76
scikit-image==0.21.0
numpy==1.25.2
pandas==2.0.3