image-denoise-using-wasserstein-gan's People
Forkers
georgeslabrecheimage-denoise-using-wasserstein-gan's Issues
couldn't get progressbar nor progressbar2 to work: recommend using tqdm instead
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.
the channel_axis parameter needs to be set when invoking the structural_similarity function
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
fake_img generator expects a 4-dim input but is given a 3-dim input
This issue can occurs here:
It can be resolved by:
- Specifying
axis=0
to expand the dimensions ofval_image
and make it 4-dimensional. - 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
divide by zero error prior to saving weights
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
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. ๐๐๐
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.