Skip to content

Conversation

@sjyttkl
Copy link
Owner

@sjyttkl sjyttkl commented Apr 5, 2020

learning

arisliang and others added 17 commits June 2, 2018 23:14
Fixed typos.
Improves sharing code without affecting readability
The sample.py cannot be used to generate caption for gray image.In the data_loader.py, all of the images have been converted to 'RGB' format. But when generating captions using sample.py for single image, this conversion is missed. So for gray image, it will have such RuntimeError: Given groups=1, weight of size [64, 3, 7, 7], expected input[1, 1, 224, 224] to have 3 channels, but got 1 channels instead.
When we load an image for the sample, we have to make sure that the image has three color channel (RGB) because it might be grayscale. So we should convert it for sampling.
Remove dollar-sign prompt from code blocks
minor refactoring and fix
Let sample.py can generate caption for gray image.
Fixed Test error when encoder(image).
fix #187 Typos in language model and generative_adversarial_network
@sjyttkl sjyttkl merged commit 48ebfa3 into sjyttkl:master Apr 5, 2020
@sjyttkl
Copy link
Owner Author

sjyttkl commented Apr 5, 2020

learning new data

@sjyttkl
Copy link
Owner Author

sjyttkl commented Apr 5, 2020

very good

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

9 participants