I couldn't find any usage of img_hr in SRGAN model. Is it unnecessary to add img_hr as input of combined model?

My suggestions for line 95 and line 229 of srgan.py:
line-95: self.combined = Model(img_lr, [validity, fake_features])
line-229: g_loss = self.combined.train_on_batch(imgs_lr, [valid, image_features])

By default, I get 8x8 grids of images for each epoch completed, both very similar to one another.

Is there any way to continue to generate more images at the final epoch? Say I wanted to create a thousand images? Any ideas on the best way to do this?

I would be happy to work on this/ write some documentation, would just like a point in the right direction.

This library is extraordinar

I understand that these two python files show two different methods to construct a model. The original n_epoch is 500 which works perfect for both python files. But if I change n_epoch to 20, only tutorial_mnist_mlp_static.py can achieve a high test accuracy (~0.97). The other file tutorial_mnist_mlp_static_2.py only get 0.47.

The models built from these two files looks the same for me (the s

I tried some RNN regression learning based on the code in the "PyTorch-Tutorial/tutorial-contents/403_RNN_regressor.py" file, which did not work for me at all.

According to an accepted answer on stack-overflow (https://stackoverflow.com/questions/52857213/recurrent-network-rnn-wont-learn-a-very-simple-function-plots-shown-in-the-q?noredirect=1#comment92916825_52857213), it turns out that the li

According to scipy, scipy.misc.toimage()

toimage is deprecated! toimage is deprecated in SciPy 1.0.0, and will be removed in 1.2.0. Use Pillow’s Image.fromarray directly instead.

which is used on line 46 of utils/visualizer.py is now a deprecated function under the newest scipy version. As a result this co

Hi, thanks for the great code!

I wonder do you have plans to support resuming from checkpoints for classification? As we all know, in terms of training ImageNet, the training process is really long and it can be interrupted somehow, but I haven't notice any code related to "resume" in scripts/classification/train_imagenet.py.

Maybe @hetong007 ? Thanks in advance.

Is there any place I can read about how to produce high-quality results? The pictures from the README look very well produced whereas the result I get from the collab demo is not as good. Is there any documentation about the parameters for that Trump-Cage example?
Thank you so much

Traceback (most recent call last):
File "train.py", line 45, in
train_display_images_b = torch.stack([train_loader_b.dataset[i] for i in range(display_size)]).cuda()
File "train.py", line 45, in
train_display_images_b = torch.stack([train_loader_b.dataset[i] for i in range(display_size)]).cuda()
File "/content/MUNIT/data.py", line 119, in getitem
pat

This project is fantastic.

If anyone would be interested in trying this project out on Kubeflow let me know (kubeflow.slack.com) I'd be happy to support that by providing a Kubeflow cluster.

It would be great to understand how well the following works

Try to run the sample notebook on Kubeflow

• Deploy Kubeflow
• Navigate to JupyterHub
• Launch Jupyter