glow-pytorch

glow-pytorch copied to clipboard

How to learn y condition?

4

Thanks for your great implementation. The learned prior are added in every block in your implementation, which produces more promising results, however, the original implementation adds the prior only at...

ueoo

loss NAN

1

In my experiment, when the data set is small, the experiment can run normally. When the number of data sets is large, the loss value always changes to Nan when...

ledashuai

Loss value

2

I have a question about the loss value. The loss value is the negative log likelihood (bits per dim) in paper, isn't it? When I trained the model, the loss...

viettmab

a question about the sigmoid function in the affine coupling layer

2

Hi, thank you for your amazing work. As you mentioned, using the sigmoid function in the affine coupling layer is benefical to the training. I was wondering why you shifted...

ShipengFu

mbaddar1

hi: I donot know how to prepair the dataset , for example, if I want to train a model on CeleBA HQ to edit eye / eyebrow /beard / nose...

alexliyang

mbaddar1

Change image_size to 256

7

Hi, I want to change image_size to 256. Do I need to change the value of n_bits and n_bins? Another question I want to ask is the meaning of the...

viettmab

File Checkpoint

1

Hi, Firstly, thank you for your easily understandable code. I want to use z_space for manipulation for my studying, I tried to train your code, but it takes me about...

doctorares

Traceback (most recent call last): File "D:/Productivity/AchievedAlgorithm/Glow-pytorch-master/train.py", line 192, in train(args, model, optimizer) File "D:/Productivity/AchievedAlgorithm/Glow-pytorch-master/train.py", line 139, in train image + torch.rand_like(image) / n_bins File "D:\Anaconda\envs\torch_cpu\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl...

oubahe