examples
examples copied to clipboard
pytorch
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
ImageFolder doc should clarify: 1. order that images returned in (it looks like it is alphabetical (which is what I want :) ), https://github.com/pytorch/vision/blob/d6c7900d06c3388bf814cecbe90f91a9afecbefb/torchvision/datasets/folder.py#L44-L45 ) 2. that images from all...
In super_resolve.py, line 35, I think 'np.uint8(out_img_y[0])' should be 'np.uint8(out_img_y[0] + 0.5)'. This is because the value after the decimal point is discarded when casting. Would not rounding be better...
(1) if RANK or WORLD_SIZE is set in env variable, they will not be picked up (2) multiprocessing-distributed won't work with env variable: WORLD_SIZE and RANK being set since the...
After run about 15 epoch, the generator seems to collapse to a parameter setting where it always emits the same point. Did anyone run the script successfully?
I notice that there is no total variation loss regularization implemented in the example of `fast_neural_style`. But the paper declared it and their torch version use it. I'm wondering if...
volatile is no more in PyTorch HEAD, which means that you have to use the `no_grad` context manager now. Any examples using volatile need to be ported accordingly. However, we...
The current implementation uses `F.binary_cross_entropy(recon_x, x.view(-1, 784), reduction='sum')` as the reconstruction loss. The image `x` has pixel values in `[0,1]`. This is not the same as Bernoulli log likelihood. The...
Hi there, I used the `torch.utils.tensorboard` to watch the weight/grad when training the DCGAN example on MNIST dataset. In the DCGAN example, we use the normal distribution to initialize both...
I'm trying to run the DCGAN on Imagenet 32x32, but am running into problems. If I just change the ```--imageSize``` to 32, then the convolutional layers break and I get...
when rendering, its as if the weights are dropped, or re-randomized. without rendering everything works fine. same goes for saving. It seems lengthy operations don't allow raining to continue, and...
