tumble-weed
tumble-weed
I can't figure out how to correct this error: ValueError: the batch size in the image (2) at run time is different than at build time (10) for the ConvOp....
From here: https://stats.stackexchange.com/questions/532170/is-variance-of-individual-points-the-best-strategy-for-chosing-points-in-active In active learning with estimators like Gaussian Processes, we typically look at the test-test covariance matrix, and choose for the next round of observation, the points who...
Hi, In the active learning for regression example, we have used gaussian processes. While the sklearn version seems to keep its length scale and noise parameters static ( maybe i...
**Describe the bug** Some confusion regarding the implementation of virtual batch norm. 1. Referring to another code: https://github.com/dansuh17/segan-pytorch/blob/938b6c837b6f091d0ad1e67fad9db32045a90151/vbnorm.py#L68 , it seems that in the torchgan version the mean and deviation...
Lasagne's `` etc. use the `` keyword, the use of `` in the implementation should be changed to match this
If you run your code with 0 multiplied with all the loss terms, you will still see the image gradually get smoother. in the Denormalize function because the tensor is...
Hello, As i understand , this [line](https://github.com/mxl1990/tsne-pytorch/blob/fb6f61f98e55a564a17aabb1a42ca63bd1a38d8b/tsne_torch.py#L124) deals with imaginary eigenvalues, and creates real eigenvectors in M. according to the torch documentation for [eig](https://pytorch.org/docs/1.8.1/generated/torch.eig.html?highlight=eig#torch.eig), the suggestion is to perform linear...
Hi, thanks for the work! i was interested in certain improvements you had made, and was wondering if you had an insight about why they help. you mention mixed precision...
Hello, thanks for the great work. I have a use case to generate multiple samples for inpainting an area on imagenet and pascal. I had some questions surrounding this. I...
Hi, thanks for the updated port, are there any pretrained weights available that we can load into the model here?