torch-two-sample

torch-two-sample copied to clipboard

Hi, Thanks for maintaining this helpful repo. I would like to add support for median heuristic for kernel bandwidth of MMD Test. Choosing a good kernel bandwidth parameter (sqrt(1/alpha) in...

lisun-ai

RuntimeErrors with "torch_two_sample.statistics_diff.SmoothKNNStatistic"

2

Hello ! Thank you very much for sharing these functions to the PyTorch community, I am successfully using the "torch_two_sample.statistics_diff.MMDStatistic" both at training/backprop and evaluation, running on GPU. I am...

adrienchaton

ModuleNotFoundError: No module named 'torch_two_sample.permutation_test'

3

I receive this error while trying to do this: from torch_two_sample import SmoothFRStatistic There was no error in the installation. Inside the torch_to_sample folder, I noticed that there is a...

AndreydeAguiarSalvi

Hi, I just ran `python setup.py test` and got mostly failures. It's not clear which dependencies I am missing, or whether that's the only problem 1. How can I determine...

rmurphy2718

Hi, I just ran `python setup.py test` and got numerous IndexErrors like > IndexError: invalid index of a 0-dim tensor. Use tensor.item() to convert a 0-dim tensor to a Python...

rmurphy2718

runtimeError in pytorch 0.4.1

5

pytorch 0.4.1 RuntimeError Traceback (most recent call last) in () 37 loss = loss_fn(Variable(batch), generator(noise), alphas=alphas) 38 print(" loss is ", batch) ---> 39 loss.backward() 40 print(" backward") 41 optimizer.step()...

monadyn

New kernel functions needed!

1

When computing MMD, it is possible to used other kernels besides RBF.

noeagles

Thanks for this amazing library! One quick update required for the code though: In inference_trees.py, line 121, ```Z, _ = torch.gesv(A, L * P.expand_as(L))``` is used to solve a system...

nkamath5