hanban

Hi, I wonder if there's repo for paper The Autoencoding Variational Autoencoder nips2020. 😄

Hi, what a great and insightful works! Thanks for offering codes! I wonder if you can offer the config of CIFAR-10 for reproducing the FID results (Table 1).

Memory leak with tfb.Glow ?

9

Info:` tf-nightly-gpu` and `tfp-nightly` , code tested on single tesla v100, ubuntu, cuda11.0, cudnn8 RAM grows linearly when training a `tfb.Glow` based `tfd.TransformedDistribution`. It takes 16G when it starts training...

Hi, if I use your service in my research paper, how to cite it properly? https://azure.microsoft.com/zh-cn/services/cognitive-services/face/

Cannot load PNG because libpng support was not compiled.

3

Apple M1 Pro. Follow the installation instructions, and try to run examples `./heif-enc` to convert png to heif and get error `Cannot load PNG because libpng support was not compiled.`...

Hi, Thanks for your works!! I have a question about this line of code: https://github.com/kamalkraj/Vision-Transformer/blob/1ee5e628f18e84aaf28b6a4675a00342b4f7d5f7/model.py#L146 Why wrapping call to tf.function?

Batch size 1 and value of Flattening Criterion

1

Great work! I have few questions, can you explain a bit for me please? 1. Why batch size set to 1? 2. I try implement it in pytorch and found...

Raise NaN when using model to fit `celebA` dataset

12

The initial loss / log_prob is very big like 1e24. I tried `CUB200` as well, but `CUB200` has around `40000` initial loss and training goes well. When I try to...

python test.py extremely slow

1

Amazing work! I'm trying to inferece some images, and found it extremely slow to start. Model loading is so slow, any solution?