Yeonwoo Jeong

Results 4 issues of Yeonwoo Jeong

Code in 'README.md' works well in 'multi_dsprites_colored_on_colored.tfrecords'. However, it doesn't work well in 'multi_dsprites_binarized.tfrecords' and 'multi_dsprites_colored_on_grayscale.tfrecords'. In the code ```python from multi_object_datasets import multi_dsprites import tensorflow as tf tf_records_path =...

https://github.com/vithursant/VAE-Gumbel-Softmax/blob/master/vae_gumbel_softmax.py#L55 You use the logits, however we have to use log(logits) to perform gumbel max trick as stated in [https://timvieira.github.io/blog/post/2014/07/31/gumbel-max-trick/](https://timvieira.github.io/blog/post/2014/07/31/gumbel-max-trick/)

Hey, I got success on compiling with this command as commented in [https://github.com/Russell91/TensorBox/issues/60](https://github.com/Russell91/TensorBox/issues/60). ``` g++ -std=c++11 -D_GLIBCXX_USE_CXX11_ABI=0 -shared hungarian.cc -o hungarian.so -fPIC -I $TF_INC ``` But, the same error comes...

Please refer to the CIFAR-10, Resnet-50 architecture in the table 2 of paper. When volume budget is 12.5 %, number of parameter is 2.8% and FLOPs is 5.1% in Table...