Revert "Fix bugs in conv functions"

openai / iaf

Code for reproducing key results in the paper "Improving Variational Inference with Inverse Autoregressive Flow"

https://arxiv.org/abs/1606.04934

MIT License

517 stars 130 forks source link

Revert "Fix bugs in conv functions" #12

Closed dpkingma closed 6 years ago

dpkingma commented 6 years ago

Reverts openai/iaf#8

Apparently causes NaN's: https://github.com/openai/iaf/issues/11

ak-kat commented 6 years ago

I am executing tf_train.py (num_gpus=1). In forward function for two for loops it is running fine for i=0,j=0;i=0,j=1; but continuously it is taking huge memory. For i=1,j=0 of for loop in forward function it calls sub_layer.up which in turn calls conv2d, it got almost very slow and memory space is increasing at execution of line no. 49 (layer.py) of con2d function. Anyone please help me to resolve this increased memory issue.