Hyungon_Ryu

nan during training in CycleGAN

2

Did you see NaN in the training? configuration tensorflow : 1.11.0 keras : 2.1.6 GPU : K80 model : CycleGAN dataset : apple2orange I've test multiple models. **aggan**, **wgan**, **dcgan**...

How to generate FF12MC forcefield to OpenMM with information? [paper](https://www.sciencedirect.com/science/article/pii/S2405580815000801) [supplementary material zip](https://ars.els-cdn.com/content/image/1-s2.0-S2405580815000801-mmc2.zip) [mmc2.txt](https://github.com/openmm/openmmforcefields/files/8001004/mmc2.txt) The following is an excerpt from the contents of the parameter forcefield of FF12MC . ```...

Create inference_colab.ipynb

2

add inference notebook on google colab

pyarrow instead of pandas for msgpack

1

pandas.read_msgpack was depreciated since pandas 0.25.0. So stuck in pandas 0.23.0 If we move to pyarrow, its faster than pandas and could avoid dependency issue for other modules. https://pandas.pydata.org/pandas-docs/version/0.25.3/reference/api/pandas.read_msgpack.html https://github.com/pandas-dev/pandas/issues/27722

GPU idle between iteration

2

Awesome work. When I check the GPU utilization during training, I found a lot of GPU idle time between each iteration. Did you see similar behavior? I'm using NFS storage....

OOM error in SSRN

4

I'm reproduce the result. after I finish Text2Mel training, I try to train SSRN. however, hit Out of Memory. https://github.com/Yangyangii/DeepConvolutionalTTS-pytorch/blob/master/train.py#L195 https://github.com/Yangyangii/DeepConvolutionalTTS-pytorch/blob/master/model.py#L75 Do you have any idea? ``` Traceback (most recent...

just avoid error in cache dir.

Dear @xujinfan I want to reproduce ` The search space is 5 in convolutional layers, 25 in fully-connected layers for RCL,DEN and PGN.` plz comment for define target variable for...

errors for charptb_discreteflow_af-scf

4

Thanks for your sharing the awesome work. I'm trying to reproduce your result on PTB dataset and `baseline` and ` charptb_discreteflow_af-af ` works well as below log but I got...

missing library for build system and utils

2

Hi, I want to reproduce your result on jupyter. doublewell model works well. however, [Dimer-LJ-Bath-Sim.ipynb](https://github.com/wehs7661/boltzmann_generators/blob/master/Notebooks/Dimer-LJ-Bath-Sim.ipynb) needs build_system and utils library in in ` In[5] build_system.build_dimer_coords` and ` In [30] utils.apply_hungarian_alg`...