tao zhang

[Download ChestX14-ray dataset] [Bit download link](http://academictorrents.com/details/557481faacd824c83fbf57dcf7b6da9383b3235a) The recommended Bit Downloader: [Bitcomet](https://www.bitcomet.com/en) Thunder is not recommended

I have meet the same problem like you when i update tensorflow2.0.0 -> 2.3.0 **Environment:** RTX1080Ti + cuda10.0 + cudnn7.6.0 + ubuntu 16.04 + tensorflow-gpu 2.3.0 **The code is very...

THANKs for your replying all these fixes focus on previous version of tensorflow. Everything goes will in tensorflow2.0.0 in my environment, but went wrong in tensorflow2.3.0.... maybe something in newest...

everything goes will when i update cuda to 10.1

Author has released the pretrained model in Readme.md [Result] |steps| |[54000](https://drive.google.com/open?id=1DSg3F5GpouEvU9n7YSPdUKH1CSmkdwSw)|

**maybe it is not the problems of this code.** i also run this code in my only one GPU(GTX1080). the batch size for training is 64 one iteration took about...

by the way, i set the value **args.single_batch==True** in my running code. maybe it is the reason why faster

@soumith i update the latest version of pytorch  Question1:it worked well in jupyter just before i update pytorch . and then it occurs "**kernel died restarting**" in jupyter also.........

@soumith thank you for your answering Later,I update all the packages in anaconda `conda update --all` delightedly Question1 and Question3 have been solved but the error in the spyder also...

THANKS for your replying and your promising work. We are going to follow your work and want to reproduce your work. We have done that on mnist and cifar dataset....