Sander

train class loss is always around 0.999?

1

emm, I have question about train cls_loss ,when I train on my own data ,the class loss can't down in 0.999,I check my data, and even change the learnning rate...

lmdb stuck/hang when use multiprocessing process(pytorch dataloder).

2

### Affected Operating Systems * Linux ### Affected py-lmdb Version lmdb=1.4.1 ### py-lmdb Installation Method pip install lmdb ### Using bundled or distribution-provided LMDB library? Bundled ### Distribution name and...

can anyone encountering this problem ？ detail description can see in : https://github.com/jnwatson/py-lmdb/issues/350