chrishkchris commented on issue #572: hotfix: cpp softmax not impl URL: https://github.com/apache/singa/pull/572#issuecomment-573575646 @dcslin I tested the examples/autograd/mlp.py (multilayer perception) and there is such error: ``` ubuntu@ip-172-31-26-47:~/singa/examples/autograd$ python3 mlp.py train_data_shape: (400, 2) train_label_shape: (400, 2) training loss = 6.682101 WARNING: Logging before InitGoogleLogging() is written to STDERR F0113 09:20:05.180658 12032 tensor_math_cpp.h:357] Check failed: a > 0.f (-nan vs. 0) *** Check failure stack trace: *** Aborted (core dumped) ``` However if I uses softmax_cross_entropy instead of softmax + cross_entropy it will be totally okay, i.e. loss = autograd.softmax_cross_entropy(x, target) The good output will be: ``` ubuntu@ip-172-31-26-47:~/singa/examples/autograd$ python3 mlp.py train_data_shape: (400, 2) train_label_shape: (400, 2) training loss = 0.6908062 training loss = 0.5960194 training loss = 0.57797414 training loss = 0.55334115 training loss = 0.48568404 training loss = 0.38458923 training loss = 0.30776194 training loss = 0.24188559 training loss = 0.18657134 training loss = 0.15864176 training loss = 0.13929243 ```
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
