XJDKC commented on issue #651: Add new example APIs URL: https://github.com/apache/singa/pull/651#issuecomment-609740189 > > can the original model run (not using the Module API)? > > Yes, I have turned the graph off (GRAPH=FALSE) and running, seems is okay I have just finished 2 rpochs, I will wait for more result. I think the different of resnet and xceptionnet is that it has multiple branch > > ``` > (singa) dcsysh@panda7:~/singa/examples/autograd$ python3 train.py xceptionnet ci > > Starting Epoch 0: > Training loss = 11198.645508, training accuracy = 0.214420 > Evaluation accuracy = 0.309000, Elapsed Time = 606.547117s > Starting Epoch 1: > Training loss = 6354.611328, training accuracy = 0.381020 > Evaluation accuracy = 0.457300, Elapsed Time = 612.817129s > Starting Epoch 2: > > ``` I know the problem. It's because some tensors were deallocated during the evaluation phase. I will fix it.
---------------------------------------------------------------- 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: [email protected] With regards, Apache Git Services
