Guan Wang comments

Results 6 comments of


                                            Guan Wang

ValueError: Shapes are not compatible when training transition model after autoencoder trained

can someone take a look? thanks!

ValueError: Shapes are not compatible when training transition model after autoencoder trained

@EderSantana Thanks a lot for the response. I've tried keras 1.0.6 and 1.0.8, tensorflow 0.9, and 0.10. All gave the same error. I still got the error after changing transition.py...

ValueError: Shapes are not compatible when training transition model after autoencoder trained

I just tried 'cpu', 'gpu', 'mem' for consume_less parameter. No luck :( My server.py output is like this guan.wang@Z440SJ-243:~/ml/comma/research$ ./server.py --time 60 --batch 64 INFO:**main**:server started INFO:dask_generator:Loading 9 hdf5 buckets....

ValueError: Shapes are not compatible when training transition model after autoencoder trained

I also solved it by completely removing keras and install the 1.0.6 version. Previously I tried virtualenv for 1.0.6 and it didn't work. Maybe my package system messed it up....

ValueError: Shapes are not compatible when training transition model after autoencoder trained

@jamesjackson Yes, source-based without Anaconda +1 @andrewraharjo Yes, I completely removed keras and reinstalled the right version.

Add command line paremter "-seed" to trainer

lgtm. Tried 2 runs with the same seed setting. The model files are almost identical. However, there are some difference in trailing digits. For example 53545c53545 "Sum": 32650.957789183747 "Sum": 32650.95778918369...