Jarrel Seah

Results 17 comments of Jarrel Seah

Is the CNN version code trained well?

Hi Thanks for kind comments. The model I have trains correctly but slowly. Did you alter any of the parameters including the batch size? Also the quality of the generated...

Is the CNN version code trained well?

Actually you are on the right path. I have just checked the code and it uses an older incorrect version of the Spectral Normalization by Gouk. Specifically it underestimates the...

Is the CNN version code trained well?

Weight_orig is the original weight and the actual parameter that is undergoes gradient descent The spectral norm replaces the weight parameter with a torch tensor which is recomputed everytime gradient...

Is the CNN version code trained well?

I did not use data parallel. I'm not sure how the actnorm would behave with data parallel, you may have to run a test batch before copying the model to...

Is the CNN version code trained well?

Hi Zenan, Saving and loading is not implemented yet. Jarrel On Mon., 20 May 2019, 07:15 Zenan Ling, wrote: > @jarrelscy Problems still exit without > data parallel. Here is...

Is the CNN version code trained well?

Interesting maybe we should be recalculating sigma during test time then On Tue., 21 May 2019, 03:32 Zenan Ling, wrote: > @jarrelscy The test loss and accuracy seem > to...

Is the CNN version code trained well?

I have yet to train the classification model. On Thu., 30 May 2019, 06:21 Zenan Ling, wrote: > my classification net doesn’t work on single gpu the loss explodes >...