Simon Donike
Simon Donike
Hello, I opened an issue regarding a similar problem trying to train an autoencoder from scratch: #270. My way of training an AE is descrided there (works to train the...
@forever208 thanks, I do. For my application I had to retrain though since I'm using more channels.
@pandas351 That's because youre calling the .forward() function. Check out the other functions like make_convolutional_sample etc
That seems like a tqdm issue, what's supposed to be written in that spot where you see the error is the iterations per second.