vq-vae-2-pytorch
vq-vae-2-pytorch copied to clipboard
Unable to get good results
I was training the model with the default parameters set in the code over a small dataset (around 5k images) but cannot obtain any good results. This is the generated output after sampling :
Is this because the hyper-parameters are not set properly or because the dataset is small? How can I get significant results using this model?
Hey @rosinality, I tried training my model according to your suggestions and was able to complete stage 1 and PixelSNAIL training top hier training for 420 epochs with a batch size of 10. Now when I try to train PixelSNAIL for even batch size 1, I get this error:
I trained the entire model before once where I didn't get any such issue. Let me know what can be done here.
You may need to reduce model sizes, for example, decrease --n_res_block.
@rosinality Thanks, it worked!