Farzad Abdolhosseini

Results 4 comments of Farzad Abdolhosseini

No, I didn't have many clues to go on really.

Yes, if you disable `learn_augmentation`, you should also change both the loss to `cross_entropy` and `stats.checkpoint_metric` to `top1` (instead of `top1.logits`).

Original question: it seems to me like you’re running out of memory (RAM) and are getting OOM killed. I’d check the following a) RAM size (free) b) the dataset implementation...

Hi, I'm really confused about what the question is here. Please say: 1) what you did (e.g. a partial code containing what is registered) 2) what you expected 3) what...