raymond00000

thanks a lot for explanation and reply. I ran the example notebook, it did work! but when i changed to my model, that was some errors. I frozen most of...

many thanks for feedback. acutally, I am learning MAML. I am confused on "second backward". according to here. https://discuss.pytorch.org/t/resolved-implementing-maml-in-pytorch/4053 (1) inner loop: a forward pass on the training example, take...

@rafaelvalle do you mean this setting? attention prior enabled "use_attn_prior": **true**, "attn_prior_threshold": 0.0, "prior_cache_path": "/attention_prior_cache", then disable it "use_attn_prior": **false**, "attn_prior_threshold": 0.0, "prior_cache_path": "/attention_prior_cache", thx for info. actually, i tried...

this work sounds great! I would also like to know how to train with my own data. Thank you so much.