maml
maml copied to clipboard
cbfinn
Code for "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"
Hey I have read the MAML paper a few times already, and i have ran the code in this repo over miniImageNet (classification task), I was trying to get the...
Hello, I use reinforcement learning. During the meta training, I will test the model parameters trained every time in the training task, and get the following success rate. In the...
I am executing the omniglot test with the following command: ``` python main.py --datasource=omniglot --metatrain_iterations=60000 --meta_batch_size=32 --update_batch_size=1 --update_lr=0.4 --num_updates=1 --logdir=logs/omniglot5way/ ``` However, I am getting the error: ``` Done initializing,...
Hi, Each time I run the main.py, it takes a long time to generate filename. Could you please fix it?
Hello, I saw this paper and code recently. There are many puzzles in it. I hope someone can give me some advice. The first question is:In data_ generator.py, why 20000...
Hi I didn't find in the paper details a scheduler being used. Is there a reason despite it being standard in DL?
Hello Great work thank you very much!! I am running the testing and I always get the same results after setting ```NUM_TEST_POINTS = 600``` This is a sample of the...
I am using a virtual environment with following packets: Package Version -------------------- --------- absl-py 0.8.1 astor 0.8.0 cachetools 3.1.1 certifi 2019.9.11 chardet 3.0.4 gast 0.2.2 google-auth 1.7.0 google-auth-oauthlib 0.4.1 google-pasta...
Thanks for your works! It is really great idea. There are one thing I want to ask. In paper, you mentioned the first-order approximation of MAML. I have seen details...
