search

foolyc / Meta-SGD

Meta-SGD experiment on Omniglot classification compared with MAML
79 stars 10 forks source link

I got an error #3

Open mbasirat opened 6 years ago

mbasirat commented 6 years ago

I run code for :python main.py --datasource=omniglot --metatrain_iterations=40000 --meta_batch_size=32 --update_batch_size=1 --update_lr=0.4 --num_updates=1 --logdir=logs/omniglot5way/

and got this error in data_generator.py : sampled_character_folders = random.sample(folders, self.num_classes) File "/usr/lib/python2.7/random.py", line 321, in sample raise ValueError("sample larger than population") would you please help me?

Bear-kai commented 6 years ago

You may check your data_folder in data_generator.

cpzys2018 commented 4 years ago

You may check your data_folder in data_generator.

After see the code about this , i can no understand if this code is the same as MAML ? i can no find different ? glad to you reply