search

yaoyao-liu / meta-transfer-learning

TensorFlow and PyTorch implementation of "Meta-Transfer Learning for Few-Shot Learning" (CVPR2019)
https://lyy.mpi-inf.mpg.de/mtl/
MIT License
731 stars 147 forks source link

FC-100 data loader #47

Closed YoungBigBird1985 closed 3 years ago

YoungBigBird1985 commented 3 years ago

I have found out the FC-100 data from links of your paper, and Could you please share the data loader and detailed setting for FC-100 experiments?

yaoyao-liu commented 3 years ago

Thanks for your interest in our work. You may directly change the data directories in this file to run the experiments on FC100. If there are any further questions, please let me know.

Best, Yaoyao

YoungBigBird1985 commented 3 years ago

Hi Liu, I want to run your code on CIFAR-FS, which has a 32 32 3 shape of Image, and cannot fit to your code. I try to change the parameter img_size from 84 to 32, but it has error with "Negative dimension size caused by subtracting 5 from 2 for 'pretrain-model/AvgPool' (op: 'AvgPool') with input shapes: [64,2,2,512]". Please help address this issue.

yaoyao-liu commented 3 years ago

I have replyed to you in this issue.

YoungBigBird1985 commented 3 years ago

thanks