search

icoz69 / DeepEMD

Code for paper "DeepEMD: Few-Shot Image Classification with Differentiable Earth Mover's Distance and Structured Classifiers", CVPR2020
MIT License
577 stars 82 forks source link

Why repeat data_shot #51

Closed zfbz closed 1 year ago

zfbz commented 1 year ago

Hi, I'm a beginner. I want to know why to repeat data_shot during meta-training. train_meta.py, line.158 logits = model((data_shot.unsqueeze(0).repeat(num_gpu, 1, 1, 1, 1), data_query))

icoz69 commented 1 year ago

hi, this is for multi-gpu computing.

zfbz commented 1 year ago

Why does data_query not need to repeat(only data_shot)? Are there any related multi-gpu programming references? I haven't used this before. Thanks.