search

GeWu-Lab / OGM-GE_CVPR2022

The repo for "Balanced Multimodal Learning via On-the-fly Gradient Modulation", CVPR 2022 (ORAL)
MIT License
236 stars 18 forks source link

What were your hyperparameter? #30

Closed seongq closed 1 year ago

seongq commented 1 year ago

Hello. I want know abot your setting for emotion recognition with CREMA-D. I have tested your code for my research. In your paper, your accuracy applied OGM-GE was 62.2 when dataset is CREMA-D and fusion method is sum. I have tested with the same setting. But, my best acc was 61.

What were your hyperparameters for emotion recognition? (alpha, batchsize and learning rate)

seongq commented 1 year ago

Your parameter can be found on this github page. I did not read closely. thank you