search

lovelyqian / AMeFu-Net

Repository for the paper "Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition"
MIT License
45 stars 3 forks source link

The training of submodels #1

Open Nanjo-Naoto opened 3 years ago

Nanjo-Naoto commented 3 years ago

I want to know when will you release the model and the submodels rgb and depth? Also, you mentioned we can train the submodels by ourselves through the previous work "emboded few-shot learning". But how can we get both pre_model_rgb and pre_model_depth?

lovelyqian commented 3 years ago

I want to know when will you release the model and the submodels rgb and depth? Also, you mentioned we can train the submodels by ourselves through the previous work "emboded few-shot learning". But how can we get both pre_model_rgb and pre_model_depth?

Hi, we have released the checkpoints of all the full models and submodels.

As for the training method of the rgb and depth submodel, they are obtained respectively. That is, the RGB input is used to train the rgb submodel, and the depth input is used to train the depth submodel.