search

icoz69 / CEC-CVPR2021

Pytorch code for CVPR2021 paper "Few-Shot Incremental Learning with Continually Evolved Classifiers"
MIT License
152 stars 33 forks source link

Is the code missing the pre-training part? #14

Closed chester-w-xie closed 2 years ago

chester-w-xie commented 2 years ago

Hi, Thank you for your wonderful work! You describe in your article that the first stage of the method is to use the training data from session 0 to pre-train the backbone so that it has some feature extraction capability. However, in your code, the pre-trained model you provided on Google Drive is loaded directly by default. I tried to run the code without loading the pre-trained model and got poor results. So, could you possibly share how you are doing in the first stage of pre-training? Or, it would be great if you could add the code for the pre-training stage, thank you very much!

Nan-S commented 2 years ago

Model/base is the pre-training part. You can use the 'Pretrain scripts' provided in README to run the first stage of pre-training. Same answer for #15 I will proceed to close both of them.