search

google-research / big_transfer

Official repository for the "Big Transfer (BiT): General Visual Representation Learning" paper.
https://arxiv.org/abs/1912.11370
Apache License 2.0
1.5k stars 175 forks source link

Pre-trained Resnet v1 model #21

Open dulucas opened 4 years ago

dulucas commented 4 years ago

Hi, Thanks for your great work! I noticed that all the released pre-trained resnet models belong to resnet v2 series, It would be really helpful if you would release pre-trained resnet v1 models as well, as the baseline for most of the downstream tasks(detection, segmentation) use resnet v1 models as their encoders. Thank you.

lucasb-eyer commented 4 years ago

This is a very good point! We have actually trained some ResNet v1 models on ImageNet-21k. They perform very similarly. Not sure if we will/can release them anytime soon though.