Skip to content

Missing some pretrained model weights #107

Discussion options

You must be logged in to vote

Hi @rezafuru

For input compression baselines, you won't need to manually download checkpoints, but just use pretrained: True in yaml configs so that you can automatically download them via compressai package like this.

The ckpt: in our yaml configs for input compression are not used actually unless you have your own trained model weights.
Same for the ResNet-50 model weights, it is from torchvision and you can just use pretrained: True like this.

Replies: 1 comment 1 reply

Comment options

You must be logged in to vote
1 reply
@rezafuru
Comment options

Answer selected by rezafuru
# for free to join this conversation on GitHub. Already have an account? # to comment
Category
Q&A
Labels
None yet
2 participants