Closed mmaaz60 closed 1 year ago
Hey @mmaaz60,
Thanks for reaching out! Yeah it is indeed an issue from my side, sorry about that, haven't checked carefully enough if everything is possible to run out of the box in the public repo. The problem you are facing is an ablation study we were doing, but didn't include in he paper and the public code. Basically, the idea was to add natural language based augmentations on the instances, but it didn't make a difference. The error you are facing tries to load these augmentation parameters into the language criterion (even though they were not used during the pretraining). To be honest I never resumed a pretraining, checkpoint, only loaded them as weights into the finetuning stage.
What you could do is to remove every weight from the checkpoint which starts with embedding_criterion.projection_model
and resume the training after. Or alternatively you could set the PL load_checkpoint
function to strict=False
. Sadly I don't have the time to test these myself right now, but I will also try to update the checkpoint next week some time.
Hope this helps, but let me know if you still have problems after trying these.
Cheers, David
Thank You @RozDavid,
I have a few more questions/requests.
Thank You
Hey @mmaaz60,
1) I am not sure I have the log files anymore, so sadly I can't help with that
2) During pretraining we don't do any kind of instance augmentation, nor focal loss. That stage is only supervised with the ContrastiveLanguageLoss
and standard geometric/color space augmentations. Clip-only refers to the finetuning stage, which you an start after loading your pretrained model or the one we shared. To do this you have to set --loss_type cross_entropy
and --sample_tail_instances False
, while keeping --use_embedding_loss None
Hi @RozDavid,
Thank you for sharing the great work. I am trying to evaluate the provided pretrained model Res16UNet34D-pretrain and it looks like the keys of the checkpoints provided and the model definition in the repo doesn't match.
Following is the parameter table that I got for your reference. It looks like the pretrained model does not contain weights corresponding to
embedding_criterion
.I am using the script text_representation_train.sh and setting
is_train
to false and setting theresume
to the downloaded checkpoint directory.However, I could successfully reproduce the results of the fine tuning stage Res16UNet34D-finetune.
I would appreciate any help. Thanks