Closed davidingram123 closed 4 hours ago
The configuration file I used is bert-12l-512d_LRW_96_bf16_rrc_WB, with some minor modifications, no more than two.
@davidingram123
Data augmentation strategy is crucial as stated by Ma et al 2022, so please, stick with our implementations for replication purpose.
val/accuracy_top1 plateau around 95.1% ~ 95.2% and train/accuracy_top1 oscillates around 80%. For more details, please refer to our attached wandb training log of word-level VSR above.
Thank you for your help.
Your welcome! Please file another issue if you need any further help! @davidingram123
Hi, I read your paper and found it very interesting. However, I encountered some issues with the code, and I am unable to replicate your results. Could you share the "train/accuracy_top1" and "val/accuracy_top1" graphs over 200 epochs (or more) with me? This would give me a reference, as I noticed that when running the code, the "val/accuracy_top1" graph tends to plateau between 40 and 50 epochs.(It might be that I missed a data augmentation strategy, but it shouldn't cause such a significant drop in accuracy, right?)