Xinpeng Wang

Hi, I want to train the model on my own dataset. How should I process the dataset? Thanks!

Can you please share complete scripts for processing datasets and training? Because there are a lot of parameters in commands in https://github.com/Sleepychord/cogdata. I'm not very clear about that. And I...

same here

I tried the following steps: 1. conda env create -f environment.yaml (ignore errors) 2. conda activate ldm 3. Create a new requirements.txt and copy the packages needed to pip install...

same problem

Not yet. Maybe the link is invalid?

And another question is when I run sh train_caption_stage1.sh, there are some errors occur: Traceback (most recent call last): File "/data33/private/xinpeng/codebase/OFA/trainer.py", line 511, in load_checkpoint self.model.load_state_dict( File "/data33/private/xinpeng/codebase/OFA/fairseq/fairseq/models/fairseq_model.py", line 125,...

I also try to run sh train_caption_stage1_base.sh, but I also met some errors: Traceback (most recent call last): File "/data33/private/xinpeng/codebase/OFA/run_scripts/caption/../../train.py", line 528, in cli_main() File "/data33/private/xinpeng/codebase/OFA/run_scripts/caption/../../train.py", line 521, in cl...

Hello, I'm reading this source now. Do you know how to build "train_sc.txt", if I just have the "train_process.txt"? Thank you!