Training Pipeline for Vision Transformers
#1
by MaxBolD - opened
Hi @KennethTM
I'm working on a similar task with Vision Transformers but I'm struggling to set up a training pipeline.
Would you mind sharing yours? It would help me a lot to get started! Thanks in advance!
Hi
I based my training on these notebooks:
https://github.com/NielsRogge/Transformers-Tutorials/blob/master/Pix2Struct/Fine_tune_Pix2Struct_on_key_value_pair_dataset_(PyTorch_Lightning).ipynb
https://github.com/huggingface/notebooks/blob/main/examples/image_captioning_pix2struct.ipynb
Hope that helps.
Kenneth
MaxBolD changed discussion status to closed