OFA
OFA copied to clipboard
OFA-Sys
Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
Hello, I am trying to test the outputs of OFA (by hand) and I find it a bit difficult to be 100% sure of how to prompt the model to...
I run the fintuning with `nohup bash train_caption_stage1_medium.sh > train_stage1.out &` and in logs I get this: train.py: error: unrecognized arguments: --warmup-ratio=0.06. Is --warmup-ratio is replaced with --warmup-updates? [5_0.06_6000.log](https://github.com/OFA-Sys/OFA/files/9298590/5_0.06_6000.log) [train_stage1.txt](https://github.com/OFA-Sys/OFA/files/9298606/train_stage1.txt)
Add unconstrained training for VQA, which does not need a pre-defined candidate answer set for both finetuning and inference. In this case, evaluation inference mode must be `beamsearch` rather than...
Hi! I am in Singapore. The download speed of models and datasets is less than 100KB/s, from aliyun servers I think. It is too slow for downloading large datasets and...
Dear authors: Thanks for the great work! In VQA validation, If I want the model to predict the most likely next token (i.e. generating a token in the answer) from...
First of all, Thanks for your amazing work.👍. I want to try something on object detection. When will the code for processing coco data and the fine-tuning code for object...
Thank you for your great work. I retrain your model on captioning tasks and the results are very good. To justify the results of my research I'd like to add...
Hi there: Can OFA perform fast retrieval task as dual-stream-like models? Since I want to get embedding for the image or text, and use the saved embedding for fast retrieval...
I'm trying to follow the fine-tuning steps for captioning as listed in readme.md. However my output is just blank and once i hit enter, it exits. Pretraining worked fine, it's...
