-
Notifications
You must be signed in to change notification settings - Fork 2.4k
How Do I fine-tune a custom DETR model as we fine-tune Hugging face transformer #109
Comments
Hi, There is a lot of useful information about finetuning in #9, so let's keep the discussion there. For your particular question, you should also add a Lines 83 to 88 in 10a2c75
Our training loop looks like the following Lines 32 to 33 in 10a2c75
IMO, the easiest way to get started with training is to clone the repo and modify the functions you need, see https://github.com/facebookresearch/detr#training for information. I hope this helps. I believe I've answered your question, and as such I'm closing this issue, but let us know if you have further questions |
@fmassa I was able to import HungarianMatcher from detr.models.matcher and it was working fine , but now it says module util not found after the last update I guess , I wrote a whole pipeline and somehow now it doesn't work , I would really appreciate some help |
@tanulsingh there should be no breaking change in the repo since its release. One thing to keep in mind is that you need to run the code from the repo root, as DETR is not packaged as a library |
@fmassa Thanks It helped I was able to write a complete pipeline that can be used to train DETR on any custom dataset just by changing the dataloader |
I am doing something like
My question is the output of the model is class and bboxes and no loss , how do I calculate the loss and backpropagate it so that I can fine tune the model
The text was updated successfully, but these errors were encountered: