Using custom loss with VisionClassifierTrainer

[guneetsk99]

I wanted to use a custom loss function with VIT how should I proceed since in the VisionClassifierTrainer there is no use of loss

[qanastek]

Hi,

Since the HugsVision VisionClassifierTrainer is based on the HuggingFace transformers library and especially on their Trainer, we cannot tweak the loss function.

[guneetsk99]

Thanks @qanastek for the prompt response and its really an amazing library
If possible can you suggest how I can use your models/ directory since there I can change the crossentropy loss to for eg KLDivLoss for testing

[qanastek]

HugsVision isn't really suited for reasearch. But you can directly rewrite the Transformers class ViTForImageClassification for the single_label_classification task.

In my opinion, it's the simplest way to do. Clone the Transformers repository, install it locally using pip install --editable . and modify the loss in the class.