How to add Image augmentation part in train_ssd.py file

I am doing object detection project, i did-not have good accuracy
So i want to add the code in image augmentation process!

How to add the code?

Hi @VK01, train_ssd.py already performs data augmentation during training here: https://github.com/dusty-nv/pytorch-ssd/blob/21383204c68846bfff95acbbd93d39914a77c707/vision/ssd/data_preprocessing.py#L4

You can add additional transformations to that section of code if you wish. However depending on the size of your dataset, you may want to add more data and/or train your model for more epochs.

1 Like

Thanks dusty_nv

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.