Fine-tuning a pre-trained VGG16 model on my own data using TF-Slim

Question

I am trying to fine-tune the VGG-16 pretrained model using TF-Slim however, i am having trouble at the beginning (when attempting to preprocess the data i.e converting images from tiff to jpeg and then to tfrecord format).

Could anyone advise on the best method to use in order to finetune the model to suit these images?

Or maybe point me in the direction of a step by step guide on how to do this? Apologies as i am new to convnets and i am trying to figure out how to begin fine-tuning.

Thanks in advance.

Answer 1

You could get the detailed steps on how to fine-tuning a pre-trained model in the below TF slim walkthrough on flower dataset https://github.com/tensorflow/models/blob/master/research/slim/slim_walkthrough.ipynb

Also, I would recommend you to look into the below git for implementing on a custom dataset. https://gist.github.com/omoindrot/dedc857cdc0e680dfb1be99762990c9c/