Training on own dataset.

[tchugh]

Hi,

Could you please provide an example on how to use a trained model on our own dataset?

I am taking the following steps:

1. After the checkpoint is created, I pass the checkpoint to test.py as "decoder_weights".
2. I had to change "saver.restore(sess, decoder_weights)" to "saver.restore(sess, tf.train.latest_checkpoint(decoder_weights))" to read it successfully from checkpoint directory.
3. What should be passed to vgg_weights in test.py? Are we not fine-tuning the encoder (i.e. vgg weights) in the training on our own dataset?
   Does it remain same as "models/vgg19_weights_normalized.h5"?

Thank you in advance.