CRNN-Keras
CRNN-Keras copied to clipboard
qjadud1994
Training from pre-trained model weights.
The code uses VGG architecture for feature extraction. My doubt is that, is it possible to begin training from VGG weights?
Initialization does not seem to matter.
Because I had trained the CRNN from scratch.
I tried CRNN with synthetic images of number plates. But the perfomance was poor on real images. So, I was wondering weather it is possible to do transfer learning with a smaller dataset that contains real images.
Of course, if you train only with synthetic images, it is natural that it does not work properly in real images.
So, I recommend pre-training with synthetic images and fine-tune with real data.
If you have few real images, it might be worth trying to proceed by learning only the last few layers.
Do you have any suggestion about, upto which layer I should set the trainable flag False. Since there are many different layers involved and GRU layers are also present, I am little confused about this.
Train all layers except pre-trained ones (VGG).
Can you please explain more ... ? How to do that ? Would you please show example code ? How to freeze those layers in model.py ? Thank you
