About the training iterations

[stark1092]

Hi, thanks for your release of this code.
I have a problem about the training iteration on kitti_odometry data.
There are 20400 pairs of images as the training data, and batch size is 8, iteration is 200000.
So the training of the odometry data has 200000/(20400/8) = 78 epochs.
But in the paper, you just train flow/depth for 20 epochs.
If I want to reproduce the result, which iteration should I take?
Or my understanding of this parameter is wrong?
Waiting for your reply, thanks!

[thuzhaowang]

Hi @stark1092, please use the hyper-parameter settings in the code.