tensorflow-vdsr
tensorflow-vdsr copied to clipboard
What does "LR_STEP_SIZE" use for?
Hi,
I'm doubting that in VDSR.py #113, if the args staircase=True
,the exp_decay won't work forever.
The exp_decay can be calculated as:
decay_learning_rate = learning_rate * decay_rate ^ (global_step / decay_steps)
But in code "VDSR.py line#113", the global_step is calculated as global_step*BATCH_SIZE
, decay_steps is calculate aslen(train_list)*LR_STEP_SIZE
Why decay_steps not to be len(train_list)
.Why should it multiply LR_STEP_SIZE??
Look forward to your kind reply.
I have the same problem too. Have you understood it well? Would you mind tell me your idea to me ? Thank you very much!