Thanks for your contribution!
But I have a question that during training, the total number of iteration of every epoch is 9446. I am wondering how this comes from...As we know, there are about 80k+40k-10k=110k images in the training set.
So the length of data_loader should be : 110k/batch_size=110k/60=1833, rather than 9446.
Can anyone help me?
Oh it came to me that since every image has about 5 or more captions, so we should let 1833 mulitply 5, then we can get the number 9165 close to 9446.
Am I right?
Thanks for your contribution! But I have a question that during training, the total number of iteration of every epoch is 9446. I am wondering how this comes from...As we know, there are about 80k+40k-10k=110k images in the training set. So the length of data_loader should be : 110k/batch_size=110k/60=1833, rather than 9446. Can anyone help me?