-
Notifications
You must be signed in to change notification settings - Fork 6.8k
index out of bound error when update eval metric #7664
Comments
I have same problem |
same problem,too. |
I have same problem,too. |
same problem here |
I add a while loop in image.py: I copy the first batch_szie-i times, It can works. |
I was training binary classification using .rec , met the same problem |
Maybe we should make our .rec files in our own ways to make sure it has no problem. |
@mxnet-label-bot add [Metric] |
Hi ,I am training a binary classification model with my own dataset. I use mx.image.ImageIter API to load raw images according to the .lst file generated myself(without using img2rec.py).
I set the data iter as below,
And my .lst file is
Then i start training, the first epoch went well, but a error was reported at the second epoch(epoch 1) as follow,
batch 3766 is the second last batch of a epoch, and batch 3767 is the last batch of a epoch.
I set the eval metric in my training script with two components:
so what is wrong in my usage?
Thx for your answer!
The text was updated successfully, but these errors were encountered: