About the training data VID2015 and training time

Thanks for your work and code.

When i use the VID2015 as training data ,it will generate 464873 pairs traning data, even the batchsize is set to be 32, it still have more than 10000 calculations in one epoch. How to solve this problem when you are training the network?

Thanks~

Start by tracing how VID2015 produces 464873 training pairs and how the configured batch size of 32 is used during an epoch. Check the training entry point and data-generation code, then determine whether the reported calculation count is expected and document or change the training behavior accordingly.

Written by the indexing model from the issue text.