You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In data_utils.py, the last incomplete batch from the next() function has wrong shape (real batch is padded with zero values). This will affect to training and testing results and is caused by: index_array, current_batch_size = next(self.index_generator), self.batch_size
Now the current batch_size is always the predefined self.batch_size, right?
I think the current batch size should be instead defined like this: current_batch_size = len(index_array)
The text was updated successfully, but these errors were encountered:
In data_utils.py, the last incomplete batch from the next() function has wrong shape (real batch is padded with zero values). This will affect to training and testing results and is caused by:
index_array, current_batch_size = next(self.index_generator), self.batch_size
Now the current batch_size is always the predefined self.batch_size, right?
I think the current batch size should be instead defined like this:
current_batch_size = len(index_array)
The text was updated successfully, but these errors were encountered: