Model tensors are linked to batch size
mikylucky opened this issue · comments
When freezing the model, the frozen graph contains the information of the training batch size.
We should somehow refactor the model to avoid this behaviour when freezing
This is an implementation of Show, Attend and Read with tensorflow
mikylucky opened this issue · comments
When freezing the model, the frozen graph contains the information of the training batch size.
We should somehow refactor the model to avoid this behaviour when freezing