Closed lizhenstat closed 4 years ago
Hi,
There is no particular reason. It is just the difference of implementation. Thanks
I find one related question on stackoverflow: https://stackoverflow.com/questions/39691902/ordering-of-batch-normalization-and-dropout which suggests placing dropout layer right after ReLu.
Since I test condensenet-182 on cifar100 with different configurations:
Hi, I noticed that the dropout is placed before convolution layer, In the original densenet-torch implementation, the order in each block is BN-->relu-->conv-->dropout Is there a particular reason for doing so?