Closed carsonDB closed 8 years ago
It looks fine for me. For the arch, it should be conv->pool->ReLU. You can now try to run UCF-101 split1. You should follow the arch of the girl's paper.
@zbwglory Fine, I'll tune my parameters in correspondence with that paper's.
But as for the order of layers. Here is a quote from that paper (at page 4).
Each convolutional layer is followed by a rectified linear unit (ReLU) and a space-time max pooling layer
I ran the network with:
Learning rate: 0.003
dataset: UCF-11
Here is the training result after running for 18 hours.
C3D_train.tar.gz