Age | Commit message (Expand) | Author | Files | Lines |
---|---|---|---|---|
2014-09-07 | fix transform_param in mnist_autoencoder.prototxt | Jeff Donahue | 1 | -3/+3 |
2014-09-03 | Move transform param one level up in the proto to reduce redundancy | Kai Li | 1 | -6/+6 |
2014-09-01 | Add "test-on-train" stage to test accuracy on the training data; correct | Jeff Donahue | 1 | -1/+21 |
2014-09-01 | mnist_autoencoder: always compute both cross-entropy loss and L2 | Jeff Donahue | 1 | -4/+4 |
2014-09-01 | use LMDB in mnist autoencoder examples | Jeff Donahue | 1 | -2/+4 |
2014-08-28 | set examples paths relative to root | Evan Shelhamer | 1 | -2/+2 |
2014-08-21 | upgrade model definitions for transformation params | Evan Shelhamer | 1 | -2/+6 |
2014-07-29 | Use unified train/test nets in examples. | Jeff Donahue | 1 | -0/+263 |