| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 2017-05-02 | use InstanceNorm2d from the latest pytorch | junyanz | |
| 2017-04-27 | changed the name of the loaded network from net_G_A to net_G | Taesung Park | |
| 2017-04-27 | 1. Added one_direction_test_model that generates the outputs in only one ↵ | Taesung Park | |
| direction 2. Changed the option naming from ntrain to max_dataset_size | |||
| 2017-04-23 | fix which_direction bug | junyanz | |
| 2017-04-22 | add comment for python 2/3 | junyanz | |
| 2017-04-22 | add dropout option for G | junyanz | |
| 2017-04-22 | fix the padding/kernel_size in D | junyanz | |
| 2017-04-21 | Following griegler's suggestion, fixed a bug in NLayerDiscriminator that ↵ | Taesung Park | |
| always applied sigmoid to the output | |||
| 2017-04-20 | add gpu_ids to save/cuda function | junyanz | |
| 2017-04-18 | Fixed bugs in the Unet structure | Taesung Park | |
| 2017-04-18 | fix assert bug | junyanz | |
| 2017-04-18 | add unet and update README | junyanz | |
| 2017-04-18 | fix assert bug | junyanz | |
| 2017-04-18 | first commit | junyanz | |
