From c41ab7acdb1e9191d91991d6461ddc4dff3243f7 Mon Sep 17 00:00:00 2001 From: Ruotian Luo Date: Tue, 18 Apr 2017 21:10:01 -0500 Subject: Use visdom instead of display --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'README.md') diff --git a/README.md b/README.md index 372d349..d05d80e 100644 --- a/README.md +++ b/README.md @@ -86,7 +86,7 @@ More example scripts can be found at `scripts` directory. ## Training/test Details - See `options/train_options.py` and `options/base_options.py` for training flags; see `optoins/test_options.py` and `options/base_options.py` for test flags. - CPU/GPU: Set `--gpu_ids -1` to use CPU mode; set `--gpu_ids 0,1,2` for multi-GPU mode. -- During training, you can visualize the result of current training. If you set `--display_id 0`, we will periodically save the training results to `[opt.checkpoints_dir]/[opt.name]/web/`. If you set `--display_id` > 0, the results will be shown on a local graphics web server launched by [szym/display: a lightweight display server for Torch](https://github.com/szym/display). To do this, you should have Torch, Python 3, and the display package installed. You need to invoke `th -ldisplay.start 8000 0.0.0.0` to start the server. +- During training, you can visualize the result of current training. If you set `--display_id 0`, we will periodically save the training results to `[opt.checkpoints_dir]/[opt.name]/web/`. If you set `--display_id` > 0, the results will be shown on a local graphics web server launched by [visdom](https://github.com/facebookresearch/visdom). To do this, you should visdom installed. You need to invoke `python -m visdom.server` to start the server. ### CycleGAN Datasets Download the CycleGAN datasets using the following script: -- cgit v1.2.3-70-g09d2