make visdom default & add no_html & update scripts

1 files changed, 11 insertions, 10 deletions

diff --git a/README.md b/README.md
index 934e4bd..42ddcd3 100644
--- a/README.md
+++ b/README.md
@@ -60,12 +60,12 @@ cd pytorch-CycleGAN-and-pix2pix
 ```bash
 bash ./datasets/download_cyclegan_dataset.sh maps
 ```
-- Train a model:
+- Train a model (`bash ./scripts/train_cyclegan.sh`):
 ```bash
 python train.py --dataroot ./datasets/maps --name maps_cyclegan --model cycle_gan
 ```
-To view results as the model trains, check out the html file `./checkpoints/maps_cyclegan/web/index.html`
-- Test the model:
+- To view training results and loss plots, run `python -m visdom.server` and click the URL http://localhost:8097. To see more intermediate results, check out `./checkpoints/maps_cyclegan/web/index.html`
+- Test the model (`bash ./scripts/test_cyclegan.sh`):
 ```bash
 python test.py --dataroot ./datasets/maps --name maps_cyclegan --model cycle_gan --phase test
 ```
@@ -76,14 +76,14 @@ The test results will be saved to a html file here: `./results/maps_cyclegan/lat
 ```bash
 bash ./datasets/download_pix2pix_dataset.sh facades
 ```
-- Train a model:
+- Train a model (`bash ./scripts/train_pix2pix.sh`):
 ```bash
-python train.py --dataroot ./datasets/facades --name facades_pix2pix --model pix2pix --which_model_netG unet_256 --align_data --which_direction BtoA
+python train.py --dataroot ./datasets/facades --name facades_pix2pix --model pix2pix --which_model_netG unet_256 --which_direction BtoA --lambda_A 100 --align_data --no_lsgan
 ```
-To view results as the model trains, check out the html file `./checkpoints/facades_pix2pix/web/index.html`
-- Test the model:
+- To view training results and loss plots, run `python -m visdom.server` and click the URL http://localhost:8097. To see more intermediate results, check out  `./checkpoints/facades_pix2pix/web/index.html`
+- Test the model (`bash ./scripts/test_pix2pix.sh`):
 ```bash
-python test.py --dataroot ./datasets/facades --name facades_pix2pix --model pix2pix --which_model_netG unet_256 --align_data --which_direction BtoA
+python test.py --dataroot ./datasets/facades --name facades_pix2pix --model pix2pix --which_model_netG unet_256 --which_direction BtoA --align_data
 ```
 The test results will be saved to a html file here: `./results/facades_pix2pix/latest_val/index.html`.
 
@@ -92,7 +92,7 @@ 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 (default `--gpu_ids 0`): Set `--gpu_ids -1` to use CPU mode; set `--gpu_ids 0,1,2` for multi-GPU mode.
-- During training, the current results can be viewed using two methods. First, 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 have visdom installed and a server running by the command `python -m visdom.server`. The default server URL is `http://localhost:8097`. `display_id` corresponds to the window ID that is displayed on the `visdom` server. The `visdom` display functionality is turned on by default. To avoid the extra overhead of communicating with `visdom` set `--display_id 0`. Second, the intermediate results are saved to `[opt.checkpoints_dir]/[opt.name]/web/` as an HTML file. To avoid this, set `--no_html`. 
+- During training, the current results can be viewed using two methods. First, if you set `--display_id` > 0, the results and loss plot will be shown on a local graphics web server launched by [visdom](https://github.com/facebookresearch/visdom). To do this, you should have visdom installed and a server running by the command `python -m visdom.server`. The default server URL is `http://localhost:8097`. `display_id` corresponds to the window ID that is displayed on the `visdom` server. The `visdom` display functionality is turned on by default. To avoid the extra overhead of communicating with `visdom` set `--display_id 0`. Second, the intermediate results are saved to `[opt.checkpoints_dir]/[opt.name]/web/` as an HTML file. To avoid this, set `--no_html`.
 
 
 ### CycleGAN Datasets
@@ -139,7 +139,8 @@ This will combine each pair of images (A,B) into a single image file, ready for
 
 ## TODO
 - add reflection and other padding layers.
-- add one-direction test model.
+- add one-direction test mode for CycleGAN.
+- add more preprocessing options.
 - fully test Unet architecture.
 - fully test instance normalization layer from [fast-neural-style project](https://github.com/darkstar112358/fast-neural-style).
 - fully test CPU mode and multi-GPU mode.