diff options
| -rw-r--r-- | README.md | 9 | ||||
| -rw-r--r-- | options/train_options.py | 1 | ||||
| -rw-r--r-- | train.py | 6 |
3 files changed, 9 insertions, 7 deletions
@@ -107,10 +107,11 @@ python test.py --dataroot ./datasets/facades/testB/ --name facades_pix2pix --mod ``` ## Training/test Details -- See `options/train_options.py` and `options/base_options.py` for training flags; see `options/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. You need a large batch size (e.g. `--batchSize 32`) to benefit from multiple gpus. -- 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`. -- Images can be resized and cropped in different ways using `--resize_or_crop` option. The default option `'resize_and_crop'` resizes the image to be of size `(opt.loadSize, opt.loadSize)` and does a random crop of size `(opt.fineSize, opt.fineSize)`. `'crop'` skips the resizing step and only performs random cropping. `'scale_width'` resizes the image to have width `opt.fineSize` while keeping the aspect ratio. `'scale_width_and_crop'` first resizes the image to have width `opt.loadSize` and then does random cropping of size `(opt.fineSize, opt.fineSize)`. +- Flags: see `options/train_options.py` and `options/base_options.py` for all the training flags; see `options/test_options.py` and `options/base_options.py` for all the 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. You need a large batch size (e.g. `--batchSize 32`) to benefit from multiple GPUs. +- Visualization: during training, the current results can be viewed using two methods. First, if you set `--display_id` > 0, the results and loss plot will appear 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`. +- Preprocessing: images can be resized and cropped in different ways using `--resize_or_crop` option. The default option `'resize_and_crop'` resizes the image to be of size `(opt.loadSize, opt.loadSize)` and does a random crop of size `(opt.fineSize, opt.fineSize)`. `'crop'` skips the resizing step and only performs random cropping. `'scale_width'` resizes the image to have width `opt.fineSize` while keeping the aspect ratio. `'scale_width_and_crop'` first resizes the image to have width `opt.loadSize` and then does random cropping of size `(opt.fineSize, opt.fineSize)`. +- Fine-tuning/Resume training: to fine-tune a pre-trained model, or resume the previous training, use the `--continue_train` flag. The program will then load the model based on `which_epoch`. By default, the program will initialize the epoch count as 0. Set '--epoch_count <int>' to specify a different starting epoch count. ### CycleGAN Datasets diff --git a/options/train_options.py b/options/train_options.py index 345f619..a595017 100644 --- a/options/train_options.py +++ b/options/train_options.py @@ -9,6 +9,7 @@ class TrainOptions(BaseOptions): self.parser.add_argument('--save_latest_freq', type=int, default=5000, help='frequency of saving the latest results') self.parser.add_argument('--save_epoch_freq', type=int, default=5, help='frequency of saving checkpoints at the end of epochs') self.parser.add_argument('--continue_train', action='store_true', help='continue training: load the latest model') + self.parser.add_argument('--epoch_count', type=int, default=1, help='the starting epoch count, we save the model by <epoch_count>, <epoch_count>+<save_latest_freq>, ...') self.parser.add_argument('--phase', type=str, default='train', help='train, val, test, etc') self.parser.add_argument('--which_epoch', type=str, default='latest', help='which epoch to load? set to latest to use latest cached model') self.parser.add_argument('--niter', type=int, default=100, help='# of iter at starting learning rate') @@ -12,15 +12,15 @@ print('#training images = %d' % dataset_size) model = create_model(opt) visualizer = Visualizer(opt) - total_steps = 0 -for epoch in range(1, opt.niter + opt.niter_decay + 1): +for epoch in range(opt.epoch_count, opt.niter + opt.niter_decay + 1): epoch_start_time = time.time() + epoch_iter = 0 for i, data in enumerate(dataset): iter_start_time = time.time() total_steps += opt.batchSize - epoch_iter = total_steps - dataset_size * (epoch - 1) + epoch_iter += opt.batchSize model.set_input(data) model.optimize_parameters() |