Skip to content

Commit

Permalink
Update README.md
Browse files Browse the repository at this point in the history
  • Loading branch information
OmerFarukAtli authored Nov 14, 2024
1 parent 06eb964 commit 070e7e4
Showing 1 changed file with 7 additions and 3 deletions.
10 changes: 7 additions & 3 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -77,19 +77,23 @@ x.png is a single image containing both source and target image side-by-side. Th
Note that for many-to-one tasks, source modalities should be in the Red and Green channels.

## Training

Step 0
Before training your data you are required to run path_generate.py to generate 'spiral_eye.npy', 'spiral_r_eye_.npy', 'despiral_r_eye_.npy' which are required for training and testing. Note that this file will be run only for the first time.
```
python3 modules/path_generate.py
```
### Commands

1. One-to-one training, e.g. T2->PD

```
python3 train.py --dataroot datasets/IXI/T2_PD/ --name ixi_t2__pd --gpu_ids 0 --model i2i_mamba_one --which_model_netG i2i_mamba --which_direction AtoB --lambda_A 100 --dataset_mode aligned --norm batch --pool_size 0 --output_nc 1 --input_nc 1 --loadSize 256 --fineSize 256 --niter 30 --niter_decay 30 --save_epoch_freq 5 --checkpoints_dir checkpoints/ --display_id 0 --lr 0.0002
python3 train.py --dataroot datasets/IXI/T2_PD/ --name ixi_t2__pd --gpu_ids 0 --model i2i_mamba_one --which_model_netG i2i_mamba --which_direction AtoB --lambda_A 100 --dataset_mode aligned --norm batch --pool_size 0 --output_nc 1 --input_nc 1 --loadSize 256 --fineSize 256 --niter 30 --niter_decay 30 --save_epoch_freq 5 --checkpoints_dir checkpoints/ --display_id 0 --lr 0.0001
```

2. Many-to-one training, e.g. T1,T2->PD

```
python3 train.py --dataroot datasets/IXI/T1_T2__PD/ --name ixi_t1_t2__pd --gpu_ids 0 --model i2i_mamba_many --which_model_netG i2i_mamba --which_direction AtoB --lambda_A 100 --dataset_mode aligned --norm batch --pool_size 0 --output_nc 1 --input_nc 3 --loadSize 256 --fineSize 256 --niter 30 --niter_decay 30 --save_epoch_freq 5 --checkpoints_dir checkpoints/ --display_id 0 --lr 0.0002
python3 train.py --dataroot datasets/IXI/T1_T2__PD/ --name ixi_t1_t2__pd --gpu_ids 0 --model i2i_mamba_many --which_model_netG i2i_mamba --which_direction AtoB --lambda_A 100 --dataset_mode aligned --norm batch --pool_size 0 --output_nc 1 --input_nc 3 --loadSize 256 --fineSize 256 --niter 30 --niter_decay 30 --save_epoch_freq 5 --checkpoints_dir checkpoints/ --display_id 0 --lr 0.0001
```

### Argument descriptions
Expand Down

0 comments on commit 070e7e4

Please sign in to comment.