lucasrufkahr/Real-ESRGAN
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add trainining with one gpu

Browse Source
This commit is contained in:
Xintao
2021-09-17 10:13:25 +08:00
parent 0ad2e9c61e
commit b525d1793b
1 changed files with 30 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
Training.md
View File

@@ -114,12 +114,22 @@ You can merge several folders into one meta_info txt. Here is the example:
CUDA_VISIBLE_DEVICES=0,1,2,3 \ CUDA_VISIBLE_DEVICES=0,1,2,3 \
python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --launcher pytorch --debug python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --launcher pytorch --debug
``` ```
Train with **a single GPU**:
```bash
python realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --debug
```
1. The formal training. We use four GPUs for training. We use the `--auto_resume` argument to automatically resume the training if necessary. 1. The formal training. We use four GPUs for training. We use the `--auto_resume` argument to automatically resume the training if necessary.
```bash ```bash
CUDA_VISIBLE_DEVICES=0,1,2,3 \ CUDA_VISIBLE_DEVICES=0,1,2,3 \
python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --launcher pytorch --auto_resume python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --launcher pytorch --auto_resume
``` ```
Train with **a single GPU**:
```bash
python realesrgan/train.py -opt options/train_realesrnet_x4plus.yml --auto_resume
```
### Train Real-ESRGAN ### Train Real-ESRGAN
1. After the training of Real-ESRNet, you now have the file `experiments/train_RealESRNetx4plus_1000k_B12G4_fromESRGAN/model/net_g_1000000.pth`. If you need to specify the pre-trained path to other files, modify the `pretrain_network_g` value in the option file `train_realesrgan_x4plus.yml`. 1. After the training of Real-ESRNet, you now have the file `experiments/train_RealESRNetx4plus_1000k_B12G4_fromESRGAN/model/net_g_1000000.pth`. If you need to specify the pre-trained path to other files, modify the `pretrain_network_g` value in the option file `train_realesrgan_x4plus.yml`.
@@ -129,12 +139,22 @@ You can merge several folders into one meta_info txt. Here is the example:
CUDA_VISIBLE_DEVICES=0,1,2,3 \ CUDA_VISIBLE_DEVICES=0,1,2,3 \
python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --launcher pytorch --debug python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --launcher pytorch --debug
``` ```
Train with **a single GPU**:
```bash
python realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --debug
```
1. The formal training. We use four GPUs for training. We use the `--auto_resume` argument to automatically resume the training if necessary. 1. The formal training. We use four GPUs for training. We use the `--auto_resume` argument to automatically resume the training if necessary.
```bash ```bash
CUDA_VISIBLE_DEVICES=0,1,2,3 \ CUDA_VISIBLE_DEVICES=0,1,2,3 \
python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --launcher pytorch --auto_resume python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --launcher pytorch --auto_resume
``` ```
Train with **a single GPU**:
```bash
python realesrgan/train.py -opt options/train_realesrgan_x4plus.yml --auto_resume
```
## Finetune Real-ESRGAN on your own dataset ## Finetune Real-ESRGAN on your own dataset
You can finetune Real-ESRGAN on your own dataset. Typically, the fine-tuning process can be divided into two cases: You can finetune Real-ESRGAN on your own dataset. Typically, the fine-tuning process can be divided into two cases:
@@ -185,6 +205,11 @@ CUDA_VISIBLE_DEVICES=0,1,2,3 \
python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/finetune_realesrgan_x4plus.yml --launcher pytorch --auto_resume python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/finetune_realesrgan_x4plus.yml --launcher pytorch --auto_resume
``` ```
Train with **a single GPU**:
```bash
python realesrgan/train.py -opt options/finetune_realesrgan_x4plus.yml --auto_resume
```
### Use your own paired data ### Use your own paired data
You can also finetune RealESRGAN with your own paired data. It is more similar to fine-tuning ESRGAN. You can also finetune RealESRGAN with your own paired data. It is more similar to fine-tuning ESRGAN.
@@ -237,3 +262,8 @@ We use four GPUs for training. We use the `--auto_resume` argument to automatica
CUDA_VISIBLE_DEVICES=0,1,2,3 \ CUDA_VISIBLE_DEVICES=0,1,2,3 \
python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/finetune_realesrgan_x4plus_pairdata.yml --launcher pytorch --auto_resume python -m torch.distributed.launch --nproc_per_node=4 --master_port=4321 realesrgan/train.py -opt options/finetune_realesrgan_x4plus_pairdata.yml --launcher pytorch --auto_resume
``` ```
Train with **a single GPU**:
```bash
python realesrgan/train.py -opt options/finetune_realesrgan_x4plus_pairdata.yml --auto_resume
```