최승미

Update README.md

......@@ -81,6 +81,7 @@ Code explanation
| ├── codec_proposed.py
| ├── codec_anotherMethod.py
| ├── train_RGB.py
| ├── train_RGB_MS-SSIMloss.py
| └── train_YCbCr.py
├── PostProcessing
| ├── get_BPP.m
......@@ -121,8 +122,9 @@ PostProcessing: HEVC 또는 VVC에서 Decoding된 영상(10bit, BGR)을 8it, RGB
codec_allIntra: ALL Intra Compression Codec
codec_proposed: First Frame Intra Compression + Other Frame Residual(clip(recon-ref, -0.5, 0.5)+0.5) Compression Codec
codec_anotherMethod: First Frame Intra + Other Frame Residual1(clip(recon-ref, 0, 1)), Residual2(-clip(recon-ref, -1, 0)) Codec
train_RGB.py: Training code of RGB 444 format residual image
train_YCbCr.py: Training code of YCbCr 444 format residual image
train_RGB.py: Training code of RGB 444 format residual image with MSE loss
train_RGB_MS-SSIMloss.py: Training code of RGB 444 format residual image with MS-SSIM loss
train_YCbCr.py: Training code of YCbCr 444 format residual image with MSE loss
명령어
```python
......@@ -133,8 +135,8 @@ python [train name] -d [data path] --epochs [epochs] -lr [learning rate] -fr [fr
```
명령어 예시
```python
python examples/codec-Copy2.py encode --model cheng2020-anchor -m mse -q 6 CrowdRun
python examples/codec_proposed.py encode --model cheng2020-anchor -m mse -q 6 CrowdRun
```
```python
python examples/mse_ycbcr.py -d Data/ --epochs 150 -lr 1e-4 -q 4 --batch-size 16 --cuda --save
python examples/train_YCbCr.py -d Data/ --epochs 150 -lr 1e-4 -q 4 --batch-size 16 --cuda --save
```
\ No newline at end of file
......