최승미

Update README.md

Showing 1 changed file with 20 additions and 4 deletions
...@@ -21,17 +21,18 @@ Our Test Sequence ...@@ -21,17 +21,18 @@ Our Test Sequence
21 - Input bit-depth: 8 21 - Input bit-depth: 8
22 - Resolution: 768x768 22 - Resolution: 768x768
23 - HEVC & VVC QP: 22, 27, 32, 37 23 - HEVC & VVC QP: 22, 27, 32, 37
24 -- Compress AI Quality: 1, 2, 3, 4, 5, 6 24 +- Compress AI Quality: 1, 2, 3, 4
25 +- Proposed Method Quality: 1, 4, 6, 8
25 26
26 #### Sensor-generated Sequence 27 #### Sensor-generated Sequence
27 |Input bit-depth|Frame rate|Test sequence name|frame count| 28 |Input bit-depth|Frame rate|Test sequence name|frame count|
28 |:------:|:---:|:---:|:---:| 29 |:------:|:---:|:---:|:---:|
29 |8|50|CrowdRun|100| 30 |8|50|CrowdRun|100|
30 -|8|50|DucksTakeOff|100| 31 +|8|50|DucksTakeOff|75|
31 |8|50|OldTownCross|100| 32 |8|50|OldTownCross|100|
32 |8|50|Parkjoy|100| 33 |8|50|Parkjoy|100|
33 34
34 -#### Computer-generated Sequence 35 +#### Computer-generated Sequence (not use)
35 |Input bit-depth|Frame rate|Test sequence name|frame count| 36 |Input bit-depth|Frame rate|Test sequence name|frame count|
36 |:------:|:---:|:---:|:---:| 37 |:------:|:---:|:---:|:---:|
37 |8|60|ArenaOfValor|120| 38 |8|60|ArenaOfValor|120|
...@@ -94,6 +95,14 @@ Code explanation ...@@ -94,6 +95,14 @@ Code explanation
94 | └── rgb_to_png.m 95 | └── rgb_to_png.m
95 ├── 영상 주관적 화질평가 96 ├── 영상 주관적 화질평가
96 | └── pYUV manual.docx 97 | └── pYUV manual.docx
98 +├── 면담발표
99 +| └── ...
100 +├── 면담보고서
101 +| └── ...
102 +├── 멘토면담보고서
103 +| └── ...
104 +├── 주간보고서
105 +| └── ...
97 ├── 기초조사서.docx 106 ├── 기초조사서.docx
98 ├── 중간보고서.hwp 107 ├── 중간보고서.hwp
99 └── 최종보고서.docx 108 └── 최종보고서.docx
...@@ -112,13 +121,20 @@ PostProcessing: HEVC 또는 VVC에서 Decoding된 영상(10bit, BGR)을 8it, RGB ...@@ -112,13 +121,20 @@ PostProcessing: HEVC 또는 VVC에서 Decoding된 영상(10bit, BGR)을 8it, RGB
112 codec_allIntra: ALL Intra Compression Codec 121 codec_allIntra: ALL Intra Compression Codec
113 codec_proposed: First Frame Intra Compression + Other Frame Residual(clip(recon-ref, -0.5, 0.5)+0.5) Compression Codec 122 codec_proposed: First Frame Intra Compression + Other Frame Residual(clip(recon-ref, -0.5, 0.5)+0.5) Compression Codec
114 codec_anotherMethod: First Frame Intra + Other Frame Residual1(clip(recon-ref, 0, 1)), Residual2(-clip(recon-ref, -1, 0)) Codec 123 codec_anotherMethod: First Frame Intra + Other Frame Residual1(clip(recon-ref, 0, 1)), Residual2(-clip(recon-ref, -1, 0)) Codec
115 - 124 +train_RGB.py: Training code of RGB 444 format residual image
125 +train_YCbCr.py: Training code of YCbCr 444 format residual image
116 126
117 명령어 127 명령어
118 ```python 128 ```python
119 python [codec name] [encode or decode mode] --model [model name] -m [mse] -fr [frame rate] -f [frame count] -q [quality] [sequence name] 129 python [codec name] [encode or decode mode] --model [model name] -m [mse] -fr [frame rate] -f [frame count] -q [quality] [sequence name]
120 ``` 130 ```
131 +```python
132 +python [train name] -d [data path] --epochs [epochs] -lr [learning rate] -fr [frame rate] -f [frame count] -q [quality] --batch-size [batch size]
133 +```
121 명령어 예시 134 명령어 예시
122 ```python 135 ```python
123 python examples/codec-Copy2.py encode --model cheng2020-anchor -m mse -q 6 CrowdRun 136 python examples/codec-Copy2.py encode --model cheng2020-anchor -m mse -q 6 CrowdRun
137 +```
138 +```python
139 +python examples/mse_ycbcr.py -d Data/ --epochs 150 -lr 1e-4 -q 4 --batch-size 16 --cuda --save
124 ``` 140 ```
...\ No newline at end of file ...\ No newline at end of file
......