 nagadomi
|
6cca2f8488
Add -force_cudnn option to tools/benchmark.lua
|
9 years ago |
|
nagadomi
|
67d36a1220
benchmark time
|
9 years ago |
|
nagadomi
|
83188c5ab7
Add support for method=noise_scale to tools/benchmark.lua
|
9 years ago |
|
nagadomi
|
c16d0a07a2
Add -crop_size and -batch_size option to tools/benchmark.lua. Fix a bug in tta mode.
|
9 years ago |
|
nagadomi
|
b8ff8c6787
Remove -gamma_correction option
|
9 years ago |
|
nagadomi
|
5e222a3981
Add -tta and -resize_blur option to benchmark
|
9 years ago |
|
nagadomi
|
8e9e4433d3
Add thread option to benchmark
|
9 years ago |
|
nagadomi
|
d31fbe9bb1
Improve benchmark script
|
9 years ago |
|
nagadomi
|
7710a30225
Add useful option to benchmark
|
9 years ago |
|
nagadomi
|
d9474702f6
Fix NaN in benchmark script
|
9 years ago |
|
nagadomi
|
13f702b968
Add support for resizing with gamma correction
|
9 years ago |
|
nagadomi
|
56296c25b3
refactor
|
10 years ago |
|
nagadomi
|
dde2cdf294
Fix denoising benchmark
|
10 years ago |
|
nagadomi
|
3c9726da81
rmse
|
10 years ago |
|
nagadomi
|
4551ddaaa6
Add support to reproduce the dynamic range bug in PSNR
|
10 years ago |
|
nagadomi
|
b829595c21
Make compatible with MATLAB based benchmarks
|
10 years ago |
|
nagadomi
|
abedec9d9b
Fix filter name for graphicsmagick
|
10 years ago |
|
nagadomi
|
e9187ecf1c
load float images directly
|
10 years ago |
|
nagadomi
|
c47df93505
show baseline
|
10 years ago |
|
nagadomi
|
7ac7923345
Don't run model2 benchmark when model2_dir is not specified
|
10 years ago |
|
nagadomi
|
5ab2c605c8
Fix header include order issues
|
10 years ago |
|
nagadomi
|
df1c1b2c1e
tools/bechmark.lua: Add -filter option. refactor
|
10 years ago |
|
nagadomi
|
2b9753157a
simplify
|
10 years ago |
|
nagadomi
|
1a20ec501b
Fix the evaluation metric in benchmark
|
10 years ago |
|
nagadomi
|
425898a3aa
Don't use cudnn.benchmark mode when predicting
|
10 years ago |
|
nagadomi
|
4c691b4640
refactor
|
10 years ago |
|
nagadomi
|
3abc5a03e3
refactor
|
10 years ago |
