 nagadomi
|
bdaca16c67
perfomance tuning
|
9 years ago |
|
nagadomi
|
b066761cdc
Add data augmentation for user method
|
9 years ago |
|
nagadomi
|
e71ff1fc6a
Fix a bug in random blur
|
9 years ago |
|
nagadomi
|
0517605d0d
Remove flip() from preprocess() because the data will flip() at flip_augmentation()
|
9 years ago |
|
nagadomi
|
5a3d012f4e
Add random blur method for data augmentation
|
9 years ago |
|
nagadomi
|
c2e4bb4380
Support for multi-thread in training
|
9 years ago |
|
nagadomi
|
f7e83e4465
performance tuning
|
9 years ago |
|
nagadomi
|
eeb90dc39b
Fix a bug in preprocessing when filters=box only
|
9 years ago |
|
nagadomi
|
9d3e1a241e
refactor
|
9 years ago |
|
nagadomi
|
2e26122a9e
performance tuning
|
9 years ago |
|
nagadomi
|
d0630d3a20
individual filters and box-only support
|
9 years ago |
|
nagadomi
|
0349fc774c
refactor
|
9 years ago |
|
nagadomi
|
70eb2b508f
Fix a performance problem in resampling
|
9 years ago |
|
nagadomi
|
99e6dd1a57
Fix border removing
|
9 years ago |
|
nagadomi
|
51ae485cd1
Add new models
|
9 years ago |
