 nagadomi
|
b8ff8c6787
Remove -gamma_correction option
|
9 年之前 |
|
nagadomi
|
01b2e6d441
Remove -upsampling_filter option
|
9 年之前 |
|
nagadomi
|
e5cfd3dfce
Add -resume option
|
9 年之前 |
|
nagadomi
|
6c758ec5c0
Correct messages
|
9 年之前 |
|
nagadomi
|
307ae40883
Add noise_scale training
|
9 年之前 |
|
nagadomi
|
d0630d3a20
individual filters and box-only support
|
9 年之前 |
|
nagadomi
|
c89fd7249a
Add learning_rate_decay
|
9 年之前 |
|
nagadomi
|
634046d5f0
Fix training mode
|
9 年之前 |
|
nagadomi
|
b96bc5d453
Use correct criterion
|
9 年之前 |
|
nagadomi
|
8088460a20
Add oracle_rate option
|
9 年之前 |
|
nagadomi
|
8fec6f1b5a
Change the learning rate decay rate
|
9 年之前 |
|
nagadomi
|
7814691cbf
Add resize_blur parameter
|
9 年之前 |
|
nagadomi
|
a210090033
Convert model files; Add new pretrained model
|
9 年之前 |
|
nagadomi
|
51ae485cd1
Add new models
|
9 年之前 |
|
nagadomi
|
b8088ca209
Remove the limit of learning_rate_decay
|
9 年之前 |
|
nagadomi
|
7af5c9443d
Add model option and 12 layers net
|
9 年之前 |
|
nagadomi
|
68a6d4cef5
Use MSE instead of PSNR
|
9 年之前 |
|
nagadomi
|
fa9355be7c
Fix validation metric
|
9 年之前 |
|
nagadomi
|
a92b2cb386
Fix progressbar
|
9 年之前 |
|
nagadomi
|
ea780f1871
Fix validation metric
|
9 年之前 |
|
nagadomi
|
30fe5db735
Add upsampling_filter option
|
9 年之前 |
|
nagadomi
|
13f702b968
Add support for resizing with gamma correction
|
9 年之前 |
|
nagadomi
|
d4833160c7
Optionalize downsampling filters
|
9 年之前 |
|
nagadomi
|
4d115e4bdb
Add support for plotting loss chart
|
9 年之前 |
|
nagadomi
|
459c7c5e18
Use similar distribution on train/validation
|
9 年之前 |
|
nagadomi
|
1900ac7500
Use PSNR for evaluation
|
9 年之前 |
|
nagadomi
|
664322fa97
Remove cleanup_model.lua; Change model format from binary to ascii
|
9 年之前 |
|
nagadomi
|
290a5f960b
Use Huber loss instead of MSE
|
9 年之前 |
|
nagadomi
|
9b238bd693
Use clearState()
|
9 年之前 |
|
nagadomi
|
9f935835dd
Add -save_history option
|
9 年之前 |
