Yin Li
15384dc9bd
Add optional adversary model and make validation optional
2020-01-09 20:24:46 -05:00
Yin Li
9cf97b3ac1
Fix seeding bug introduced in the completely wrong commit f64b1e4
2020-01-06 20:20:05 -05:00
Yin Li
848dc87169
Change __dict__ to getattr
2019-12-23 16:11:43 -05:00
Yin Li
77710bc8a3
Cache data during the first epoch
2019-12-18 17:51:11 -05:00
Yin Li
01b0c8b514
Add data division, good with data caching
2019-12-18 17:13:40 -05:00
Yin Li
de24f8d585
Fix testing glob patterns
2019-12-18 15:31:39 -05:00
Yin Li
796c7918d8
Print args in testing
2019-12-17 20:23:27 -05:00
Yin Li
843fe09a92
Add data caching, and new pad and crop features
2019-12-17 12:00:13 -05:00
Yin Li
d03bcb59a1
Fix bug from 0533150
2019-12-12 19:26:57 -05:00
Yin Li
6d021ec949
Simplify swish for readability
2019-12-12 19:24:35 -05:00
Yin Li
0533150194
Save past best models by not overwriting them
2019-12-12 18:05:16 -05:00
Yin Li
946805c6be
Add swish activation, kernel_size in ConvBlock, and optional trailing activation in ResBlock
2019-12-12 16:49:19 -05:00
Yin Li
341bdbff84
Fix issue that pytorch 1.1 does not flush tensorboard
2019-12-12 15:25:45 -05:00
Yin Li
bd3798222a
Add weight decay
2019-12-12 12:04:39 -05:00
Yin Li
96b683bfef
Fix bug in cropping width indices
2019-12-11 16:45:14 -05:00
Yin Li
0c4a551354
Fix input shape and norm, and target norm in testing
2019-12-10 17:19:57 -05:00
Yin Li
7b6ff73be1
Move UNet with ResBlock to VNet and Revert UNet to the previous simple version
2019-12-09 21:53:27 -05:00
Yin Li
9e039c0407
Add variable skip connection in ResBlock
2019-12-09 20:59:39 -05:00
Yin Li
139caabe31
Remove pytorch version constraint and Add python 3 constraint in setup.py
2019-12-09 17:21:25 -05:00
Yin Li
0764a1006e
Remove unnecessary arguments --in-channels and --out-channels
2019-12-09 10:19:21 -05:00
Yin Li
f64b1e42e9
Add synchronized random seed to training
2019-12-08 21:27:44 -05:00
Yin Li
11c9caa1e2
Fix unstable training by limiting pytorch version to 1.1
2019-12-08 21:02:08 -05:00
Yin Li
437126e296
Fix DistributedDataParallel model save and load during training, leave testing for later
2019-12-08 21:00:51 -05:00
Yin Li
f2e9af6d5f
Revert scheduler to ReduceLROnPlateau
2019-12-08 20:58:46 -05:00
Yin Li
34b8c62c76
Merge branch 'master' of github.com:eelregit/map2map
...
Conflicts:
map2map/train.py
2019-12-03 18:07:11 -05:00
Yin Li
b253bb687b
Change ReduceLROnPlateau to CyclicLR
2019-12-03 18:06:33 -05:00
Yin Li
054ccb194e
Merge branch 'master' of github.com:eelregit/map2map
2019-12-03 18:03:41 -05:00
Yin Li
044e4c9376
Change ReduceLROnPlateau to CyclicLR
2019-12-03 18:02:56 -05:00
Yin Li
1f6b34dbf6
Merge branch 'master' of github.com:eelregit/map2map
2019-12-03 18:02:03 -05:00
Yin Li
36cf2ac93b
Change ReduceLROnPlateau to CyclicLR
2019-12-03 17:53:20 -05:00
Yin Li
afeefcaa9e
Merge branch 'master' of github.com:eelregit/map2map
...
Conflicts:
map2map/train.py
2019-12-03 17:52:01 -05:00
Yin Li
7540154eba
Change ReduceLROnPlateau to CyclicLR
2019-12-03 17:49:56 -05:00
Yin Li
bf3fe86afe
Change ReduceLROnPlateau to CyclicLR
2019-12-03 17:40:08 -05:00
Yin Li
0211eed0ec
Add testing
2019-12-01 21:40:35 -05:00
Yin Li
bcf95275f3
Fix global_step in tensorboard summary to start from 1
2019-11-30 22:15:10 -05:00
Yin Li
9d4b5daae3
Add enhanced model
...
Add ResBlock using ConvBlock;
Use ResBlock in UNet;
Use PReLU instead of LeakyReLU;
Add more channels in lower levels in UNet;
Add more blocks in each level in UNet;
2019-11-30 21:49:10 -05:00
Yin Li
88bfd11594
Add training
2019-11-30 16:31:10 -05:00
Yin Li
6015dd6b31
Initial commit
2019-11-30 15:27:25 -05:00
