Commit Graph

276 Commits

Author SHA1 Message Date
Yin Li
b50c7b6350 Remove input upsampling 2020-04-30 21:12:34 -04:00
Yin Li
a88f27a3a1 Add better looking tensorboard images 2020-04-22 00:56:29 -04:00
Yin Li
996c0d3aed Add auto loading of checkpoint 2020-04-21 18:34:18 -04:00
Yin Li
c9f468c568 Add explicit barrier after init dist groups 2020-04-21 13:38:02 -04:00
Yin Li
28d7cc9e9b Add default values to command line help 2020-04-21 13:01:17 -04:00
Yin Li
356e28c31f Add TOC 2020-04-21 12:34:14 -04:00
Yin Li
5adf6cbac6 Add exit when GPU not found 2020-04-20 19:27:57 -04:00
Yin Li
facfc13132 Add descriptions on files and tensorboard 2020-04-19 14:34:23 -04:00
Yin Li
01a60cc0c7 Add checkpoint symlink to state file 2020-04-16 17:50:08 -04:00
Yin Li
d01d0cee83 Add noise annealing duration 2020-03-09 12:07:55 -04:00
Yin Li
93d973b5c8 Change state saving to every epoch 2020-03-07 18:03:19 -05:00
Yin Li
ccb323e6ee Rewrite instance noise annealing scheduler 2020-03-07 15:04:01 -05:00
Yin Li
7a0f0bd979 Add new pytorch features with fallback to old 2020-03-07 14:49:18 -05:00
Yin Li
b7b14a37eb Make main.py runnable 2020-03-04 22:23:34 -05:00
Yin Li
5fbf447e2d Fix spectral norm interference with gradient visualization
spectral norm introduces weight_orig, so that not all weight parameters
ends with ".weight"
2020-03-04 16:21:00 -05:00
Yin Li
33fd13e4ac Fix bug from 1963530 to show last instead of 2nd layer gradients 2020-03-03 20:53:34 -05:00
Yin Li
d768aadb36 Add instructions 2020-03-03 20:23:13 -05:00
Yin Li
ef993d83e9 Add instance noise 2020-03-03 20:22:31 -05:00
Yin Li
1963530984 Add gradient norms to tensorboard 2020-03-02 11:31:38 -05:00
Yin Li
9567db7332 Add weight initialization 2020-03-01 22:31:30 -05:00
Yin Li
75b1c19dcd Combine input and output figures 2020-03-01 15:40:53 -05:00
Yin Li
a46746287a Fix bug when env SLURM_STEP_NUM_NODES is not defined 2020-02-14 15:51:36 -05:00
Yin Li
5cb4a1bbae Remove label smoothing for generator 2020-02-14 09:22:57 -05:00
Yin Li
b67079bf72 Add runtime address and port determination and share them via file
Together with slurm step node counts, make it possible to launch
multiple training in one job
2020-02-13 19:56:54 -06:00
Yin Li
1818e11265 Add simple label smoothing by --adv-real-label 2020-02-13 16:44:56 -05:00
Yin Li
d2840f01b0 Add --adv-start as epoch to start adversarial training
This is similar to the deprecated --adv-delay, but specify
absolute epoch (--adv-delay counts from start_epoch in resumed training)
2020-02-13 16:00:50 -05:00
Yin Li
e8039dcccc Move map loss computation forward in training 2020-02-13 14:40:51 -05:00
Yin Li
e383ec3977 Fix warnings on incompatible keys 2020-02-13 14:39:37 -05:00
Yin Li
53ed5a91f4 Change to nearest interpolation from linear in model super-resolution
To be consistent with the data super-resolution in data/fields.py
2020-02-13 12:01:04 -05:00
Yin Li
db3414e11c Disable D grad when updating G; Revert D and G order
The reason for the latter is to follow most code but I haven't
found the reason
2020-02-13 11:33:40 -05:00
Yin Li
aeeeb966d8 Add stride to ConvBlock 2020-02-11 17:20:42 -05:00
Yin Li
cc0efd28ec Fix bug: pprint -> pformat 2020-02-11 12:55:08 -05:00
Yin Li
2e2adc761d Add spectral normalization 2020-02-11 11:58:05 -05:00
Yin Li
b41e85eda5 Fix stupid merging bug 2020-02-09 23:07:40 -05:00
Yin Li
16b82fcc56 Merge branch 'anneal_loss'
Conflicts:
	map2map/models/patchgan.py
	map2map/train.py
2020-02-09 21:25:39 -05:00
Yin Li
2aed00d97e Add argument to disable ReduceLROnPlateau by default 2020-02-09 20:15:23 -05:00
Yin Li
a2e3a9dc64 Change PatchGAN architecture 2020-02-09 17:33:23 -05:00
Yin Li
1dd2b6d748 Extend training epochs in example scripts 2020-02-09 17:32:27 -05:00
Yin Li
09493ad4ec Add non-strict model state loading 2020-02-09 17:32:09 -05:00
Yin Li
f831afbccf Add PatchGAN42 similar to the PatchGAN in pix2pix 2020-02-07 15:26:16 -05:00
Yin Li
45c1d57e72 Add pretty-print argument to job stdout 2020-02-07 11:40:08 -05:00
Yin Li
3fb9708575 Remove saving / loading optimizer & scheduler states
Conflicts:
	map2map/train.py
2020-02-07 10:15:14 -05:00
Yin Li
23b903f81b Remove saving / loading optimizer & scheduler states 2020-02-07 10:02:32 -05:00
Yin Li
1cd34c2eed Remove lazy argument feeding from field dataset 2020-02-07 09:49:27 -05:00
Yin Li
890a459363 Fix bug 2020-02-06 19:34:43 -06:00
Yin Li
cd63324724 Change delayed adversary to a smooth annealing scheme 2020-02-06 19:04:30 -05:00
Yin Li
291dfb24b3 Add diff between out and tgt to figure 2020-02-05 21:19:03 -05:00
Yin Li
e20f3194a5 Change linear interpolation to nearest in super-resolution 2020-02-05 21:09:39 -05:00
Yin Li
679f9f2545 Add pyramid network 2020-02-05 20:20:17 -05:00
Yin Li
a5c48e71b0 Change noise channel removal from input 2020-02-05 14:40:45 -05:00