Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

add MGDA, DG, and normal training code #9

Open
wants to merge 74 commits into
base: master
Choose a base branch
from
Open

add MGDA, DG, and normal training code #9

wants to merge 74 commits into from

Conversation

johnwlambert
Copy link
Collaborator

  • Add MSeg model training code (plain mix)
  • Add MGDA training code
  • Add CCSA domain generalization training code
  • Add training configs

mseg-dataset and others added 26 commits August 23, 2020 00:56
@mseg-dataset
add MGDA, DG, and normal training code
822e341
@mseg-dataset
clean up training script
81360f0
@mseg-dataset
continue cleaning up the training script
8498539
@mseg-dataset
clean up imports
b1584ce
rename StupidTaxonomyConverter to NaiveTaxonomyConverter
8724d2e
remove commented lines
82ab6a0
remove commented out lines
196d10c
remove commented out lines
535cec1
remove commented out lines
f3586f9
remove commented out lines
9710a55
remove commented out lines
2584bd7
remove commented out lines
5c15c5d
remove commented out lines
b30ac36
remove commented out lines
19a5d26
remove commented out lines
53b5d46
remove commented out lines
c774215
remove commented-out lines
f0e5b64
remove commented out lines
86b941d
remove commented-out lines
db8390c
remove commented-out lines
6a29c5e
remove commented out lines
fdb38a0
Create training.md
b7c7a09
remove commented-out lines
7c2f909
Update training.md
dd57119
Update training.md
0cc23ac
remove commented-out lines
0deeac1
@johnwlambert johnwlambert mentioned this pull request Oct 13, 2020
Closed
johnwlambert and others added 30 commits October 17, 2020 13:19
@johnwlambert
improve var names
cacd162
@johnwlambert
improve var names
b2b8d29
@johnwlambert
improve var names
41d48bf
@johnwlambert
improve var names
3726638
@johnwlambert
update args.tc.classes to args.tc.num_uclasses to reflect TaxononomyC…
f8afb3c 
…onverter update
remove outdated config
b7ad193
clean up old yaml files, just pass dataset name at command line
566a1ad
remove unused config param
71e4cd7
remove outdated configs
dbe7b06
Delete unused configs
12f6655
remove unused configs
61fc77b
remove unused configs
dcda7e1
remove old VGA configs
dee5a37
correct typo
ea31c75
clean up train.py logic
0917abb
clean up train.py logic
ae063cc
remove tensorboard, since not using writer anyways
751000e
fix typos in train script
d011fab
merge master into training branch
6711886
remove old print statements
87cc9c8
Merge branch 'training' of https://github.com/mseg-dataset/mseg-semantic
c987204 
 into training
reformat train script using Python black formatter
cb23214
reformat more code with python black and remove finetune option (unused)
e741a3a
remove unused finetune option from configs
6592799
make a separate function to just compute number of iterations required
b121012
reformat with black
f8aac5c
clarify docstring when determining number of iters to run
fdf3b60
edit docstring describing number of iters
f45dfbb
fix type hint
f6d6a8b
move apex docstring to training.md
e9e35bf
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@johnwlambert @mseg-dataset