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.

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

Remove logs #4

Merged
merged 81 commits into from
Jul 17, 2024
Merged
Changes from 1 commit
Commits
Show all changes
81 commits
Select commit Hold shift + click to select a range
38b1cf1
initial github copilot based refactor
FelixBenning May 9, 2024
6028bec
learning rate multiples
FelixBenning May 9, 2024
e825b65
some better descriptions
FelixBenning May 9, 2024
c8fc3c3
plotting gets own file
FelixBenning May 9, 2024
b505078
forgotten return
FelixBenning May 9, 2024
8c76ac2
linting
FelixBenning May 9, 2024
855943a
redo qq plots
FelixBenning May 9, 2024
bcace3d
some bugfixes
FelixBenning May 9, 2024
8dfbf90
Merge branch 'main' into factor-out-plotting
FelixBenning May 10, 2024
5b08567
start introducing metrics
FelixBenning May 10, 2024
c4672f6
towards a working benchmark
FelixBenning May 10, 2024
71573e5
working training
FelixBenning May 11, 2024
38682c4
benchmark directory
FelixBenning May 11, 2024
7b65239
adjust learning rate
FelixBenning May 11, 2024
1a0fdf8
remove wandb
FelixBenning May 11, 2024
6c5c3ab
batch size for learning rate
FelixBenning May 12, 2024
19ff92d
generalize sample cache
FelixBenning May 12, 2024
32fc421
visualize covariance
FelixBenning May 12, 2024
5151e5b
bug in lightning?
FelixBenning May 12, 2024
1a9b7ea
factour out regression and simplify repr
FelixBenning May 12, 2024
9344d3c
oversampled MNIST_CNN7
FelixBenning May 12, 2024
d981bda
get closer to FOB benchmarks
FelixBenning May 12, 2024
dc0ebc9
copy implementation from FOB
FelixBenning May 12, 2024
1397d1f
computer modern font
FelixBenning May 13, 2024
29eaab7
remove title add x-label
FelixBenning May 13, 2024
fdd1a55
remove mnistSimpleCNN folder
FelixBenning May 13, 2024
56dda0c
move plotting to its own space
FelixBenning May 13, 2024
f8dcb24
remove predict ugliness
FelixBenning May 13, 2024
69ed827
move appendix
FelixBenning May 13, 2024
d321feb
add rational quadratic implementation
FelixBenning May 13, 2024
c7af432
formatting
FelixBenning May 13, 2024
6b4d824
caches
FelixBenning May 14, 2024
9a1d458
fix comments
FelixBenning May 14, 2024
1e60ec6
logging everything about mnist
FelixBenning May 14, 2024
845e7f1
fix bug
FelixBenning May 14, 2024
58a6145
savefig
FelixBenning May 15, 2024
a4b3204
gitignore
FelixBenning May 15, 2024
9fb0114
Merge branch 'factor-out-plotting' of github.com:FelixBenning/pyrfd i…
FelixBenning May 15, 2024
21d45ef
learning rate output
FelixBenning May 15, 2024
60d94d2
norm lock feature
FelixBenning May 15, 2024
bcb4470
back to mnist
FelixBenning May 15, 2024
23d888a
Merge branch 'factor-out-plotting' of github.com:FelixBenning/pyrfd i…
FelixBenning May 15, 2024
0d00fd0
plot metrics
FelixBenning May 15, 2024
314dbe2
plot step behavior
FelixBenning May 15, 2024
0929361
plot_metrics
FelixBenning May 16, 2024
b4bf2b9
add logs
FelixBenning May 16, 2024
418072e
more metrics
FelixBenning May 16, 2024
9c742ff
more logs
FelixBenning May 16, 2024
92c6560
metrics and covariance fit
FelixBenning May 16, 2024
de9d849
more logs
FelixBenning May 16, 2024
5982bff
Merge branch 'factor-out-plotting' of github.com:FelixBenning/pyrfd i…
FelixBenning May 16, 2024
31d5da3
multiple runs of covariance fit
FelixBenning May 16, 2024
777b9de
add logs for cnn3
FelixBenning May 16, 2024
50d220b
logs and new plotting
FelixBenning May 17, 2024
7562722
128 logs
FelixBenning May 20, 2024
ac985cb
more logging
FelixBenning May 20, 2024
ed6bb2f
fix logging
FelixBenning May 20, 2024
4d96dfa
make linters happy
FelixBenning May 20, 2024
94e590f
conservative rfd
FelixBenning May 20, 2024
3a55033
tested conservatism
FelixBenning May 20, 2024
5fbbed1
black formatter
FelixBenning May 20, 2024
240b3f4
logs
FelixBenning May 20, 2024
d56b5be
more logs
FelixBenning May 20, 2024
0751abb
fix type annotations
FelixBenning May 20, 2024
d6eff3d
legacy workarounds
FelixBenning May 20, 2024
13ca61c
add conservatism to optimizer
FelixBenning May 20, 2024
e92d831
more logs
FelixBenning May 20, 2024
7d17707
fix bug
FelixBenning May 20, 2024
cf1d3d7
more logs
FelixBenning May 20, 2024
725747e
fashion mnist logs
FelixBenning May 20, 2024
999d264
fashion mnist logs
FelixBenning May 21, 2024
959d953
fix bug
FelixBenning May 21, 2024
f3f3e3a
algo - perf addition
FelixBenning May 21, 2024
afa66cb
AlgoPerf
FelixBenning May 21, 2024
656d2a3
logs of conservatism for debugging
FelixBenning May 22, 2024
be84ffa
logs of conservatism
FelixBenning May 22, 2024
5c0397b
more plotting machinery
FelixBenning May 22, 2024
3ca41ff
better covariance tests
FelixBenning May 22, 2024
0736f0d
identify conservatism problem
FelixBenning May 22, 2024
e64e3de
fix bug
FelixBenning May 22, 2024
b15a0f4
repo cleanup
simon-forb Jul 17, 2024
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
bug in lightning?
  • Loading branch information
FelixBenning committed May 12, 2024
commit 5151e5b0d678f370a657f2317f385a9dafb18f31
8 changes: 3 additions & 5 deletions benchmarking/classification/mnist/data.py
Original file line number Diff line number Diff line change
Expand Up @@ -40,8 +40,6 @@ def setup(self, stage: str):
self.train_data = MNISTDataset(
self.data_dir, train=True, transform=self.transform
)

if stage == "validate":
self.validation_data = MNISTDataset(
self.data_dir, train=False, transform=self.transform
)
Expand Down Expand Up @@ -97,11 +95,11 @@ def prepare_data(self):
def setup(self, stage: str):
# Assign train/val datasets for use in dataloaders
if stage == "fit":
mnist_full = FashionMNISTDataset(
self.train_data = FashionMNISTDataset(
self.data_dir, train=True, transform=self.transform
)
self.train_data, self.validation_data = random_split(
mnist_full, [0.8, 0.2], generator=torch.Generator().manual_seed(42)
self.validation_data = FashionMNISTDataset(
self.data_dir, train=False, transform=self.transform
)

# Assign test dataset for use in dataloader(s)
Expand Down