-
Notifications
You must be signed in to change notification settings - Fork 6
Add deep EBMs #66
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
Open
nbereux
wants to merge
32
commits into
DsysDML:develop
Choose a base branch
from
AidanLiotard:develop
base: develop
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Add deep EBMs #66
Changes from all commits
Commits
Show all changes
32 commits
Select commit
Hold shift + click to select a range
57e8174
Premiere tentative implémentation EBM
ArdSionnach 8aff401
Premier essai EBM
ArdSionnach d282fa6
Avant gros train
ArdSionnach 791883f
added visible field
ArdSionnach 85cb3c8
Update cli
ArdSionnach bad733f
notebooks and trainings
ArdSionnach 74361bc
update var init
ArdSionnach 3664a4c
alpha
ArdSionnach f24edd6
alpha v2
ArdSionnach 7877abf
CEBM
ArdSionnach 90251ed
BEBM_MLP_ReLU_vs_SiLU
ArdSionnach d1dde0d
update_h_gradient
ArdSionnach 2677495
notebook comparaison
ArdSionnach 2307ab3
h start a 0
ArdSionnach af905e2
Notebooks
ArdSionnach 595fbde
init h
ArdSionnach 0bc5cee
notebook
ArdSionnach c3621bb
sigmoid
ArdSionnach f9c1e8a
bug init h
ArdSionnach 41875c0
revert silu
ArdSionnach 314c94c
MLP no w2 + modular weights
ArdSionnach 6d1d162
debug
ArdSionnach d2d6273
Sigmo no w2
ArdSionnach 3be6369
option silu sigmo
ArdSionnach af70bf4
weight scale
ArdSionnach 7079921
weight scale
ArdSionnach 8eb0f7e
alpha init
ArdSionnach c450bf7
alpha again
ArdSionnach 133ba16
nb
ArdSionnach ecf8977
weight scale init
ArdSionnach 6cb833c
Restructure
ArdSionnach 654ea3f
Merge pull request #1 from AidanLiotard/update_h_gradient
AidanLiotard File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
Binary file not shown.
Large diffs are not rendered by default.
Oops, something went wrong.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,130 @@ | ||
| [ | ||
| { | ||
| "label": "PCD SiLU NoW2", | ||
| "file": "pcd_trains/BEBM_SiLUNoW2_MNIST_DMALA1000_h500_init2e-3_lr1_1M.h5", | ||
| "n_saved": 149, | ||
| "last_update": 165958, | ||
| "keys": [ | ||
| "activation_id", | ||
| "net.0.bias", | ||
| "net.0.weight", | ||
| "visible_field" | ||
| ], | ||
| "vf_norm": 83033.9921875, | ||
| "vf_max": 11102.6220703125, | ||
| "vf_mean": -1595.8912353515625, | ||
| "w1_shape": "(500, 784)", | ||
| "w1_top1": 316697.84375, | ||
| "w1_top10": 35082.2109375, | ||
| "w1_top100": 3777.509765625, | ||
| "w1_rank1_share": 0.9939182996749878, | ||
| "w1_fro": 317665.21875, | ||
| "b1_mean": -186.12503051757812, | ||
| "b1_std": 4.241181373596191, | ||
| "b1_max": 199.09078979492188 | ||
| }, | ||
| { | ||
| "label": "PCD Sigmoid NoW2", | ||
| "file": "pcd_trains/BEBM_SigmoidNoW2_MNIST_DMALA1000_h500_init2e-3_lr1_1M.h5", | ||
| "n_saved": 149, | ||
| "last_update": 165958, | ||
| "keys": [ | ||
| "activation_id", | ||
| "net.0.bias", | ||
| "net.0.weight", | ||
| "visible_field" | ||
| ], | ||
| "vf_norm": 175.0694122314453, | ||
| "vf_max": 12.101303100585938, | ||
| "vf_mean": -4.691315174102783, | ||
| "w1_shape": "(500, 784)", | ||
| "w1_top1": 246.93637084960938, | ||
| "w1_top10": 119.21197509765625, | ||
| "w1_top100": 38.297794342041016, | ||
| "w1_rank1_share": 0.22283990681171417, | ||
| "w1_fro": 523.1046142578125, | ||
| "b1_mean": -3.8225128650665283, | ||
| "b1_std": 2.0763652324676514, | ||
| "b1_max": 6.312178134918213 | ||
| }, | ||
| { | ||
| "label": "PCD SiLU W2", | ||
| "file": "pcd_trains/BEBM_SiLUW2_MNIST_DMALA1000_h500_init2e-3_lr1e-1_1M.h5", | ||
| "n_saved": 134, | ||
| "last_update": 58884, | ||
| "keys": [ | ||
| "net.0.bias", | ||
| "net.0.weight", | ||
| "net.2.bias", | ||
| "net.2.weight", | ||
| "visible_field" | ||
| ], | ||
| "vf_norm": 162.9449462890625, | ||
| "vf_max": 9.335200309753418, | ||
| "vf_mean": -4.58335542678833, | ||
| "w1_shape": "(500, 784)", | ||
| "w1_top1": 38.34831237792969, | ||
| "w1_top10": 24.081403732299805, | ||
| "w1_top100": 11.07005500793457, | ||
| "w1_rank1_share": 0.08474628627300262, | ||
| "w1_fro": 131.73036193847656, | ||
| "w2_shape": "(1, 500)", | ||
| "w2_norm": 48.97020721435547, | ||
| "w2_max": 5.792479991912842, | ||
| "b1_mean": -0.2771584689617157, | ||
| "b1_std": 2.4273900985717773, | ||
| "b1_max": 23.419179916381836 | ||
| }, | ||
| { | ||
| "label": "PTT SiLU NoW2", | ||
| "file": "ptt_trains/BEBM_SiLUNoW2_MNIST_PTT_DMALA1000_h500_init2e-3_lr1_500k.h5", | ||
| "n_saved": 148, | ||
| "last_update": 65407, | ||
| "keys": [ | ||
| "activation_id", | ||
| "net.0.bias", | ||
| "net.0.weight", | ||
| "visible_field" | ||
| ], | ||
| "vf_norm": 237.40695190429688, | ||
| "vf_max": 18.76725196838379, | ||
| "vf_mean": -6.284590721130371, | ||
| "w1_shape": "(500, 784)", | ||
| "w1_top1": 292.43609619140625, | ||
| "w1_top10": 283.3573303222656, | ||
| "w1_top100": 239.63055419921875, | ||
| "w1_rank1_share": 0.010965309105813503, | ||
| "w1_fro": 2792.67578125, | ||
| "b1_mean": -0.03123946487903595, | ||
| "b1_std": 1.0010740756988525, | ||
| "b1_max": 3.9160094261169434 | ||
| }, | ||
| { | ||
| "label": "PTT SiLU W2", | ||
| "file": "ptt_trains/BEBM_SiLUW2_MNIST_PTT_DMALA1000_h500_init2e-3_lr1e-1_500k.h5", | ||
| "n_saved": 163, | ||
| "last_update": 33879, | ||
| "keys": [ | ||
| "net.0.bias", | ||
| "net.0.weight", | ||
| "net.2.bias", | ||
| "net.2.weight", | ||
| "visible_field" | ||
| ], | ||
| "vf_norm": 153.01023864746094, | ||
| "vf_max": 9.231229782104492, | ||
| "vf_mean": -4.340636730194092, | ||
| "w1_shape": "(500, 784)", | ||
| "w1_top1": 7.3609299659729, | ||
| "w1_top10": 4.708344459533691, | ||
| "w1_top100": 1.409213662147522, | ||
| "w1_rank1_share": 0.1199466660618782, | ||
| "w1_fro": 21.253896713256836, | ||
| "w2_shape": "(1, 500)", | ||
| "w2_norm": 35.71017837524414, | ||
| "w2_max": 10.47995662689209, | ||
| "b1_mean": 0.06310277432203293, | ||
| "b1_std": 0.463110089302063, | ||
| "b1_max": 7.387264728546143 | ||
| } | ||
| ] |
|
Contributor
Author
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Retire le du dossier |
Large diffs are not rendered by default.
Oops, something went wrong.
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
ca degage