Home › Code › set_weight_decay

set_weight_decay

Syntologyentry name in harvested coderead from the graph 2026-09-24

set_weight_decay appears in the code Syntology harvested for 32 papers, as 13 distinct code bodies found in 32 places (a place is one code body under one paper). At least one of them ran in 21 of the papers; 0 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named set_weight_decay do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 4 of the 13 distinct code bodies named set_weight_decay; 9 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
0ran · our draft was wrong
0ran · fixture could not drive it
4ran
9unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 12 of the 32 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

32 papers shown of 32, newest first; 32 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive; 6 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
Expanding Sparse Tuning for Low Memory Usage 4 Nov 2024 ssfgunner/SNELL/lib/utils.py b3b2e6a0853dff09 unverified MIT (permissive)
Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion 19 Oct 2024 edwardchasel/spatial-mamba/classification/utils/optimizer.py 2d5473f673967c35 unverified Apache-2.0 (permissive)
Depth-Wise Convolutions in Vision Transformers for Efficient Training on Small Datasets 28 Jul 2024 ztx-100/efficient_vit_with_dw/optimizer.py b33222a09fc93bec ran no licence file found · pointer only
DenoiseRep: Denoising Model for Representation Learning 13 Jun 2024 wangguanan/DenoiseRep/Classification/imagenet/Swin-Transformer/optimizer.py b33222a09fc93bec ran Apache-2.0 (permissive)
High-Performance Temporal Reversible Spiking Neural Networks with $O(L)$ Training Memory and $O(1)$ Inference Cost 26 May 2024 biclab/t-revsnn/optimizer.py 5dd42a7ce2cea5bd ran no licence file found · pointer only
Learning Spatial Similarity Distribution for Few-shot Object Counting 20 May 2024 CBalance/SSD/optimizer.py b33222a09fc93bec ran no licence file found · pointer only
Fast and Controllable Post-training Sparsity: Learning Optimal Sparsity Allocation with Global Constraint in Minutes 9 May 2024 ModelTC/FCPTS/train/optimizer.py 284f23322c9df1e7 unverified no licence file found · pointer only
DGMamba: Domain Generalization via Generalized State Space Model 11 Apr 2024 longshaocong/dgmamba/utils/optimizer.py 2d5473f673967c35 unverified no licence file found · pointer only
SS-MAE: Spatial-Spectral Masked Auto-Encoder for Multi-Source Remote Sensing Image Classification 8 Nov 2023 summitgao/ss-mae/utils/optimizer_step.py b33222a09fc93bec ran no licence file found · pointer only
arXiv:2310.15165 2023-10 (from id) sarapieri/fed_het/utils/util.py b33222a09fc93bec ran no licence file found · pointer only
At Which Training Stage Does Code Data Help LLMs Reasoning? 28 Sep 2023 yingweima2022/codellm/instruction_following.py f12f9486ba2960e6 ran no licence file found · pointer only
Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models 6 Sep 2023 lj2lijia/adapt/codegeex/mindspore/finetune.py f12f9486ba2960e6 ran MIT (permissive)
Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition 13 Jul 2023 talalwasim/video-focalnets/optimizer.py b33222a09fc93bec ran no licence file found · pointer only
Large-scale Dataset Pruning with Dynamic Uncertainty 8 Jun 2023 baai-dcai/dataset-pruning/ImageNet/optimizer.py b33222a09fc93bec ran MIT (permissive)
MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer 24 Apr 2023 fistyee/MixPro/optimizer.py b33222a09fc93bec ran MIT (permissive)
CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X 30 Mar 2023 THUDM/CodeGeeX/codegeex/mindspore/finetune.py f12f9486ba2960e6 ran Apache-2.0 (permissive)
Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency 21 Mar 2023 cerebrasresearch/sift/ComputerVision/ImageNet/utils/optim_utils.py 87e81f47b5aefd7c unverified Apache-2.0 (permissive)
Fine-tuned CLIP Models are Efficient Video Learners 6 Dec 2022 muzairkhattak/vifi-clip/utils/optimizer.py 883e1ab4ad47ea2d unverified MIT (permissive)
To update or not to update? Neurons at equilibrium in deep models 19 Jul 2022 eidoslab/neq/src/Swin-Transformer/optimizer.py d54a6d0b660e3b69 unverified MIT (permissive)
ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection 30 May 2022 ZHUANGHP/Analytic-continual-learning/analytic/ACIL.py 515618290aea20f8 ran MIT (permissive)
MetaFormer: A Unified Meta Framework for Fine-Grained Recognition 5 Mar 2022 dqshuai/metaformer/optimizer.py eac7e5fdc70e5cc9 unverified MIT (permissive)
Mixing and Shifting: Exploiting Global and Local Dependencies in Vision MLPs 14 Feb 2022 jegzheng/ms-mlp/optimizer.py b33222a09fc93bec ran MIT (permissive)
AS-MLP: An Axial Shifted MLP Architecture for Vision 18 Jul 2021 svip-lab/AS-MLP/optimizer.py b33222a09fc93bec ran MIT (permissive)
On the Connection between Local Attention and Dynamic Depth-wise Convolution 8 Jun 2021 Atten4Vis/DemystifyLocalViT/optimizer.py b33222a09fc93bec ran MIT (permissive)
Efficient Training of Visual Transformers with Small Datasets 7 Jun 2021 yhlleo/VTs-Drloc/optimizer.py b33222a09fc93bec ran MIT recorded; this copy not marked cleared · pointer only
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer 7 Jun 2021 mulinmeng/Shuffle-Transformer/optimizer.py b33222a09fc93bec ran MIT (permissive)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows 25 Mar 2021 canerozer/qct/optimizer.py b33222a09fc93bec ran MIT recorded; this copy not marked cleared · pointer only
arXiv:ijcai2025_0271 ZheminZhang1/HcNet/HcNet/optimizer.py b33222a09fc93bec ran MIT (permissive)
arXiv:ijcai2023_0504 Markin-Wang/CLEViT/optimizer.py 78862c82805c0e53 unverified MIT recorded; this copy not marked cleared · pointer only
arXiv:aaai_27798 LJ2lijia/AdapT/codegeex/mindspore/finetune.py f12f9486ba2960e6 ran MIT (permissive)
arXiv:Xie_PVMamba_Parallelizing_Vision_Mamba_via_Dynamic_State_Aggregation_ICCV_2025_paper VISION-SJTU/PVMamba/classification/utils/optimizer.py 2d5473f673967c35 unverified Apache-2.0 (permissive)
arXiv:Gao_Bootstrapping_SparseFormers_from_Vision_Foundation_Models_CVPR_2024_paper showlab/sparseformer/imagenet/optimizer.py a71abeaf668b91d6 unverified MIT (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections