Home › Code › train_class_batch

train_class_batch

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

train_class_batch appears in the code Syntology harvested for 17 papers, as 8 distinct code bodies found in 21 places (a place is one code body under one paper). At least one of them ran in 8 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 train_class_batch 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 6 of the 8 distinct code bodies named train_class_batch; 2 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
6ran
2unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 8 of the 21 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

17 papers shown of 17, newest first; 21 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; 1 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
VMBench: A Benchmark for Perception-Aligned Video Motion Generation 13 Mar 2025 AMAP-ML/VMBench/VideoMAEv2/engine_for_finetuning.py c7976ea27edc377a unverified Apache-2.0 (permissive)
VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding 3 Dec 2024 kangsankim07/videoicl/InternVideo/InternVideo1/Pretrain/VideoMAE/engine_for_finetuning.py c7976ea27edc377a unverified no licence file found · pointer only
EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation 26 Jun 2024 opengvlab/egovideo/eccv-2022/engine_for_finetuning_ego4d_hands.py 011d4cf8cfdc2ffb ran no licence file found · pointer only
EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation 26 Jun 2024 opengvlab/egovideo/eccv-2022/engine_for_finetuning.py c7976ea27edc377a unverified no licence file found · pointer only
EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation 26 Jun 2024 opengvlab/egovideo/eccv-2022/engine_for_finetuning_ego4d_sta.py a0032907bd3ccf71 unverified no licence file found · pointer only
Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI 29 May 2024 935963004/labram/engine_for_finetuning.py bd7dd95069160f2e ran MIT (permissive)
TIM: A Time Interval Machine for Audio-Visual Action Recognition 8 Apr 2024 JacobChalk/TIM/feature_extractors/VideoMAE/engine_for_finetuning.py 93f25c853b7eeac5 ran no licence file found · pointer only
Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions 29 Mar 2024 Alvin-Zeng/temporal-robustness-benchmark/extract_corrupted_feature_code/videomae_v2/engine_for_finetuning.py c7976ea27edc377a unverified no licence file found · pointer only
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding 14 Mar 2024 opengvlab/video-mamba-suite/video-mamba-suite/action-recognition/engines/engine_for_finetuning_regression.py fb98703650f02bf6 ran MIT (permissive)
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding 14 Mar 2024 opengvlab/video-mamba-suite/video-mamba-suite/action-recognition/engines/engine_for_finetuning.py c7976ea27edc377a unverified MIT (permissive)
Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data 8 Feb 2024 jacklishufan/Mamba-ND/video_pretraining/engines/engine_for_finetuning_regression.py fb98703650f02bf6 ran no licence file found · pointer only
Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data 8 Feb 2024 jacklishufan/Mamba-ND/video_pretraining/engines/engine_for_finetuning.py c7976ea27edc377a unverified no licence file found · pointer only
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters 6 Feb 2024 baaivision/EVA/EVA-01/eva/engine_for_finetuning.py c7976ea27edc377a unverified MIT (permissive)
SA$^2$VP: Spatially Aligned-and-Adapted Visual Prompt 16 Dec 2023 tommy-xq/sa2vp/engine_for_train.py d15b621dd834bc4f ran MIT (permissive)
From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos 9 Dec 2023 FER-LMC/S2D/engine_for_finetuning.py 6b9b585439223637 ran Apache-2.0 (permissive)
Frozen Transformers in Language Models Are Effective Visual Encoder Layers 19 Oct 2023 ziqipang/lm4visualencoding/video_understanding/engine_for_finetuning.py c7976ea27edc377a unverified MIT (permissive)
MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition 5 Jul 2023 sunlicai/mae-dfer/engine_for_finetuning.py c7976ea27edc377a unverified MIT (permissive)
Masked Event Modeling: Self-Supervised Pretraining for Event Cameras 20 Dec 2022 tum-vision/mem/mem/engine_for_finetuning.py c7976ea27edc377a unverified Apache-2.0 (permissive)
AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders 16 Nov 2022 wgcban/adamae/msc/engine_for_finetuning.py c7976ea27edc377a unverified MIT (permissive)
Mugs: A Multi-Granular Self-Supervised Learning Framework 27 Mar 2022 sail-sg/mugs/eval/eval_finetuning/engine_for_finetuning.py c7976ea27edc377a unverified Apache-2.0 (permissive)
arXiv:aaai_28243 tommy-xq/SA2VP/engine_for_train.py d15b621dd834bc4f ran 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