Diagonalwise Refactorization: An Efficient Training Method for Depthwise Convolutions

Q: How reproducible is "Diagonalwise Refactorization: An Efficient Training Method for Depthwise Convolutions"?

Estimated time to first reproduction: a few days. Risk flags: No repository-level reproducibility signals are currently available, Estimate is based on paper-only reproduction flow. No direct maintained implementation was found. Use the paper PDF and citation graph to design a baseline reproduction.

Zheng Qin, Zhaoning Zhang, Dongsheng Li, Yiming Zhang, Yuxing Peng

Published: Jul 1, 2018

No direct implementation yet

Evidence: Inferred

Domain fit: AI-adjacent

Verified repos: 0

Paper appears method- or tooling-adjacent to AI workflows with partial ecosystem coverage.

Time to first repro: a few days

2 risk flags

DOI Publisher

Depthwise convolutions provide significant performance benefits owing to the reduction in both parameters and mult-adds. However, training depthwise convolution layers with GPUs is slow in current deep learning frameworks because their implementations cannot fully utilize the GPU capacity. To address this problem, in this paper we present an efficient method (called diagonalwise refactorization) for accelerating the ...

Read full abstract

training of depthwise convolution layers. Our key idea is to rearrange the weight vectors of a depthwise convolution into a large diagonal weight matrix so as to convert the depthwise convolution into one single standard convolution, which is well supported by the cuDNN library that is highly-optimized for GPU computations. We have implemented our training method in five popular deep learning frameworks. Evaluation results show that our proposed method gains 15.4× training speedup on Darknet, 8.4× on Caffe, 5.4× on PyTorch, 3.5× on MXNet, and 1.4× on TensorFlow, compared to their original implementations of depthwise convolutions.

Technical details

Canonical key: doi-10.1109_ijcnn.2018.8489312

Cache status: Fresh

Generated at: Jun 17, 2026, 6:14 PM

Artifact coverage: sparse

HF provider: ok (mixed)

PWC source used: No

LLM status: not_generated

LLM model: n/a

LLM generated: Unknown

LLM content type: n/a

HF policy: hf-relevance-v27

context only

Benchmarks: missing

Time to repro: a few days

2 risk flags

Results & Benchmarks

Freshness tier: cold

Direct + Inferred Evidence

No concrete benchmark grounding is available yet. Treat the page as context or an implementation starting point only.

Depthwise convolutions provide significant performance benefits owing to the reduction in both parameters and mult-adds.

Implementation Evidence Summary

Confidence: low

Recommendation evidence is currently too limited for a maintained-repo choice. Use Implementation Status and Reproduction Path for a practical baseline plan.

Reproduction Risks

Estimate is based on paper-only reproduction flow

Hardware Notes

Expect multi-day setup/compute for meaningful reproduction based on current guidance.

Evidence disclosure

Evidence graph: 2 refs, 1 links.

Utility signals: depth 65/100, grounding 58/100, status medium.

Implementation Status

No verified maintained repo

There is no verified maintained implementation yet. Use this baseline plan to decide whether to prototype now or defer.

No direct maintained implementation was found. Use the paper PDF and citation graph to design a baseline reproduction.
Start from related paper: Another view on parallel speedup.
Track assumptions and missing details in an experiment log before coding.

Time to first repro: a few days

Reproduction readiness

No Repo

Time to first repro: days

Last checked: Jun 17, 2026

Hardware requirements

Expect multi-day setup/compute for meaningful reproduction based on current guidance.

No verified implementation available

· No maintained repository has been identified for this paper. Check adjacent implementations or HF artifacts below.

No benchmark numbers could be verified. You will not be able to validate reproduction correctness against published numbers.

Hugging Face artifacts

No trustworthy direct or curated related Hugging Face artifacts were found yet.

Continue with targeted Hugging Face searches derived from the paper title and method context:

Models

Diagonalwise Refactorization Convolution (computer science) Convolution (computer science) model

Datasets

Convolution (computer science) dataset Diagonalwise Refactorization dataset

Spaces

Convolution (computer science) demo Diagonalwise Refactorization demo

Tip: start with models, then check datasets/spaces if you need evaluation data or demos.

Direct artifact matches are currently sparse. Use targeted Hugging Face searches to quickly locate candidate models, datasets, and demos.

Search models Search datasets Search spaces

Research context

Citations

References

Tasks

Computer science, Convolution (computer science), Speedup, Diagonal, Computation, Deep learning, Implementation, Key (lock)

Methods

Algorithm

Domains

Artificial intelligence, Computer Vision and Pattern Recognition

Evaluation & Human Feedback Data

Open this paper in HFEPX to review benchmark signals, evaluation modes, and human-feedback protocol context.

Open in HFEPX

Explore Similar Papers

Jump to Paper2Code search queries derived from this paper's research context.

Computer science Convolution (computer science) Speedup Diagonal Computation Deep learning