Papers › DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of...

DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks

2 Jun 2022arXiv:2206.00843archive 2025-07-28

Yonggan Fu, Haichuan Yang, Jiayi Yuan, Meng Li, Cheng Wan, Raghuraman Krishnamoorthi, Vikas Chandra, Yingyan Celine Lin

Efficient deep neural network (DNN) models equipped with compact operators (e.g., depthwise convolutions) have shown great potential in reducing DNNs' theoretical complexity (e.g., the total number of weights/operations) while maintaining a decent model accuracy. However, existing efficient DNNs are still limited in fulfilling their promise in boosting real-hardware efficiency, due to their commonly adopted compact operators' low hardware utilization. In this work, we open up a new compression paradigm for developing real-hardware efficient DNNs, leading to boosted hardware efficiency while maintaining model accuracy. Interestingly, we observe that while some DNN layers' activation functions help DNNs' training optimization and achievable accuracy, they can be properly removed after training without compromising the model accuracy. Inspired by this observation, we propose a framework dubbed DepthShrinker, which develops hardware-friendly compact networks via shrinking the basic building blocks of existing efficient DNNs that feature irregular computation patterns into dense ones with much improved hardware utilization and thus real-hardware efficiency. Excitingly, our DepthShrinker framework delivers hardware-friendly compact networks that outperform both state-of-the-art efficient DNNs and compression techniques, e.g., a 3.06% higher accuracy and 1.53× throughput on Tesla V100 over SOTA channel-wise pruning method MetaPruning. Our codes are available at: https://github.com/facebookresearch/DepthShrinker.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 13 ran (of which 3 constructed an object rather than computing a result; 9 with no instrument failure: 5 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 13 ran (9 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

facebookresearch/depthshrinker officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 15 samples, 13 ran (4 instrument-failed) · 2 unverified report
rice-eic/depthshrinker officialmentioned in paperMITSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested: 13 ran (of which 3 constructed an object rather than computing a result; 9 with no instrument failure: 5 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran · honoured contract
1ran · violated contract
4ran · our draft was wrong
3ran
2unverified

Licence: 15 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from facebookresearch/depthshrinker. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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 label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

facebookresearch/depthshrinker official repository 15 samples, 13 ran (4 instrument-failed) · 2 unverified
CondConv2d models/efficientnet_blocks.py ran · metamorphic tier: deterministic licence not identified · pointer only · eb9c56ce6ebabe0e · report fixture: returned CondConv2d · level recorded 2026-09-22
Conv2dSame in 7 papers models/efficientnet_blocks.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 5ce1979636036635 · report fixture: returned Conv2dSame · level recorded 2026-09-22
MixedConv2d models/efficientnet_blocks.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 8e8ca221bdc062f3 · report fixture: returned MixedConv2d · level recorded 2026-09-22
_split_channels models/efficientnet_blocks.py ran · honoured contract fingerprinted licence not identified · pointer only · f28e60bc5be022ce · report fixture: signature num_chan:int/0/int, num_groups:int/0/int · returned list · level recorded 2026-09-22
conv2d_same in 8 papers models/efficientnet_blocks.py ran · our draft was wrong licence not identified · pointer only · 61bb8dbefa4ed19a · report fixture: signature x:Tensor/4/float, weight:Tensor/4/float, bias:Tensor/1/float, stride:tuple/1/int, padding:tuple/1/int, dilation:tuple/1/int, groups:int/0/int · returned Tensor · level recorded 2026-09-22
create_conv2d_pad in 6 papers models/efficientnet_blocks.py ran · our draft was wrong licence not identified · pointer only · 9ad464c2bfb49b0f · report fixture: signature in_chs:int/0/int, out_chs:int/0/int, kernel_size:int/0/int · returned Conv2d · level recorded 2026-09-22
get_condconv_initializer models/efficientnet_blocks.py ran · our draft was wrong licence not identified · pointer only · 816ebe82b6b6275f · report fixture: signature initializer:callable/0/?, num_experts:int/0/int, expert_shape:tuple/1/int · returned function · level recorded 2026-09-22
get_padding in 84 papers models/efficientnet_blocks.py ran · honoured contract fingerprinted licence not identified · pointer only · 73876e077d3acdf5 · report fixture: signature kernel_size:int/0/int, stride:int/0/int, dilation:int/0/int · returned int · level recorded 2026-09-22
get_padding_value in 7 papers models/efficientnet_blocks.py ran · honoured contract licence not identified · pointer only · 5993ba1d4c4de0b5 · report fixture: signature padding:str/0/str, kernel_size:int/0/int, stride:int/0/int, dilation:int/0/int · returned tuple · level recorded 2026-09-22
get_same_padding in 16 papers models/efficientnet_blocks.py ran · honoured contract fingerprinted licence not identified · pointer only · 54e11386110ff042 · report fixture: signature x:int/0/int, k:int/0/int, s:int/0/int, d:int/0/int · returned int · level recorded 2026-09-22
is_static_pad models/efficientnet_blocks.py ran · violated contract licence not identified · pointer only · ffb95d7b0bd531e5 · report fixture: signature kernel_size:int/0/int, stride:int/0/int, dilation:int/0/int · returned bool · level recorded 2026-09-22
make_divisible in 76 papers models/efficientnet_blocks.py ran · honoured contract fingerprinted licence not identified · pointer only · 24400bc088ed228d · report fixture: signature v:int/0/int, divisor:int/0/int, min_value:NoneType/0/?, round_limit:float/0/float · returned int · level recorded 2026-09-22
pad_same in 5 papers models/efficientnet_blocks.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 3035cd0e2de9e8a4 · report fixture: signature x:Tensor/4/float, k:list/1/int, s:list/1/int, d:list/1/int, value:float/0/float · returned Tensor · level recorded 2026-09-22
InvertedResidual_Share_Act models/efficientnet_blocks.py unverified licence not identified · pointer only · 05657319f92544ce · report
create_conv2d models/efficientnet_blocks.py unverified licence not identified · pointer only · afb4d58768af3f8f · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for DepthShrinker (graph method: DepthShrinker). 17 bricks; individually on a fixture: 15 ran (of which 3 constructed an object rather than computing a result; 9 with no instrument failure: 5 honoured, 1 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. InvertedResidual_Share_Act entry · level 0 · unverified · 05657319f92544ce
  2. create_conv2d helper · level 0 · unverified · afb4d58768af3f8f
  3. drop_path helper · level 1 · ran; the contract check could not run · 39eace7e2822504f
  4. make_divisible helper · level 1 · ran · honoured contract · 24400bc088ed228d
  5. CondConv2d helper · level 1 · ran · eb9c56ce6ebabe0e
  6. MixedConv2d helper · level 1 · ran · 8e8ca221bdc062f3
  7. create_conv2d_pad helper · level 1 · ran · our draft was wrong · 9ad464c2bfb49b0f
  8. conv2d_same helper · level 1 · ran · our draft was wrong · 61bb8dbefa4ed19a
  9. get_condconv_initializer helper · level 1 · ran · our draft was wrong · 816ebe82b6b6275f
  10. get_padding_value helper · level 1 · ran · honoured contract · 5993ba1d4c4de0b5
  11. _split_channels helper · level 1 · ran · honoured contract · f28e60bc5be022ce
  12. Conv2dSame helper · level 1 · ran · 5ce1979636036635
  13. pad_same helper · level 1 · ran · our draft was wrong · 3035cd0e2de9e8a4
  14. get_padding helper · level 1 · ran · honoured contract · 73876e077d3acdf5
  15. is_static_pad helper · level 1 · ran · violated contract · ffb95d7b0bd531e5
  16. get_same_padding helper · level 1 · ran · honoured contract · 54e11386110ff042
  17. _ntuple helper · level 1 · ran · our draft was wrong · 553ee0765abad219

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2206.00843") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Pruning

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