Papers › Pruning Filters for Efficient ConvNets
Pruning Filters for Efficient ConvNets
Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet, Hans Peter Graf
The success of CNNs in various applications is accompanied by a significant increase in the computation and parameter storage costs. Recent efforts toward reducing these overheads involve pruning and compressing the weights of various layers without hurting original accuracy. However, magnitude-based pruning of weights reduces a significant number of parameters from the fully connected layers and may not adequately reduce the computation costs in the convolutional layers due to irregular sparsity in the pruned networks. We present an acceleration method for CNNs, where we prune filters from CNNs that are identified as having a small effect on the output accuracy. By removing whole filters in the network together with their connecting feature maps, the computation costs are reduced significantly. In contrast to pruning weights, this approach does not result in sparse connectivity patterns. Hence, it does not need the support of sparse convolution libraries and can work with existing efficient BLAS libraries for dense matrix multiplications. We show that even simple filter pruning techniques can reduce inference costs for VGG-16 by up to 34% and ResNet-110 by up to 38% on CIFAR10 while regaining close to the original accuracy by retraining the networks.
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):
get_harvested_code_for_paper(arxiv_id="1608.08710")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1608.08710", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1608.08710")
Code
Syntology 36 code samples harvested from 11 repositories linked to this paper: 23 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 14 where Syntology's instrument failed) · 13 unverified. Where Syntology's instrument failed: 11 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: community (archive-listed): 36 samples from 11 repositories, 23 ran (9 with no instrument failure; 14 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.
No sample is linked to this paper from 4 of its repositories that Syntology harvested for other papers:
- Adlik/model_optimizer, community (archive-listed): harvested for another paper, listed under the repository
- VainF/Torch-Pruning, community (archive-listed): harvested for another paper, listed under the repository
- lehduong/kesi, community (archive-listed): harvested for another paper, listed under the repository
- PaddlePaddle/PaddleOCR, community (archive-listed): harvested for another paper, listed under the repository
Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 23 samples that ran has no recorded date.
21 repositories listed; official and paper-mentioned ones first.
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.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
36 samples harvested: 23 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 14 where Syntology's instrument failed) · 13 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.
Licence: 22 of the 36 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 11 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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 1 sample 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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
7b447ef653b6fd6a · report
fixture: signature a:list/1/int · returned tuple · level recorded 2026-09-22 2af2848312c7f731 · report
fixture: signature model:callable/0/?, pruning_perc:float/0/float · returned list · level recorded 2026-09-22 05588a795fc38ffd · report
fixture: signature model:callable/0/?, masks:list/1/ndarray · returned list · level recorded 2026-09-22 ef13bc5f154a40bc · report
fixture: signature model:callable/0/?, verbose:bool/0/bool · returned float64 · level recorded 2026-09-22 152f217a1bf86018 · report
fixture: signature weight_matrix:Tensor/2/float, prune_num:int/0/int, residue:Tensor/2/float, independentflag:bool/0/bool · returned list · level recorded 2026-09-22 b2d26cb03ffebe9d · report
fixture: returned Conv2d · level recorded 2026-09-22 e4917253b4ffc6a8 · report
fixture: returned Linear · level recorded 2026-09-22 6f17e5800058ad1a · report
fixture: returned BatchNorm2d · level recorded 2026-09-22 769b77d02a742c60 · report
fixture: returned tuple · level recorded 2026-09-22 41598b11a124fdd7 · report
fixture: signature filter_num:int/0/int, gradient:ndarray/4/float, std_times:float/0/float · returned list · level recorded 2026-09-22 05b9fa9dad6ede01 · report
fixture: returned Mask · level recorded 2026-09-22 census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket imagenet/weight-level/main_finetune.py ran MIT (permissive) ·
80752954f2a868b8 · report
fixture: signature output:Tensor/2/float, target:Tensor/1/int, topk:tuple/1/int · returned list · level recorded 2026-09-25 fac5364e2f53c6db · report
fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded 7835366b1d8d0c63 · report
fixture: signature layer:callable/0/?, num_keep:int/0/int · returned Tensor · level recorded 2026-09-25 89d6cfa68bf25631 · report
fixture: signature model:callable/0/? · returned Tensor · level recorded 2026-09-25 census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket imagenet/l1-norm-pruning/ensemble_finetune.py unverified MIT (permissive) here; the stored copy is pointer only ·
4d3faaaa1c706b0b · report
15487f2b7b36c9cc · report
1dcc89e293ab6570 · report
61e4d0bc645ebb64 · report
5d815bc1bdb41c80 · report
fixture: returned Pruner · level recorded 2026-09-22 b5096faa1be476c7 · report
a391dad107f2f625 · report
fixture: returned Tensor · level recorded 2026-09-22 841ab10a9e621c3e · report
eb229809230a2c98 · report
8dbc5200982548c5 · report
fbb0ce8d88ebc264 · report
fixture: returned Tensor · level recorded 2026-09-22 d02925cbefd3694f · report
fixture: signature model:callable/0/?, pruning_perc:int/0/int, min_conv_id:int/0/int, max_conv_id:int/0/int, verbose:int/0/int · returned list · level recorded 2026-09-22 0a177233e25de4aa · report
fixture: signature layer:Tensor/2/float · returned float · level recorded 2026-09-22 73a3fe3ae770b450 · report
fixture: returned pruned_conv2d · level recorded 2026-09-22 f21b8549dee8b153 · report
fixture: signature model:callable/0/? · returned ModuleList · level recorded 2026-09-22 be78e984674fdadb · report
fixture: returned zero_padding · level recorded 2026-09-22 ee1b9c63cd1f32ce · 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.
10 assemblies on this paper: 10 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
10 sibling assemblies for filter pruning (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for filter pruning (graph method: filter pruning). 4 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 10 siblings
- filter_prune entry · level 1 · ran · our draft was wrong ·
2af2848312c7f731 - prune_one_filter helper · level 1 · ran · our draft was wrong ·
05588a795fc38ffd - prune_rate helper · level 1 · ran · honoured contract ·
ef13bc5f154a40bc - arg_nonzero_min helper · level 1 · ran; the contract check could not run (RAISES) ·
7b447ef653b6fd6a
harvested Assembly for filter pruning (graph method: filter pruning). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 10 siblings
- obtain_bn_mask entry · level 1 · ran; the contract check could not run (RAISES) ·
fbb0ce8d88ebc264
harvested Assembly for filter pruning (graph method: filter pruning). 8 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.
one of 10 siblings
- prune_net entry · level 0 · unverified ·
85de63fef209d807 - prune_resnet model · level 0 · unverified ·
85dea7b7b4ee357b - prune_vgg model · level 0 · unverified ·
fd290760eb0c67b9 - channels_index helper · level 1 · ran · our draft was wrong ·
152f217a1bf86018 - get_new_conv helper · level 1 · ran; the contract check could not run (RAISES) ·
b2d26cb03ffebe9d - get_new_linear helper · level 1 · ran · our draft was wrong ·
e4917253b4ffc6a8 - get_new_norm helper · level 1 · ran · our draft was wrong ·
6f17e5800058ad1a - select_channels helper · level 1 · ran · our draft was wrong ·
769b77d02a742c60
harvested Assembly for filter pruning (graph method: filter pruning). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 10 siblings
- Mask entry · level 1 · ran ·
05b9fa9dad6ede01
harvested Assembly for filter pruning (graph method: filter pruning). 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 10 siblings
- Pruner entry · level 1 · ran ·
5d815bc1bdb41c80 - OptimizerPruner helper · level 0 · unverified ·
b5096faa1be476c7
harvested Assembly for filter pruning (graph method: filter pruning). 6 bricks; individually on a fixture: 4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.
one of 10 siblings
- prune_model entry · level 0 · unverified ·
3adf7e9d6eff8e41 - count_model_param_flops helper · level 0 · unverified ·
ee1b9c63cd1f32ce - layer_eval helper · level 1 · ran · our draft was wrong ·
0a177233e25de4aa - pruned_conv2d helper · level 1 · ran ·
73a3fe3ae770b450 - unwrap_model helper · level 1 · ran · our draft was wrong ·
f21b8549dee8b153 - zero_padding helper · level 1 · ran ·
be78e984674fdadb
harvested Assembly for filter pruning (graph method: filter pruning). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 10 siblings
- get_filtered_idx entry · level 1 · ran · violated contract ·
41598b11a124fdd7
harvested Assembly for filter pruning (graph method: filter pruning). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 10 siblings
- quick_filter_prune_v2 entry · level 1 · ran · our draft was wrong ·
d02925cbefd3694f
harvested Assembly for filter pruning (graph method: filter pruning). 4 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 10 siblings
- Pruner entry · level 0 · unverified ·
eb229809230a2c98 - MetaPruner helper · level 0 · unverified ·
841ab10a9e621c3e - _weights_init helper · level 0 · unverified ·
8dbc5200982548c5 - Layer helper · level 1 · ran ·
d54cd5c9b293f300
harvested Assembly for filter pruning (graph method: filter pruning). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 10 siblings
- obtain_bn_mask entry · level 1 · ran · our draft was wrong ·
a391dad107f2f625
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="1608.08710") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Network Pruning | ImageNet | ResNet50-2.3 GFLOPs | Accuracy | 78.79 | #1 of 16 | Archive leaderboard | report |
| Network Pruning | ImageNet | ResNet50-2.3 GFLOPs | GFLOPs | 2.335 | #1 of 16 | Archive leaderboard | report |
| Network Pruning | ImageNet | ResNet50-2.3 GFLOPs | MParams | 14.811 | #1 of 16 | Archive leaderboard | report |
| Network Pruning | ImageNet | ResNet50-1.5 GFLOPs | Accuracy | 78.07 | #2 of 16 | Archive leaderboard | report |
| Network Pruning | ImageNet | ResNet50-1.5 GFLOPs | GFLOPs | 1.635 | #2 of 16 | Archive leaderboard | report |
| Network Pruning | ImageNet | ResNet50-1.5 GFLOPs | MParams | 10.511 | #2 of 16 | Archive leaderboard | report |
| Network Pruning | ImageNet | ResNet50-1G FLOPs | Accuracy | 76.376 | #8 of 16 | Archive leaderboard | report |
| Network Pruning | ImageNet | ResNet50-1G FLOPs | GFLOPs | 1.075 | #8 of 16 | Archive leaderboard | report |
| Network Pruning | ImageNet | ResNet50-1G FLOPs | MParams | 6.954 | #8 of 16 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Introduced by this paper: 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