SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1608.03665 · 2016

Learning Structured Sparsity in Deep Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

3 of 14 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 failures of our instrument; 11 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1608.03665.json · badge: /api/ran/1608.03665.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
ZJCV/SSL community (classifier label)
classifier basis not recorded on the link
3 ran · 11 no recorded run
FunctionStatusWhere it lives
create_batchnorm2d Ran
ran on a synthesized input
ZJCV/SSL/sslearning/prune/layers.py
code served (permissive licence) · get_code("587ea2d9b6e9d61d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned BatchNorm2d. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create an old BatchNorm2d instance with specific eps and momentum
old_batchnorm2d = nn.BatchNorm2d(
    num_features=3,
    eps=1e-5,
    momentum=0.1
)

# Define in_channels
in_channels = 5

ARGS = {
    "old_batchnorm2d": old_batchnorm2d,
    "in_channels": in_channels
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type BatchNorm2d — a BatchNorm2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a BatchNorm2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
create_conv2d Ran
ran on a synthesized input
ZJCV/SSL/sslearning/prune/layers.py
code served (permissive licence) · get_code("a21ac6077cf08c3f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Conv2d. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a sample Conv2d layer to use as old_conv2d
old_conv2d = nn.Conv2d(
    in_channels=3,
    out_channels=16,
    kernel_size=3,
    stride=1,
    padding=1,
    padding_mode='zeros',
    groups=1,
    dilation=1,
    bias=True
)

ARGS = {
    'old_conv2d': old_conv2d,
    'in_channels': 4,
    'out_filters': 32,
    'old_groups': None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
create_linear Ran
ran on a synthesized input
ZJCV/SSL/sslearning/prune/layers.py
code served (permissive licence) · get_code("b5f7cd56c2cc63e5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create an old_linear nn.Linear module with specific dimensions
# in_features=5, out_features=3, with bias
old_linear = nn.Linear(in_features=5, out_features=3, bias=True)

# Create in_channels parameter (distinct from old_linear's dimensions)
in_channels = 4

ARGS = {
    "old_linear": old_linear,
    "in_channels": in_channels,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
compute_mask Not yet run
unverified (harvested, no recorded run)
ZJCV/SSL/sslearning/prune/prune_vggnet_by_filter_and_channel.py
code served (permissive licence) · get_code("7161254df5577f1d")
How it ran

no invocation recorded.

computer_bottleneck_weight Not yet run
unverified (harvested, no recorded run)
ZJCV/SSL/sslearning/prune/prune_resnet_by_depth.py
code served (permissive licence) · get_code("6f0c98250fa6667e")
How it ran

no invocation recorded.

computer_out_idx Not yet run
unverified (harvested, no recorded run)
ZJCV/SSL/sslearning/prune/prune_vggnet_by_filter_and_channel.py
code served (permissive licence) · get_code("71b67a4093fd6e16")
How it ran

no invocation recorded.

prune Not yet run
unverified (harvested, no recorded run)
ZJCV/SSL/sslearning/prune/prune_resnet_by_depth.py
code served (permissive licence) · get_code("d8ae353c6503316a")
How it ran

no invocation recorded.

prune_bottleneck Not yet run
unverified (harvested, no recorded run)
ZJCV/SSL/sslearning/prune/prune_resnet_by_depth.py
code served (permissive licence) · get_code("8400f740e15a35f2")
How it ran

no invocation recorded.

prune_classifier Not yet run
unverified (harvested, no recorded run)
ZJCV/SSL/sslearning/prune/prune_vggnet_by_filter.py
code served (permissive licence) · get_code("549292cb3c24a501")
How it ran

no invocation recorded.

prune_conv_bn_relu Not yet run
unverified (harvested, no recorded run)
ZJCV/SSL/sslearning/prune/prune_vggnet_by_channel.py
code served (permissive licence) · get_code("eeea4d1c97d32bc2")
How it ran

no invocation recorded.

prune_conv_bn_relu Not yet run
unverified (harvested, no recorded run)
ZJCV/SSL/sslearning/prune/prune_vggnet_by_filter.py
code served (permissive licence) · get_code("3b1a7ef75bcdd7fd")
How it ran

no invocation recorded.

prune_conv_bn_relu Not yet run
unverified (harvested, no recorded run)
ZJCV/SSL/sslearning/prune/prune_vggnet_by_filter_and_channel.py
code served (permissive licence) · get_code("9936b8b0a479ae6f")
How it ran

no invocation recorded.

prune_features Not yet run
unverified (harvested, no recorded run)
ZJCV/SSL/sslearning/prune/prune_vggnet_by_channel.py
code served (permissive licence) · get_code("af5704b466281ae7")
How it ran

no invocation recorded.

prune_features Not yet run
unverified (harvested, no recorded run)
ZJCV/SSL/sslearning/prune/prune_vggnet_by_filter.py
code served (permissive licence) · get_code("ac785d648e672e56")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 14 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

High demand for computation resources severely hinders deployment of large-scale Deep Neural Networks (DNN) in resource constrained devices. In this work, we propose a Structured Sparsity Learning (SSL) method to regularize the structures (i.e., filters, channels, filter shapes, and layer depth) of DNNs. SSL can: (1) learn a compact structure from a bigger DNN to reduce computation cost; (2) obtain a hardware-friendly structured sparsity of DNN to efficiently accelerate the DNNs evaluation. Experimental results show that SSL achieves on average 5.1x and 3.1x speedups of convolutional layer computation of AlexNet against CPU and GPU, respectively, with off-the-shelf libraries. These speedups are about twice speedups of non-structured sparsity; (3) regularize the DNN structure to improve classification accuracy. The results show that for CIFAR-10, regularization on layer depth can reduce 20 layers of a Deep Residual Network (ResNet) to 18 layers while improve the accuracy from 91.25% to 92.60%, which is still slightly higher than that of original ResNet with 32 layers. For AlexNet, structure regularization by SSL also reduces the error by around ~1%. Open source code is in https://github.com/wenwei202/caffe/tree/scnn

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1608.03665")
get_code_for_paper("1608.03665")
have("1608.03665")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1608.03665.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1608.03665.svg)](https://syntology.ai/paper/1608.03665)

Connect an agent — have() is free.