SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1602.07360 · 2016

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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 0 have no contract verdict; 4 failures of our instrument; 0 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/1602.07360.json · badge: /api/ran/1602.07360.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
adeely9/experiment_2_python3 reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
jiweibo/imagenet reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
fire_layer Ran
ran; our contract draft was wrong, not the code
adeely9/experiment_2_python3/model.py
pointer only (licence: NONE) · get_code("8791c0396e418bc7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, adeely9/experiment_2_python3 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

squeezenet Ran
ran; our contract draft was wrong, not the code
adeely9/experiment_2_python3/model.py
pointer only (licence: NONE) · get_code("988c8db2810e24f8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, adeely9/experiment_2_python3 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

squeezenet1_0 Ran
ran; our contract draft was wrong, not the code
jiweibo/imagenet/models/squeezenet.py
code served (permissive licence) · get_code("fcda65eed65cff5d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned SqueezeNet. 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
import os

torch.manual_seed(0)

# The function squeezenet1_0 has two parameters:
# 1. pretrained (bool) - whether to load pretrained weights
# 2. **kwargs - additional keyword arguments passed to SqueezeNet constructor

# Since pretrained=True would try to load a file from disk (which we want to avoid),
# we set it to False
# kwargs can be empty or contain parameters like num_classes

ARGS = {
    'pretrained': False,
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SqueezeNet — a SqueezeNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SqueezeNet 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
squeezenet1_1 Ran
ran; our contract draft was wrong, not the code
jiweibo/imagenet/models/squeezenet.py
code served (permissive licence) · get_code("44349b0fe759e3a9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned SqueezeNet. 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 os

torch.manual_seed(0)

# The function squeezenet1_1 has two parameters:
# 1. pretrained (bool, default=False)
# 2. **kwargs (additional keyword arguments passed to SqueezeNet constructor)

# Since pretrained=True would try to load a file from disk (which we want to avoid),
# we set it to False. The **kwargs can be empty or contain parameters like num_classes.

ARGS = {
    'pretrained': False,
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SqueezeNet — a SqueezeNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SqueezeNet 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

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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

More are linked than shown here.

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

Abstract

Recent research on deep neural networks has focused primarily on improving accuracy. For a given accuracy level, it is typically possible to identify multiple DNN architectures that achieve that accuracy level. With equivalent accuracy, smaller DNN architectures offer at least three advantages: (1) Smaller DNNs require less communication across servers during distributed training. (2) Smaller DNNs require less bandwidth to export a new model from the cloud to an autonomous car. (3) Smaller DNNs are more feasible to deploy on FPGAs and other hardware with limited memory. To provide all of these advantages, we propose a small DNN architecture called SqueezeNet. SqueezeNet achieves AlexNet-level accuracy on ImageNet with 50x fewer parameters. Additionally, with model compression techniques we are able to compress SqueezeNet to less than 0.5MB (510x smaller than AlexNet). The SqueezeNet architecture is available for download here: https://github.com/DeepScale/SqueezeNet

For agents

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

get_harvested_code_for_paper("1602.07360")
get_code_for_paper("1602.07360")
have("1602.07360")

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

curl https://syntology.ai/api/ran/1602.07360.json

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

[![Syntology run record](https://syntology.ai/api/ran/1602.07360.svg)](https://syntology.ai/paper/1602.07360)

Connect an agent — have() is free.