{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/squeezenext-hardware-aware-neural-network","title":"SqueezeNext: Hardware-Aware Neural Network Design","arxiv_id":"1803.10615","date":"2018-03-23","proceeding":null,"authors":["Amir Gholami","Kiseok Kwon","Bichen Wu","Zizheng Tai","Xiangyu Yue","Peter Jin","Sicheng Zhao","Kurt Keutzer"],"abstract":"One of the main barriers for deploying neural networks on embedded systems\nhas been large memory and power consumption of existing neural networks. In\nthis work, we introduce SqueezeNext, a new family of neural network\narchitectures whose design was guided by considering previous architectures\nsuch as SqueezeNet, as well as by simulation results on a neural network\naccelerator. This new network is able to match AlexNet's accuracy on the\nImageNet benchmark with $112\\times$ fewer parameters, and one of its deeper\nvariants is able to achieve VGG-19 accuracy with only 4.4 Million parameters,\n($31\\times$ smaller than VGG-19). SqueezeNext also achieves better top-5\nclassification accuracy with $1.3\\times$ fewer parameters as compared to\nMobileNet, but avoids using depthwise-separable convolutions that are\ninefficient on some mobile processor platforms. This wide range of accuracy\ngives the user the ability to make speed-accuracy tradeoffs, depending on the\navailable resources on the target hardware. Using hardware simulation results\nfor power and inference speed on an embedded system has guided us to design\nvariations of the baseline model that are $2.59\\times$/$8.26\\times$ faster and\n$2.25\\times$/$7.5\\times$ more energy efficient as compared to\nSqueezeNet/AlexNet without any accuracy degradation.","url_abs":"http://arxiv.org/abs/1803.10615v2","url_pdf":"http://arxiv.org/pdf/1803.10615v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"squeezenext-hardware-aware-neural-network","repo_url":"https://github.com/amirgholami/SqueezeNext","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"squeezenext-hardware-aware-neural-network","repo_url":"https://github.com/Timen/squeezenext-tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"squeezenext-hardware-aware-neural-network","repo_url":"https://github.com/luuuyi/SqueezeNext.PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"squeezenext-hardware-aware-neural-network","repo_url":"https://github.com/osmr/imgclsmob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"squeezenext-hardware-aware-neural-network","repo_url":"https://github.com/2023-MindSpore-1/ms-code-217/tree/main/squeezenet1_1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"squeezenext-hardware-aware-neural-network","repo_url":"https://github.com/2023-MindSpore-4/Code11/tree/main/squeezenet1_1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"squeezenext-hardware-aware-neural-network","repo_url":"https://github.com/2023-MindSpore-4/Code7/tree/main/squeezenet1_1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"squeezenext-hardware-aware-neural-network","repo_url":"https://gitlab.com/birder/birder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"fire-module","method_name":"Fire Module"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"polynomial-rate-decay","method_name":"Polynomial Rate Decay"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sgd-with-momentum","method_name":"SGD with Momentum"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"spatially-separable-convolution","method_name":"Spatially Separable Convolution"},{"method_slug":"squeezenext","method_name":"SqueezeNeXt"},{"method_slug":"squeezenext-block","method_name":"SqueezeNeXt Block"},{"method_slug":"squeezenet","method_name":"SqueezeNet"},{"method_slug":"vgg-19","method_name":"VGG-19"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"xavier-initialization","method_name":"Xavier Initialization"}],"datasets_introduced":[],"methods_introduced":[{"slug":"squeezenext","name":"SqueezeNeXt","full_name":"SqueezeNeXt"},{"slug":"squeezenext-block","name":"SqueezeNeXt Block","full_name":"SqueezeNeXt Block"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.10615","atlas_url":"https://app.syntology.ai/?focus=1803.10615","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.10615"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/amirgholami/SqueezeNext","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-4/Code11/tree/main/squeezenet1_1","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Timen/squeezenext-tensorflow","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/luuuyi/SqueezeNext.PyTorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-1/ms-code-217/tree/main/squeezenet1_1","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/osmr/imgclsmob","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://gitlab.com/birder/birder","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-4/Code7/tree/main/squeezenet1_1","reach":null}],"summary":{"ran_fixture":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2326566ecfff4fd4","entry":"lookup_human_readable","repo":"Timen/squeezenext-tensorflow","repo_kind":"listed","path":"predict.py","file_url":"https://github.com/Timen/squeezenext-tensorflow/blob/HEAD/predict.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2326566ecfff4fd4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}