{"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/quantization-and-training-of-neural-networks","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","arxiv_id":"1712.05877","date":"2017-12-15","proceeding":"CVPR 2018 6","authors":["Benoit Jacob","Skirmantas Kligys","Bo Chen","Menglong Zhu","Matthew Tang","Andrew Howard","Hartwig Adam","Dmitry Kalenichenko"],"abstract":"The rising popularity of intelligent mobile devices and the daunting\ncomputational cost of deep learning-based models call for efficient and\naccurate on-device inference schemes. We propose a quantization scheme that\nallows inference to be carried out using integer-only arithmetic, which can be\nimplemented more efficiently than floating point inference on commonly\navailable integer-only hardware. We also co-design a training procedure to\npreserve end-to-end model accuracy post quantization. As a result, the proposed\nquantization scheme improves the tradeoff between accuracy and on-device\nlatency. The improvements are significant even on MobileNets, a model family\nknown for run-time efficiency, and are demonstrated in ImageNet classification\nand COCO detection on popular CPUs.","url_abs":"http://arxiv.org/abs/1712.05877v1","url_pdf":"http://arxiv.org/pdf/1712.05877v1.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":"quantization-and-training-of-neural-networks","repo_url":"https://github.com/ArtyZe/yolo_quantization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"quantization-and-training-of-neural-networks","repo_url":"https://github.com/Janus-Shiau/awd-lstm-tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"quantization-and-training-of-neural-networks","repo_url":"https://github.com/MaximIntegratedAI/ai8x-synthesis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"quantization-and-training-of-neural-networks","repo_url":"https://github.com/MaximIntegratedAI/ai8x-training","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"quantization-and-training-of-neural-networks","repo_url":"https://github.com/PhilipPfeffer/haptic_vest","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"quantization-and-training-of-neural-networks","repo_url":"https://github.com/Qengineering/ARMnn_Quantize_RPi_32-bits","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"quantization-and-training-of-neural-networks","repo_url":"https://github.com/Qengineering/TensorFlow_Lite_Classification_Jetson-Nano","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"quantization-and-training-of-neural-networks","repo_url":"https://github.com/Qengineering/TensorFlow_Lite_Classification_RPi_32-bits","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"quantization-and-training-of-neural-networks","repo_url":"https://github.com/Qengineering/TensorFlow_Lite_Classification_RPi_64-bits","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"quantization-and-training-of-neural-networks","repo_url":"https://github.com/Qengineering/TensorFlow_Lite_Classification_RPi_zero","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"quantization-and-training-of-neural-networks","repo_url":"https://github.com/Qengineering/TensorFlow_Lite_RPi_32-bits","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"quantization-and-training-of-neural-networks","repo_url":"https://github.com/Qengineering/TensorFlow_Lite_RPi_64-bits","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"quantization-and-training-of-neural-networks","repo_url":"https://github.com/analogdevicesinc/ai8x-training","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"quantization-and-training-of-neural-networks","repo_url":"https://github.com/geffencooper/ai8x-synthesis_ECE196","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"quantization-and-training-of-neural-networks","repo_url":"https://github.com/hey-yahei/Quantization.MXNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"unanswered"}},{"paper_slug":"quantization-and-training-of-neural-networks","repo_url":"https://github.com/hey-yahei/RT_Quantization.MXNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"unanswered"}},{"paper_slug":"quantization-and-training-of-neural-networks","repo_url":"https://github.com/jameszampa/ECE-570-Implementation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"quantization-and-training-of-neural-networks","repo_url":"https://github.com/jameszampa/VIP-SoCET-Benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"quantization-and-training-of-neural-networks","repo_url":"https://github.com/linyang-zhh/FQ-ViT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"quantization-and-training-of-neural-networks","repo_url":"https://github.com/tensorflow/models/tree/master/research/seq_flow_lite","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"quantization-and-training-of-neural-networks","repo_url":"https://github.com/tensorflow/models/tree/master/research/sequence_projection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1712.05877","atlas_url":"https://app.syntology.ai/?focus=1712.05877","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.05877"}},"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/MaximIntegratedAI/ai8x-synthesis","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jameszampa/ECE-570-Implementation","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ArtyZe/yolo_quantization","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hey-yahei/Quantization.MXNet","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Qengineering/TensorFlow_Lite_Classification_Jetson-Nano","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jameszampa/VIP-SoCET-Benchmark","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/linyang-zhh/FQ-ViT","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/analogdevicesinc/ai8x-training","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PhilipPfeffer/haptic_vest","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Qengineering/TensorFlow_Lite_RPi_64-bits","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Janus-Shiau/awd-lstm-tensorflow","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Qengineering/ARMnn_Quantize_RPi_32-bits","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Qengineering/TensorFlow_Lite_Classification_RPi_32-bits","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Qengineering/TensorFlow_Lite_Classification_RPi_zero","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tensorflow/models/tree/master/research/sequence_projection","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/geffencooper/ai8x-synthesis_ECE196","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Qengineering/TensorFlow_Lite_RPi_32-bits","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tensorflow/models/tree/master/research/seq_flow_lite","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hey-yahei/RT_Quantization.MXNet","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Qengineering/TensorFlow_Lite_Classification_RPi_64-bits","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MaximIntegratedAI/ai8x-training","reach":null}],"summary":{"ran":3,"ran_draft_wrong":1,"ran_honours":3},"by_repo_kind":{"listed":{"samples":7,"ran":7,"repositories":3}},"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":4,"samples":[{"code_sha256_prefix":"6c8c5613a41846a2","entry":"BaseQuantizer","repo":"linyang-zhh/FQ-ViT","repo_kind":"listed","path":"models/ptq/quantizer/uniform.py","file_url":"https://github.com/linyang-zhh/FQ-ViT/blob/HEAD/models/ptq/quantizer/uniform.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6c8c5613a41846a2"}},{"code_sha256_prefix":"40771743ce834305","entry":"FullyConnected","repo":"jameszampa/ECE-570-Implementation","repo_kind":"listed","path":"python/integer_inference.py","file_url":"https://github.com/jameszampa/ECE-570-Implementation/blob/HEAD/python/integer_inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"40771743ce834305"}},{"code_sha256_prefix":"9c24f357578474e5","entry":"MultiplyByQuantizedMultiplierSmallerThanOne","repo":"jameszampa/ECE-570-Implementation","repo_kind":"listed","path":"python/integer_inference.py","file_url":"https://github.com/jameszampa/ECE-570-Implementation/blob/HEAD/python/integer_inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9c24f357578474e5"}},{"code_sha256_prefix":"fbe27ee7dc10aa67","entry":"QuantizationFunction","repo":"MaximIntegratedAI/ai8x-training","repo_kind":"listed","path":"ai8x.py","file_url":"https://github.com/MaximIntegratedAI/ai8x-training/blob/HEAD/ai8x.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fbe27ee7dc10aa67"}},{"code_sha256_prefix":"f80d39ab0932d302","entry":"RoundingDivideByPOT","repo":"jameszampa/ECE-570-Implementation","repo_kind":"listed","path":"python/integer_inference.py","file_url":"https://github.com/jameszampa/ECE-570-Implementation/blob/HEAD/python/integer_inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f80d39ab0932d302"}},{"code_sha256_prefix":"98ec162d7259fc3b","entry":"SaturatingRoundingDoublingHighMul","repo":"jameszampa/ECE-570-Implementation","repo_kind":"listed","path":"python/integer_inference.py","file_url":"https://github.com/jameszampa/ECE-570-Implementation/blob/HEAD/python/integer_inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"98ec162d7259fc3b"}},{"code_sha256_prefix":"476098355ebe4558","entry":"UniformQuantizer","repo":"linyang-zhh/FQ-ViT","repo_kind":"listed","path":"models/ptq/quantizer/uniform.py","file_url":"https://github.com/linyang-zhh/FQ-ViT/blob/HEAD/models/ptq/quantizer/uniform.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"476098355ebe4558"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}