{"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/emq-evolving-training-free-proxies-for","title":"EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization","arxiv_id":"2307.10554","date":"2023-07-20","proceeding":"ICCV 2023 1","authors":["Peijie Dong","Lujun Li","Zimian Wei","Xin Niu","Zhiliang Tian","Hengyue Pan"],"abstract":"Mixed-Precision Quantization~(MQ) can achieve a competitive accuracy-complexity trade-off for models. Conventional training-based search methods require time-consuming candidate training to search optimized per-layer bit-width configurations in MQ. Recently, some training-free approaches have presented various MQ proxies and significantly improve search efficiency. However, the correlation between these proxies and quantization accuracy is poorly understood. To address the gap, we first build the MQ-Bench-101, which involves different bit configurations and quantization results. Then, we observe that the existing training-free proxies perform weak correlations on the MQ-Bench-101. To efficiently seek superior proxies, we develop an automatic search of proxies framework for MQ via evolving algorithms. In particular, we devise an elaborate search space involving the existing proxies and perform an evolution search to discover the best correlated MQ proxy. We proposed a diversity-prompting selection strategy and compatibility screening protocol to avoid premature convergence and improve search efficiency. In this way, our Evolving proxies for Mixed-precision Quantization~(EMQ) framework allows the auto-generation of proxies without heavy tuning and expert knowledge. Extensive experiments on ImageNet with various ResNet and MobileNet families demonstrate that our EMQ obtains superior performance than state-of-the-art mixed-precision methods at a significantly reduced cost. The code will be released.","url_abs":"https://arxiv.org/abs/2307.10554v1","url_pdf":"https://arxiv.org/pdf/2307.10554v1.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":"emq-evolving-training-free-proxies-for","repo_url":"https://github.com/lilujunai/emq-series","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"}],"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":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.10554","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.10554"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/lilujunai/emq-series","reach":null}],"summary":{"ran":5,"ran_violates":2,"unverified":12},"by_repo_kind":{"official":{"samples":19,"ran":7,"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":"cc18b58d20c93dfd","entry":"BasicBlock","repo":"lilujunai/emq-series","repo_kind":"official","path":"emq/predictor/pruners/measures/qe_score.py","file_url":"https://github.com/lilujunai/emq-series/blob/HEAD/emq/predictor/pruners/measures/qe_score.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":"cc18b58d20c93dfd"}},{"code_sha256_prefix":"df082992e7ba0798","entry":"Bottleneck","repo":"lilujunai/emq-series","repo_kind":"official","path":"emq/predictor/pruners/measures/qe_score.py","file_url":"https://github.com/lilujunai/emq-series/blob/HEAD/emq/predictor/pruners/measures/qe_score.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":"df082992e7ba0798"}},{"code_sha256_prefix":"491ef5b3386ab4b7","entry":"InvertedResidual","repo":"lilujunai/emq-series","repo_kind":"official","path":"emq/predictor/pruners/measures/qe_score.py","file_url":"https://github.com/lilujunai/emq-series/blob/HEAD/emq/predictor/pruners/measures/qe_score.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"491ef5b3386ab4b7"}},{"code_sha256_prefix":"78941fdc9f230be6","entry":"StraightThrough","repo":"lilujunai/emq-series","repo_kind":"official","path":"emq/predictor/pruners/measures/qe_score.py","file_url":"https://github.com/lilujunai/emq-series/blob/HEAD/emq/predictor/pruners/measures/qe_score.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"78941fdc9f230be6"}},{"code_sha256_prefix":"140878966d2be929","entry":"_fold_bn","repo":"lilujunai/emq-series","repo_kind":"official","path":"emq/predictor/pruners/measures/qe_score.py","file_url":"https://github.com/lilujunai/emq-series/blob/HEAD/emq/predictor/pruners/measures/qe_score.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":"140878966d2be929"}},{"code_sha256_prefix":"21b513cf47621143","entry":"is_absorbing","repo":"lilujunai/emq-series","repo_kind":"official","path":"emq/predictor/pruners/measures/qe_score.py","file_url":"https://github.com/lilujunai/emq-series/blob/HEAD/emq/predictor/pruners/measures/qe_score.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"21b513cf47621143"}},{"code_sha256_prefix":"39d986a037856c1d","entry":"is_bn","repo":"lilujunai/emq-series","repo_kind":"official","path":"emq/predictor/pruners/measures/qe_score.py","file_url":"https://github.com/lilujunai/emq-series/blob/HEAD/emq/predictor/pruners/measures/qe_score.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"39d986a037856c1d"}},{"code_sha256_prefix":"819d5ef809058894","entry":"BaseQuantBlock","repo":"lilujunai/emq-series","repo_kind":"official","path":"emq/predictor/pruners/measures/qe_score.py","file_url":"https://github.com/lilujunai/emq-series/blob/HEAD/emq/predictor/pruners/measures/qe_score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"819d5ef809058894"}},{"code_sha256_prefix":"2028d48de55aba38","entry":"ComputeMadnasScore","repo":"lilujunai/emq-series","repo_kind":"official","path":"emq/predictor/pruners/measures/qe_score.py","file_url":"https://github.com/lilujunai/emq-series/blob/HEAD/emq/predictor/pruners/measures/qe_score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2028d48de55aba38"}},{"code_sha256_prefix":"affd5495e8ec4d0e","entry":"QuantBasicBlock","repo":"lilujunai/emq-series","repo_kind":"official","path":"emq/predictor/pruners/measures/qe_score.py","file_url":"https://github.com/lilujunai/emq-series/blob/HEAD/emq/predictor/pruners/measures/qe_score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"affd5495e8ec4d0e"}},{"code_sha256_prefix":"88f5b8c6e343729d","entry":"QuantBottleneck","repo":"lilujunai/emq-series","repo_kind":"official","path":"emq/predictor/pruners/measures/qe_score.py","file_url":"https://github.com/lilujunai/emq-series/blob/HEAD/emq/predictor/pruners/measures/qe_score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"88f5b8c6e343729d"}},{"code_sha256_prefix":"47fc8538a2628e4c","entry":"QuantInvertedResidual","repo":"lilujunai/emq-series","repo_kind":"official","path":"emq/predictor/pruners/measures/qe_score.py","file_url":"https://github.com/lilujunai/emq-series/blob/HEAD/emq/predictor/pruners/measures/qe_score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"47fc8538a2628e4c"}},{"code_sha256_prefix":"4895c833da6c7c80","entry":"QuantModel","repo":"lilujunai/emq-series","repo_kind":"official","path":"emq/predictor/pruners/measures/qe_score.py","file_url":"https://github.com/lilujunai/emq-series/blob/HEAD/emq/predictor/pruners/measures/qe_score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4895c833da6c7c80"}},{"code_sha256_prefix":"0d7bbdf53ee6e6db","entry":"QuantModule","repo":"lilujunai/emq-series","repo_kind":"official","path":"emq/predictor/pruners/measures/qe_score.py","file_url":"https://github.com/lilujunai/emq-series/blob/HEAD/emq/predictor/pruners/measures/qe_score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0d7bbdf53ee6e6db"}},{"code_sha256_prefix":"d4a79d5ee2cd4666","entry":"UniformAffineQuantizer","repo":"lilujunai/emq-series","repo_kind":"official","path":"emq/predictor/pruners/measures/qe_score.py","file_url":"https://github.com/lilujunai/emq-series/blob/HEAD/emq/predictor/pruners/measures/qe_score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d4a79d5ee2cd4666"}},{"code_sha256_prefix":"ac0703e88e81917a","entry":"compute_qe_score","repo":"lilujunai/emq-series","repo_kind":"official","path":"emq/predictor/pruners/measures/qe_score.py","file_url":"https://github.com/lilujunai/emq-series/blob/HEAD/emq/predictor/pruners/measures/qe_score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ac0703e88e81917a"}},{"code_sha256_prefix":"ced4515523449616","entry":"convert_qnn","repo":"lilujunai/emq-series","repo_kind":"official","path":"emq/predictor/pruners/measures/qe_score.py","file_url":"https://github.com/lilujunai/emq-series/blob/HEAD/emq/predictor/pruners/measures/qe_score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ced4515523449616"}},{"code_sha256_prefix":"529664956b8dab9a","entry":"fold_bn_into_conv","repo":"lilujunai/emq-series","repo_kind":"official","path":"emq/predictor/pruners/measures/qe_score.py","file_url":"https://github.com/lilujunai/emq-series/blob/HEAD/emq/predictor/pruners/measures/qe_score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"529664956b8dab9a"}},{"code_sha256_prefix":"de6383d946b71e09","entry":"search_fold_and_remove_bn","repo":"lilujunai/emq-series","repo_kind":"official","path":"emq/predictor/pruners/measures/qe_score.py","file_url":"https://github.com/lilujunai/emq-series/blob/HEAD/emq/predictor/pruners/measures/qe_score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"de6383d946b71e09"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}