{"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/dual-patchnorm","title":"Dual PatchNorm","arxiv_id":"2302.01327","date":"2023-02-02","proceeding":null,"authors":["Manoj Kumar","Mostafa Dehghani","Neil Houlsby"],"abstract":"We propose Dual PatchNorm: two Layer Normalization layers (LayerNorms), before and after the patch embedding layer in Vision Transformers. We demonstrate that Dual PatchNorm outperforms the result of exhaustive search for alternative LayerNorm placement strategies in the Transformer block itself. In our experiments, incorporating this trivial modification, often leads to improved accuracy over well-tuned Vision Transformers and never hurts.","url_abs":"https://arxiv.org/abs/2302.01327v3","url_pdf":"https://arxiv.org/pdf/2302.01327v3.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":"dual-patchnorm","repo_url":"https://github.com/google-research/big_vision","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"dual-patchnorm","repo_url":"https://github.com/lucidrains/MEGABYTE-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"dual-patchnorm","repo_url":"https://github.com/lucidrains/denoising-diffusion-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dual-patchnorm","repo_url":"https://github.com/lucidrains/musiclm-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"dual-patchnorm","repo_url":"https://github.com/lucidrains/phenaki-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dual-patchnorm","repo_url":"https://github.com/lucidrains/recurrent-interface-network-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dual-patchnorm","repo_url":"https://github.com/osier0524/lottery-ticket-to-ddpm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.01327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.01327"}},"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/lucidrains/denoising-diffusion-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/big_vision","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lucidrains/musiclm-pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lucidrains/recurrent-interface-network-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lucidrains/phenaki-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lucidrains/MEGABYTE-pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/osier0524/lottery-ticket-to-ddpm","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"ran_violates":3,"ran_draft_wrong":1,"ran":1,"unverified":3},"by_repo_kind":{"listed":{"samples":9,"ran":6,"repositories":2}},"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":"5cfcc1d3230706ff","entry":"cast_tuple","repo":"lucidrains/musiclm-pytorch","repo_kind":"listed","path":"musiclm_pytorch/trainer.py","file_url":"https://github.com/lucidrains/musiclm-pytorch/blob/HEAD/musiclm_pytorch/trainer.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5cfcc1d3230706ff"}},{"code_sha256_prefix":"60fff7c3c400d7ff","entry":"default","repo":"lucidrains/MEGABYTE-pytorch","repo_kind":"listed","path":"MEGABYTE_pytorch/megabyte.py","file_url":"https://github.com/lucidrains/MEGABYTE-pytorch/blob/HEAD/MEGABYTE_pytorch/megabyte.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"60fff7c3c400d7ff"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"lucidrains/MEGABYTE-pytorch","repo_kind":"listed","path":"MEGABYTE_pytorch/attend.py","file_url":"https://github.com/lucidrains/MEGABYTE-pytorch/blob/HEAD/MEGABYTE_pytorch/attend.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"0ff658860f6a6e4f","entry":"first","repo":"lucidrains/musiclm-pytorch","repo_kind":"listed","path":"musiclm_pytorch/musiclm_pytorch.py","file_url":"https://github.com/lucidrains/musiclm-pytorch/blob/HEAD/musiclm_pytorch/musiclm_pytorch.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0ff658860f6a6e4f"}},{"code_sha256_prefix":"52e10a7d6b0fa036","entry":"once","repo":"lucidrains/MEGABYTE-pytorch","repo_kind":"listed","path":"MEGABYTE_pytorch/attend.py","file_url":"https://github.com/lucidrains/MEGABYTE-pytorch/blob/HEAD/MEGABYTE_pytorch/attend.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"52e10a7d6b0fa036"}},{"code_sha256_prefix":"d95562c398a6b25e","entry":"yes_or_no","repo":"lucidrains/musiclm-pytorch","repo_kind":"listed","path":"musiclm_pytorch/trainer.py","file_url":"https://github.com/lucidrains/musiclm-pytorch/blob/HEAD/musiclm_pytorch/trainer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d95562c398a6b25e"}},{"code_sha256_prefix":"444ef2a4a08a512e","entry":"all_gather_same_dim","repo":"lucidrains/musiclm-pytorch","repo_kind":"listed","path":"musiclm_pytorch/distributed.py","file_url":"https://github.com/lucidrains/musiclm-pytorch/blob/HEAD/musiclm_pytorch/distributed.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"444ef2a4a08a512e"}},{"code_sha256_prefix":"68fd08f2f8ed9157","entry":"all_gather_variable_dim","repo":"lucidrains/musiclm-pytorch","repo_kind":"listed","path":"musiclm_pytorch/distributed.py","file_url":"https://github.com/lucidrains/musiclm-pytorch/blob/HEAD/musiclm_pytorch/distributed.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"68fd08f2f8ed9157"}},{"code_sha256_prefix":"6182326691dd827b","entry":"pack_one","repo":"lucidrains/MEGABYTE-pytorch","repo_kind":"listed","path":"MEGABYTE_pytorch/megabyte.py","file_url":"https://github.com/lucidrains/MEGABYTE-pytorch/blob/HEAD/MEGABYTE_pytorch/megabyte.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6182326691dd827b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}