{"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/sharpness-aware-minimization-for-efficiently-1","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","arxiv_id":"2010.01412","date":"2020-10-03","proceeding":"ICLR 2021 1","authors":["Pierre Foret","Ariel Kleiner","Hossein Mobahi","Behnam Neyshabur"],"abstract":"In today's heavily overparameterized models, the value of the training loss provides few guarantees on model generalization ability. Indeed, optimizing only the training loss value, as is commonly done, can easily lead to suboptimal model quality. Motivated by prior work connecting the geometry of the loss landscape and generalization, we introduce a novel, effective procedure for instead simultaneously minimizing loss value and loss sharpness. In particular, our procedure, Sharpness-Aware Minimization (SAM), seeks parameters that lie in neighborhoods having uniformly low loss; this formulation results in a min-max optimization problem on which gradient descent can be performed efficiently. We present empirical results showing that SAM improves model generalization across a variety of benchmark datasets (e.g., CIFAR-10, CIFAR-100, ImageNet, finetuning tasks) and models, yielding novel state-of-the-art performance for several. Additionally, we find that SAM natively provides robustness to label noise on par with that provided by state-of-the-art procedures that specifically target learning with noisy labels. We open source our code at \\url{https://github.com/google-research/sam}.","url_abs":"https://arxiv.org/abs/2010.01412v3","url_pdf":"https://arxiv.org/pdf/2010.01412v3.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":"sharpness-aware-minimization-for-efficiently-1","repo_url":"https://github.com/google-research/sam","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"sharpness-aware-minimization-for-efficiently-1","repo_url":"https://github.com/Ashay-20/TF-SAM-Sharpness-Aware-Minimization-Implementation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"sharpness-aware-minimization-for-efficiently-1","repo_url":"https://github.com/Jannoshh/simple-sam","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"sharpness-aware-minimization-for-efficiently-1","repo_url":"https://github.com/Janus-Shiau/SAM-tf2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"sharpness-aware-minimization-for-efficiently-1","repo_url":"https://github.com/NiMlr/pynlqn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"sharpness-aware-minimization-for-efficiently-1","repo_url":"https://github.com/Yuheon/Sharp-Aware-Minimization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"sharpness-aware-minimization-for-efficiently-1","repo_url":"https://github.com/borealisai/perturbed-forgetting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"sharpness-aware-minimization-for-efficiently-1","repo_url":"https://github.com/davda54/sam","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"sharpness-aware-minimization-for-efficiently-1","repo_url":"https://github.com/denizyuret/playground","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"sharpness-aware-minimization-for-efficiently-1","repo_url":"https://github.com/mhassann22/GCSAM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"sharpness-aware-minimization-for-efficiently-1","repo_url":"https://github.com/moskomule/sam.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"sharpness-aware-minimization-for-efficiently-1","repo_url":"https://github.com/rollovd/LookSAM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"sharpness-aware-minimization-for-efficiently-1","repo_url":"https://github.com/sayakpaul/Sharpness-Aware-Minimization-TensorFlow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"sharpness-aware-minimization-for-efficiently-1","repo_url":"https://github.com/simon20010923/DDAMFN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"sharpness-aware-minimization-for-efficiently-1","repo_url":"https://github.com/MindCode-4/code-13/tree/main/Scalable-Sharpness-Aware-Minimization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"sharpness-aware-minimization-for-efficiently-1","repo_url":"https://github.com/wangermeng2021/FastClassification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"sharpness-aware-minimization-for-efficiently-1","repo_url":"https://github.com/wangermeng2021/Scaled-YOLOv4-tensorflow2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"sharpness-aware-minimization-for-efficiently-1","repo_url":"https://github.com/ys-zong/medfair","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"learning-with-noisy-labels","task_name":"Learning with noisy labels"}],"methods":[{"method_slug":"sharpness-aware-minimization","method_name":"Sharpness-Aware Minimization"}],"datasets_introduced":[],"methods_introduced":[{"slug":"sharpness-aware-minimization","name":"Sharpness-Aware Minimization","full_name":"Sharpness-Aware Minimization"}],"results":[{"leaderboard":"/sota/fine-grained-image-classification-on-birdsnap","task":"Fine-Grained Image Classification","dataset":"Birdsnap","model":"EffNet-L2 (SAM)","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"90.07%"},"uses_additional_data":true},{"leaderboard":"/sota/fine-grained-image-classification-on-fgvc","task":"Fine-Grained Image Classification","dataset":"FGVC Aircraft","model":"EffNet-L2 (SAM)","rank_in_archive_order":56,"of":57,"metrics":{"Top-1 Error Rate":"4.82"},"uses_additional_data":true},{"leaderboard":"/sota/fine-grained-image-classification-on-food-101","task":"Fine-Grained Image Classification","dataset":"Food-101","model":"EffNet-L2 (SAM)","rank_in_archive_order":2,"of":15,"metrics":{"Accuracy":"96.18"},"uses_additional_data":true},{"leaderboard":"/sota/fine-grained-image-classification-on-oxford-2","task":"Fine-Grained Image Classification","dataset":"Oxford-IIIT Pets","model":"EffNet-L2 (SAM)","rank_in_archive_order":1,"of":19,"metrics":{"Accuracy":"97.10","Top-1 Error Rate":"2.90%"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-stanford","task":"Fine-Grained Image Classification","dataset":"Stanford Cars","model":"EffNet-L2 (SAM)","rank_in_archive_order":8,"of":83,"metrics":{"Accuracy":"95.96%"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"EffNet-L2 (SAM)","rank_in_archive_order":1,"of":211,"metrics":{"Percentage correct":"96.08"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"PyramidNet (SAM)","rank_in_archive_order":27,"of":211,"metrics":{"Percentage correct":"89.7"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"CNN39","rank_in_archive_order":205,"of":211,"metrics":{"Percentage correct":"42.64"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"CNN36","rank_in_archive_order":206,"of":211,"metrics":{"Percentage correct":"36.07"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-flowers-102","task":"Image Classification","dataset":"Flowers-102","model":"EffNet-L2 (SAM)","rank_in_archive_order":6,"of":52,"metrics":{"Accuracy":"99.65%"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"EfficientNet-L2-475 (SAM)","rank_in_archive_order":35,"of":1060,"metrics":{"Number of params":"480M","Top 1 Accuracy":"88.61%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ResNet-152 (SAM)","rank_in_archive_order":621,"of":1060,"metrics":{"Top 1 Accuracy":"81.6%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.01412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.01412"}},"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/davda54/sam","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ys-zong/medfair","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Jannoshh/simple-sam","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rollovd/LookSAM","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/denizyuret/playground","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/moskomule/sam.pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindCode-4/code-13/tree/main/Scalable-Sharpness-Aware-Minimization","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Janus-Shiau/SAM-tf2","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/google-research/sam","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Ashay-20/TF-SAM-Sharpness-Aware-Minimization-Implementation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wangermeng2021/FastClassification","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/simon20010923/DDAMFN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Yuheon/Sharp-Aware-Minimization","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mhassann22/GCSAM","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/NiMlr/pynlqn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sayakpaul/Sharpness-Aware-Minimization-TensorFlow","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/borealisai/perturbed-forgetting","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wangermeng2021/Scaled-YOLOv4-tensorflow2","reach":null}],"summary":{"ran":6,"ran_fixture":1,"ran_draft_wrong":1,"unverified":12},"by_repo_kind":{"official":{"samples":9,"ran":0,"repositories":1},"listed":{"samples":10,"ran":7,"repositories":9}},"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":6,"samples":[{"code_sha256_prefix":"6b43b1c7e8d505da","entry":"AssignLR","repo":"wangermeng2021/Scaled-YOLOv4-tensorflow2","repo_kind":"listed","path":"utils/sam.py","file_url":"https://github.com/wangermeng2021/Scaled-YOLOv4-tensorflow2/blob/HEAD/utils/sam.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":"6b43b1c7e8d505da"}},{"code_sha256_prefix":"f04e7b9eb0136335","entry":"SAM","repo":"simon20010923/DDAMFN","repo_kind":"listed","path":"DDAMFN++/sam.py","file_url":"https://github.com/simon20010923/DDAMFN/blob/HEAD/DDAMFN%2B%2B/sam.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f04e7b9eb0136335"}},{"code_sha256_prefix":"954d13e2c6b31007","entry":"SAM","repo":"Jannoshh/simple-sam","repo_kind":"listed","path":"sam.py","file_url":"https://github.com/Jannoshh/simple-sam/blob/HEAD/sam.py","link_basis":"first_harvest_node","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":"954d13e2c6b31007"}},{"code_sha256_prefix":"dfc916dc5ccaee4e","entry":"SAMOptimizer","repo":"wangermeng2021/Scaled-YOLOv4-tensorflow2","repo_kind":"listed","path":"utils/sam.py","file_url":"https://github.com/wangermeng2021/Scaled-YOLOv4-tensorflow2/blob/HEAD/utils/sam.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":"dfc916dc5ccaee4e"}},{"code_sha256_prefix":"5583e2f7e9e49a0c","entry":"SAMSGD","repo":"moskomule/sam.pytorch","repo_kind":"listed","path":"sam.py","file_url":"https://github.com/moskomule/sam.pytorch/blob/HEAD/sam.py","link_basis":"first_harvest_node","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":"5583e2f7e9e49a0c"}},{"code_sha256_prefix":"46c3f10ab0f4669c","entry":"SAM_optimizer","repo":"ys-zong/medfair","repo_kind":"listed","path":"models/SAM/utils.py","file_url":"https://github.com/ys-zong/medfair/blob/HEAD/models/SAM/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"46c3f10ab0f4669c"}},{"code_sha256_prefix":"27a3d56a09e0e7cf","entry":"centralized_gradient","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"27a3d56a09e0e7cf"}},{"code_sha256_prefix":"23710a8851b7ec81","entry":"sam","repo":"NiMlr/pynlqn","repo_kind":"listed","path":"pynlqn/algorithms.py","file_url":"https://github.com/NiMlr/pynlqn/blob/HEAD/pynlqn/algorithms.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"23710a8851b7ec81"}},{"code_sha256_prefix":"90e63eaa2117ba4e","entry":"GCSAM","repo":"mhassann22/GCSAM","repo_kind":"listed","path":"cifar10_gcsam_resnet50.py","file_url":"https://github.com/mhassann22/GCSAM/blob/HEAD/cifar10_gcsam_resnet50.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"90e63eaa2117ba4e"}},{"code_sha256_prefix":"2debef19d3a36af7","entry":"LookSAM","repo":"rollovd/LookSAM","repo_kind":"listed","path":"looksam.py","file_url":"https://github.com/rollovd/LookSAM/blob/HEAD/looksam.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2debef19d3a36af7"}},{"code_sha256_prefix":"b2eabc22e2ca9282","entry":"SAMWarpper","repo":"Janus-Shiau/SAM-tf2","repo_kind":"listed","path":"lib/optimizers/sam.py","file_url":"https://github.com/Janus-Shiau/SAM-tf2/blob/HEAD/lib/optimizers/sam.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b2eabc22e2ca9282"}},{"code_sha256_prefix":"33f3bcef5a763ff8","entry":"cutout","repo":"google-research/sam","repo_kind":"official","path":"sam_jax/datasets/augmentation.py","file_url":"https://github.com/google-research/sam/blob/HEAD/sam_jax/datasets/augmentation.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":"33f3bcef5a763ff8"}},{"code_sha256_prefix":"be4a2c63cc33ff44","entry":"dense_layer_init_fn","repo":"google-research/sam","repo_kind":"official","path":"sam_jax/models/utils.py","file_url":"https://github.com/google-research/sam/blob/HEAD/sam_jax/models/utils.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":"be4a2c63cc33ff44"}},{"code_sha256_prefix":"cb2821198470712c","entry":"name_to_image_size","repo":"google-research/sam","repo_kind":"official","path":"sam_jax/efficientnet/efficientnet.py","file_url":"https://github.com/google-research/sam/blob/HEAD/sam_jax/efficientnet/efficientnet.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":"cb2821198470712c"}},{"code_sha256_prefix":"245dfb545218b755","entry":"normalize_image","repo":"google-research/sam","repo_kind":"official","path":"sam_jax/datasets/dataset_source_imagenet.py","file_url":"https://github.com/google-research/sam/blob/HEAD/sam_jax/datasets/dataset_source_imagenet.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":"245dfb545218b755"}},{"code_sha256_prefix":"db053b3b48a12365","entry":"preprocess_for_eval","repo":"google-research/sam","repo_kind":"official","path":"sam_jax/datasets/dataset_source_imagenet.py","file_url":"https://github.com/google-research/sam/blob/HEAD/sam_jax/datasets/dataset_source_imagenet.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":"db053b3b48a12365"}},{"code_sha256_prefix":"2c7d0d794dc5a73c","entry":"round_filters","repo":"google-research/sam","repo_kind":"official","path":"sam_jax/efficientnet/efficientnet.py","file_url":"https://github.com/google-research/sam/blob/HEAD/sam_jax/efficientnet/efficientnet.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":"2c7d0d794dc5a73c"}},{"code_sha256_prefix":"61a40ee8921487b9","entry":"round_repeats","repo":"google-research/sam","repo_kind":"official","path":"sam_jax/efficientnet/efficientnet.py","file_url":"https://github.com/google-research/sam/blob/HEAD/sam_jax/efficientnet/efficientnet.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":"61a40ee8921487b9"}},{"code_sha256_prefix":"16e98d61f39aa54e","entry":"shake_shake_train","repo":"google-research/sam","repo_kind":"official","path":"sam_jax/models/utils.py","file_url":"https://github.com/google-research/sam/blob/HEAD/sam_jax/models/utils.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":"16e98d61f39aa54e"}},{"code_sha256_prefix":"967ecdba90ad4784","entry":"weak_image_augmentation","repo":"google-research/sam","repo_kind":"official","path":"sam_jax/datasets/augmentation.py","file_url":"https://github.com/google-research/sam/blob/HEAD/sam_jax/datasets/augmentation.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":"967ecdba90ad4784"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}