{"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/self-training-with-noisy-student-improves","title":"Self-training with Noisy Student improves ImageNet classification","arxiv_id":"1911.04252","date":"2019-11-11","proceeding":"CVPR 2020 6","authors":["Qizhe Xie","Minh-Thang Luong","Eduard Hovy","Quoc V. Le"],"abstract":"We present Noisy Student Training, a semi-supervised learning approach that works well even when labeled data is abundant. Noisy Student Training achieves 88.4% top-1 accuracy on ImageNet, which is 2.0% better than the state-of-the-art model that requires 3.5B weakly labeled Instagram images. On robustness test sets, it improves ImageNet-A top-1 accuracy from 61.0% to 83.7%, reduces ImageNet-C mean corruption error from 45.7 to 28.3, and reduces ImageNet-P mean flip rate from 27.8 to 12.2. Noisy Student Training extends the idea of self-training and distillation with the use of equal-or-larger student models and noise added to the student during learning. On ImageNet, we first train an EfficientNet model on labeled images and use it as a teacher to generate pseudo labels for 300M unlabeled images. We then train a larger EfficientNet as a student model on the combination of labeled and pseudo labeled images. We iterate this process by putting back the student as the teacher. During the learning of the student, we inject noise such as dropout, stochastic depth, and data augmentation via RandAugment to the student so that the student generalizes better than the teacher. Models are available at https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet. Code is available at https://github.com/google-research/noisystudent.","url_abs":"https://arxiv.org/abs/1911.04252v4","url_pdf":"https://arxiv.org/pdf/1911.04252v4.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":"self-training-with-noisy-student-improves","repo_url":"https://github.com/google-research/noisystudent","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"self-training-with-noisy-student-improves","repo_url":"https://github.com/tensorflow/tpu","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"self-training-with-noisy-student-improves","repo_url":"https://github.com/adventure2165/Summarization_self-training_with_noisy_student_improves_imagenet_classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"self-training-with-noisy-student-improves","repo_url":"https://github.com/hamed-ahangari/Separation-Index-of-convolutional-layers-in-EfficientNet-B0","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"self-training-with-noisy-student-improves","repo_url":"https://github.com/leondgarse/Keras_efficientnet_v2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"self-training-with-noisy-student-improves","repo_url":"https://github.com/leondgarse/Keras_efficientnet_v2_test","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"self-training-with-noisy-student-improves","repo_url":"https://github.com/mhd-medfa/NoisyStudent-Based-Object-Recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"self-training-with-noisy-student-improves","repo_url":"https://github.com/phamtrancsek12/offensive-identification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"self-training-with-noisy-student-improves","repo_url":"https://github.com/stanleyjzheng/PyData","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"self-training-with-noisy-student-improves","repo_url":"https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"self-training-with-noisy-student-improves","repo_url":"https://github.com/thomasly/PaperTranslation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"self-training-with-noisy-student-improves","repo_url":"https://github.com/xultaeculcis/coral-net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"self-training-with-noisy-student-improves","repo_url":"https://github.com/yakhyo/EfficientNet-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"}],"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":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"efficientnet","method_name":"EfficientNet"},{"method_slug":"fixres","method_name":"FixRes"},{"method_slug":"inverted-residual-block","method_name":"Inverted Residual Block"},{"method_slug":"noisy-student","method_name":"Noisy Student"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"rmsprop","method_name":"RMSProp"},{"method_slug":"randaugment","method_name":"RandAugment"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"squeeze-and-excitation-block","method_name":"Squeeze-and-Excitation Block"},{"method_slug":"step-decay","method_name":"Step Decay"},{"method_slug":"stochastic-depth","method_name":"Stochastic Depth"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"NoisyStudent (EfficientNet-L2)","rank_in_archive_order":48,"of":1060,"metrics":{"Hardware Burden":"51800G","Number of params":"480M","Top 1 Accuracy":"88.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"NoisyStudent (EfficientNet-B7)","rank_in_archive_order":118,"of":1060,"metrics":{"GFLOPs":"37","Number of params":"66M","Top 1 Accuracy":"86.9%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"NoisyStudent (EfficientNet-B6)","rank_in_archive_order":148,"of":1060,"metrics":{"Number of params":"43M","Top 1 Accuracy":"86.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"NoisyStudent (EfficientNet-B5)","rank_in_archive_order":172,"of":1060,"metrics":{"Number of params":"30M","Top 1 Accuracy":"86.1%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"NoisyStudent (EfficientNet-B4)","rank_in_archive_order":240,"of":1060,"metrics":{"Number of params":"19M","Top 1 Accuracy":"85.3%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"NoisyStudent (EfficientNet-B3)","rank_in_archive_order":351,"of":1060,"metrics":{"Number of params":"12M","Top 1 Accuracy":"84.1%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"NoisyStudent (EfficientNet-B2)","rank_in_archive_order":538,"of":1060,"metrics":{"Number of params":"9.2M","Top 1 Accuracy":"82.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"NoisyStudent (EfficientNet-B1)","rank_in_archive_order":633,"of":1060,"metrics":{"Number of params":"7.8M","Top 1 Accuracy":"81.5%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"NoisyStudent (EfficientNet-B0)","rank_in_archive_order":803,"of":1060,"metrics":{"Number of params":"5.3M","Top 1 Accuracy":"78.8%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet-real","task":"Image Classification","dataset":"ImageNet ReaL","model":"EfficientNet-L2","rank_in_archive_order":16,"of":57,"metrics":{"Accuracy":"90.55%","Params":"480M"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1911.04252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.04252"}},"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/tensorflow/tpu","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/adventure2165/Summarization_self-training_with_noisy_student_improves_imagenet_classification","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stanleyjzheng/PyData","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mhd-medfa/NoisyStudent-Based-Object-Recognition","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/noisystudent","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/leondgarse/Keras_efficientnet_v2","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hamed-ahangari/Separation-Index-of-convolutional-layers-in-EfficientNet-B0","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thomasly/PaperTranslation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xultaeculcis/coral-net","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/leondgarse/Keras_efficientnet_v2_test","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yakhyo/EfficientNet-PyTorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/phamtrancsek12/offensive-identification","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran_fixture":2,"ran_honours":2,"unverified":19},"by_repo_kind":{"official":{"samples":16,"ran":0,"repositories":1},"listed":{"samples":8,"ran":5,"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":"e9ed9f7ced6189ee","entry":"batchnorm_with_activation","repo":"leondgarse/Keras_efficientnet_v2_test","repo_kind":"listed","path":"keras_efficientnet_v2/efficientnet_v2.py","file_url":"https://github.com/leondgarse/Keras_efficientnet_v2_test/blob/HEAD/keras_efficientnet_v2/efficientnet_v2.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e9ed9f7ced6189ee"}},{"code_sha256_prefix":"96248e1c8a073860","entry":"conv2d_no_bias","repo":"leondgarse/Keras_efficientnet_v2_test","repo_kind":"listed","path":"keras_efficientnet_v2/efficientnet_v2.py","file_url":"https://github.com/leondgarse/Keras_efficientnet_v2_test/blob/HEAD/keras_efficientnet_v2/efficientnet_v2.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"96248e1c8a073860"}},{"code_sha256_prefix":"5640ec0612debaea","entry":"round_filters","repo":"leondgarse/Keras_efficientnet_v2_test","repo_kind":"listed","path":"convert_effnetv2_model.py","file_url":"https://github.com/leondgarse/Keras_efficientnet_v2_test/blob/HEAD/convert_effnetv2_model.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5640ec0612debaea"}},{"code_sha256_prefix":"b43c2e4c5402cf83","entry":"se_module","repo":"leondgarse/Keras_efficientnet_v2_test","repo_kind":"listed","path":"keras_efficientnet_v2/efficientnet_v2.py","file_url":"https://github.com/leondgarse/Keras_efficientnet_v2_test/blob/HEAD/keras_efficientnet_v2/efficientnet_v2.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b43c2e4c5402cf83"}},{"code_sha256_prefix":"bd1c72a9d8556505","entry":"to_4d","repo":"leondgarse/Keras_efficientnet_v2_test","repo_kind":"listed","path":"keras_efficientnet_v2/augment.py","file_url":"https://github.com/leondgarse/Keras_efficientnet_v2_test/blob/HEAD/keras_efficientnet_v2/augment.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd1c72a9d8556505"}},{"code_sha256_prefix":"574c2e00bbe4667f","entry":"blend","repo":"google-research/noisystudent","repo_kind":"official","path":"randaugment.py","file_url":"https://github.com/google-research/noisystudent/blob/HEAD/randaugment.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":"574c2e00bbe4667f"}},{"code_sha256_prefix":"53da5ea39ee2fa51","entry":"build_learning_rate","repo":"google-research/noisystudent","repo_kind":"official","path":"utils.py","file_url":"https://github.com/google-research/noisystudent/blob/HEAD/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":"53da5ea39ee2fa51"}},{"code_sha256_prefix":"7b88b9f2e3c23c21","entry":"build_optimizer","repo":"google-research/noisystudent","repo_kind":"official","path":"utils.py","file_url":"https://github.com/google-research/noisystudent/blob/HEAD/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":"7b88b9f2e3c23c21"}},{"code_sha256_prefix":"4ae6bf83cccbb591","entry":"conv_kernel_initializer","repo":"google-research/noisystudent","repo_kind":"official","path":"efficientnet_model.py","file_url":"https://github.com/google-research/noisystudent/blob/HEAD/efficientnet_model.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":"4ae6bf83cccbb591"}},{"code_sha256_prefix":"cafc76d8c85afb88","entry":"conv_kernel_initializer","repo":"leondgarse/Keras_efficientnet_v2_test","repo_kind":"listed","path":"convert_effnetv2_model.py","file_url":"https://github.com/leondgarse/Keras_efficientnet_v2_test/blob/HEAD/convert_effnetv2_model.py","link_basis":"harvester_set","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":"cafc76d8c85afb88"}},{"code_sha256_prefix":"d42d54a4353367b5","entry":"cutout","repo":"google-research/noisystudent","repo_kind":"official","path":"randaugment.py","file_url":"https://github.com/google-research/noisystudent/blob/HEAD/randaugment.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":"d42d54a4353367b5"}},{"code_sha256_prefix":"e430f1fd246b1b51","entry":"dense_kernel_initializer","repo":"google-research/noisystudent","repo_kind":"official","path":"efficientnet_model.py","file_url":"https://github.com/google-research/noisystudent/blob/HEAD/efficientnet_model.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":"e430f1fd246b1b51"}},{"code_sha256_prefix":"538d8c4191034b39","entry":"dense_kernel_initializer","repo":"leondgarse/Keras_efficientnet_v2_test","repo_kind":"listed","path":"convert_effnetv2_model.py","file_url":"https://github.com/leondgarse/Keras_efficientnet_v2_test/blob/HEAD/convert_effnetv2_model.py","link_basis":"harvester_set","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":"538d8c4191034b39"}},{"code_sha256_prefix":"00e16fdd1db60196","entry":"efficientnet_params","repo":"google-research/noisystudent","repo_kind":"official","path":"efficientnet_builder.py","file_url":"https://github.com/google-research/noisystudent/blob/HEAD/efficientnet_builder.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":"00e16fdd1db60196"}},{"code_sha256_prefix":"b10fb8ac53c53a97","entry":"from_4d","repo":"leondgarse/Keras_efficientnet_v2_test","repo_kind":"listed","path":"keras_efficientnet_v2/augment.py","file_url":"https://github.com/leondgarse/Keras_efficientnet_v2_test/blob/HEAD/keras_efficientnet_v2/augment.py","link_basis":"harvester_set","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":"b10fb8ac53c53a97"}},{"code_sha256_prefix":"aabbd55b6f0e8db6","entry":"get_keep_image_idx","repo":"google-research/noisystudent","repo_kind":"official","path":"filter_unlabel.py","file_url":"https://github.com/google-research/noisystudent/blob/HEAD/filter_unlabel.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":"aabbd55b6f0e8db6"}},{"code_sha256_prefix":"ab69b327577ef8d4","entry":"get_mean_std","repo":"google-research/noisystudent","repo_kind":"official","path":"task_info.py","file_url":"https://github.com/google-research/noisystudent/blob/HEAD/task_info.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":"ab69b327577ef8d4"}},{"code_sha256_prefix":"5edab72c1f95b154","entry":"get_num_eval_images","repo":"google-research/noisystudent","repo_kind":"official","path":"task_info.py","file_url":"https://github.com/google-research/noisystudent/blob/HEAD/task_info.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":"5edab72c1f95b154"}},{"code_sha256_prefix":"8823cc7b394ad9d1","entry":"get_num_train_images","repo":"google-research/noisystudent","repo_kind":"official","path":"task_info.py","file_url":"https://github.com/google-research/noisystudent/blob/HEAD/task_info.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":"8823cc7b394ad9d1"}},{"code_sha256_prefix":"d8e0266f26c70d20","entry":"set_shapes","repo":"google-research/noisystudent","repo_kind":"official","path":"predict_label.py","file_url":"https://github.com/google-research/noisystudent/blob/HEAD/predict_label.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":"d8e0266f26c70d20"}},{"code_sha256_prefix":"0df948cabd4bdae3","entry":"shuffle_split","repo":"google-research/noisystudent","repo_kind":"official","path":"proc_svhn.py","file_url":"https://github.com/google-research/noisystudent/blob/HEAD/proc_svhn.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":"0df948cabd4bdae3"}},{"code_sha256_prefix":"033941ec31eafc06","entry":"small_image_crop","repo":"google-research/noisystudent","repo_kind":"official","path":"preprocessing.py","file_url":"https://github.com/google-research/noisystudent/blob/HEAD/preprocessing.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":"033941ec31eafc06"}},{"code_sha256_prefix":"e40dd3a18c0fb8bc","entry":"solarize","repo":"google-research/noisystudent","repo_kind":"official","path":"randaugment.py","file_url":"https://github.com/google-research/noisystudent/blob/HEAD/randaugment.py","link_basis":"harvester_set","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":"e40dd3a18c0fb8bc"}},{"code_sha256_prefix":"c0942e1efe9598d2","entry":"stochastic_depth","repo":"google-research/noisystudent","repo_kind":"official","path":"utils.py","file_url":"https://github.com/google-research/noisystudent/blob/HEAD/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":"c0942e1efe9598d2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}