{"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/class-balanced-loss-based-on-effective-number","title":"Class-Balanced Loss Based on Effective Number of Samples","arxiv_id":"1901.05555","date":"2019-01-16","proceeding":"CVPR 2019 6","authors":["Yin Cui","Menglin Jia","Tsung-Yi Lin","Yang song","Serge Belongie"],"abstract":"With the rapid increase of large-scale, real-world datasets, it becomes\ncritical to address the problem of long-tailed data distribution (i.e., a few\nclasses account for most of the data, while most classes are\nunder-represented). Existing solutions typically adopt class re-balancing\nstrategies such as re-sampling and re-weighting based on the number of\nobservations for each class. In this work, we argue that as the number of\nsamples increases, the additional benefit of a newly added data point will\ndiminish. We introduce a novel theoretical framework to measure data overlap by\nassociating with each sample a small neighboring region rather than a single\npoint. The effective number of samples is defined as the volume of samples and\ncan be calculated by a simple formula $(1-\\beta^{n})/(1-\\beta)$, where $n$ is\nthe number of samples and $\\beta \\in [0,1)$ is a hyperparameter. We design a\nre-weighting scheme that uses the effective number of samples for each class to\nre-balance the loss, thereby yielding a class-balanced loss. Comprehensive\nexperiments are conducted on artificially induced long-tailed CIFAR datasets\nand large-scale datasets including ImageNet and iNaturalist. Our results show\nthat when trained with the proposed class-balanced loss, the network is able to\nachieve significant performance gains on long-tailed datasets.","url_abs":"http://arxiv.org/abs/1901.05555v1","url_pdf":"http://arxiv.org/pdf/1901.05555v1.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":"class-balanced-loss-based-on-effective-number","repo_url":"https://github.com/richardaecn/class-balanced-loss","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"class-balanced-loss-based-on-effective-number","repo_url":"https://github.com/bazinga699/ncl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"class-balanced-loss-based-on-effective-number","repo_url":"https://github.com/feidfoe/AdjustBnd4Imbalance","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"class-balanced-loss-based-on-effective-number","repo_url":"https://github.com/frgfm/Holocron","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"class-balanced-loss-based-on-effective-number","repo_url":"https://github.com/lijian16/fcc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"class-balanced-loss-based-on-effective-number","repo_url":"https://github.com/statsu1990/yoto_class_balanced_loss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"class-balanced-loss-based-on-effective-number","repo_url":"https://github.com/tiagoCuervo/JapaNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"class-balanced-loss-based-on-effective-number","repo_url":"https://github.com/vandit15/Class-balanced-loss-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"class-balanced-loss-based-on-effective-number","repo_url":"https://github.com/MindCode-4/code-11/tree/main/Class-balanced-loss-pytorch-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"class-balanced-loss-based-on-effective-number","repo_url":"https://github.com/MindCode-4/code-6/tree/main/Class-balanced-loss-pytorch-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"class-balanced-loss-based-on-effective-number","repo_url":"https://github.com/MindSpore-scientific/code-3/tree/main/Class-balanced-loss-pytorch-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"long-tail-learning","task_name":"Long-tail Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-inaturalist-2018","task":"Image Classification","dataset":"iNaturalist 2018","model":"ResNet-152","rank_in_archive_order":41,"of":60,"metrics":{"Top-1 Accuracy":"69.05%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-inaturalist-2018","task":"Image Classification","dataset":"iNaturalist 2018","model":"ResNet-101","rank_in_archive_order":44,"of":60,"metrics":{"Top-1 Accuracy":"67.98%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-inaturalist-2018","task":"Image Classification","dataset":"iNaturalist 2018","model":"ResNet-50","rank_in_archive_order":52,"of":60,"metrics":{"Top-1 Accuracy":"64.16%"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-10-lt-r-10","task":"Long-tail Learning","dataset":"CIFAR-10-LT (ρ=10)","model":"Class-balanced Focal Loss","rank_in_archive_order":45,"of":50,"metrics":{"Error Rate":"12.90"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-10-lt-r-10","task":"Long-tail Learning","dataset":"CIFAR-10-LT (ρ=10)","model":"Class-balanced Reweighting","rank_in_archive_order":48,"of":50,"metrics":{"Error Rate":"13.46"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-100","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=100)","model":"Cross-Entropy (CE)","rank_in_archive_order":65,"of":66,"metrics":{"Error Rate":"61.68"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-coco-mlt","task":"Long-tail Learning","dataset":"COCO-MLT","model":"CB Loss(ResNet-50)","rank_in_archive_order":9,"of":13,"metrics":{"Average mAP":"49.06"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-egtea","task":"Long-tail Learning","dataset":"EGTEA","model":"CB Loss","rank_in_archive_order":2,"of":3,"metrics":{"Average Precision":"63.39","Average Recall":"63.26"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-voc-mlt","task":"Long-tail Learning","dataset":"VOC-MLT","model":"CB Focal(ResNet-50)","rank_in_archive_order":9,"of":13,"metrics":{"Average mAP":"75.24"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.05555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.05555"}},"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/feidfoe/AdjustBnd4Imbalance","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindCode-4/code-11/tree/main/Class-balanced-loss-pytorch-master","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bazinga699/ncl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/frgfm/Holocron","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tiagoCuervo/JapaNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/richardaecn/class-balanced-loss","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vandit15/Class-balanced-loss-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific/code-3/tree/main/Class-balanced-loss-pytorch-master","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindCode-4/code-6/tree/main/Class-balanced-loss-pytorch-master","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/statsu1990/yoto_class_balanced_loss","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lijian16/fcc","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"ran":5,"unverified":20},"by_repo_kind":{"official":{"samples":19,"ran":0,"repositories":1},"listed":{"samples":8,"ran":7,"repositories":5}},"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":"213dab5ee3c9a730","entry":"CB_loss","repo":"vandit15/Class-balanced-loss-pytorch","repo_kind":"listed","path":"class_balanced_loss.py","file_url":"https://github.com/vandit15/Class-balanced-loss-pytorch/blob/HEAD/class_balanced_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"213dab5ee3c9a730"}},{"code_sha256_prefix":"749ae093d1002dc8","entry":"ClassBalanceCE","repo":"lijian16/fcc","repo_kind":"listed","path":"lib/loss/loss_impl/class_balanced_loss.py","file_url":"https://github.com/lijian16/fcc/blob/HEAD/lib/loss/loss_impl/class_balanced_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"749ae093d1002dc8"}},{"code_sha256_prefix":"fa48de5142876479","entry":"ClassBalancedWrapper","repo":"frgfm/Holocron","repo_kind":"listed","path":"holocron/nn/modules/loss.py","file_url":"https://github.com/frgfm/Holocron/blob/HEAD/holocron/nn/modules/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fa48de5142876479"}},{"code_sha256_prefix":"68d1f62eac95f880","entry":"ClassBalanced_CELoss","repo":"statsu1990/yoto_class_balanced_loss","repo_kind":"listed","path":"src/model/cb_loss.py","file_url":"https://github.com/statsu1990/yoto_class_balanced_loss/blob/HEAD/src/model/cb_loss.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":"68d1f62eac95f880"}},{"code_sha256_prefix":"03ec3d933bc9e286","entry":"CrossEntropy","repo":"lijian16/fcc","repo_kind":"listed","path":"lib/loss/loss_impl/class_balanced_loss.py","file_url":"https://github.com/lijian16/fcc/blob/HEAD/lib/loss/loss_impl/class_balanced_loss.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":"03ec3d933bc9e286"}},{"code_sha256_prefix":"e4d180e212ea7092","entry":"NBOD","repo":"bazinga699/ncl","repo_kind":"listed","path":"lib/loss/loss.py","file_url":"https://github.com/bazinga699/ncl/blob/HEAD/lib/loss/loss.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":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e4d180e212ea7092"}},{"code_sha256_prefix":"49b09b16b775ec58","entry":"NIL_NBOD","repo":"bazinga699/ncl","repo_kind":"listed","path":"lib/loss/loss.py","file_url":"https://github.com/bazinga699/ncl/blob/HEAD/lib/loss/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"49b09b16b775ec58"}},{"code_sha256_prefix":"44a9936773ea082c","entry":"convert_array_to_image","repo":"richardaecn/class-balanced-loss","repo_kind":"official","path":"tpu/models/experimental/dcgan/cifar_input.py","file_url":"https://github.com/richardaecn/class-balanced-loss/blob/HEAD/tpu/models/experimental/dcgan/cifar_input.py","link_basis":"first_harvest_node","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":"44a9936773ea082c"}},{"code_sha256_prefix":"90a8002ad4ce5c44","entry":"dir2version","repo":"richardaecn/class-balanced-loss","repo_kind":"official","path":"src/cifar_main.py","file_url":"https://github.com/richardaecn/class-balanced-loss/blob/HEAD/src/cifar_main.py","link_basis":"first_harvest_node","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":"90a8002ad4ce5c44"}},{"code_sha256_prefix":"59ec4e09ac2ce079","entry":"discriminator","repo":"richardaecn/class-balanced-loss","repo_kind":"official","path":"tpu/models/experimental/dcgan/cifar_model.py","file_url":"https://github.com/richardaecn/class-balanced-loss/blob/HEAD/tpu/models/experimental/dcgan/cifar_model.py","link_basis":"first_harvest_node","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":"59ec4e09ac2ce079"}},{"code_sha256_prefix":"c32ccdb4e101c470","entry":"focal_loss","repo":"vandit15/Class-balanced-loss-pytorch","repo_kind":"listed","path":"class_balanced_loss.py","file_url":"https://github.com/vandit15/Class-balanced-loss-pytorch/blob/HEAD/class_balanced_loss.py","link_basis":"first_harvest_node","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":"c32ccdb4e101c470"}},{"code_sha256_prefix":"787ada018be76773","entry":"generate_input_fn","repo":"richardaecn/class-balanced-loss","repo_kind":"official","path":"tpu/models/experimental/dcgan/dcgan_main.py","file_url":"https://github.com/richardaecn/class-balanced-loss/blob/HEAD/tpu/models/experimental/dcgan/dcgan_main.py","link_basis":"first_harvest_node","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":"787ada018be76773"}},{"code_sha256_prefix":"6bfcb692805e9db9","entry":"generator","repo":"richardaecn/class-balanced-loss","repo_kind":"official","path":"tpu/models/experimental/dcgan/cifar_model.py","file_url":"https://github.com/richardaecn/class-balanced-loss/blob/HEAD/tpu/models/experimental/dcgan/cifar_model.py","link_basis":"first_harvest_node","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":"6bfcb692805e9db9"}},{"code_sha256_prefix":"ea12a62c609bc291","entry":"get_imbalanced_data","repo":"richardaecn/class-balanced-loss","repo_kind":"official","path":"src/generate_cifar_tfrecords_im.py","file_url":"https://github.com/richardaecn/class-balanced-loss/blob/HEAD/src/generate_cifar_tfrecords_im.py","link_basis":"first_harvest_node","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":"ea12a62c609bc291"}},{"code_sha256_prefix":"306ffaa84f8da0c6","entry":"get_traindata_list","repo":"richardaecn/class-balanced-loss","repo_kind":"official","path":"src/generate_cifar_tfrecords_im.py","file_url":"https://github.com/richardaecn/class-balanced-loss/blob/HEAD/src/generate_cifar_tfrecords_im.py","link_basis":"first_harvest_node","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":"306ffaa84f8da0c6"}},{"code_sha256_prefix":"4f59b56fcbea8270","entry":"img_num","repo":"richardaecn/class-balanced-loss","repo_kind":"official","path":"src/data_utils.py","file_url":"https://github.com/richardaecn/class-balanced-loss/blob/HEAD/src/data_utils.py","link_basis":"first_harvest_node","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":"4f59b56fcbea8270"}},{"code_sha256_prefix":"57184f395fe4ff8f","entry":"input_fn","repo":"richardaecn/class-balanced-loss","repo_kind":"official","path":"tpu/models/experimental/cifar_keras/cifar_keras.py","file_url":"https://github.com/richardaecn/class-balanced-loss/blob/HEAD/tpu/models/experimental/cifar_keras/cifar_keras.py","link_basis":"first_harvest_node","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":"57184f395fe4ff8f"}},{"code_sha256_prefix":"10fc348fea580bf2","entry":"learning_rate_schedule","repo":"richardaecn/class-balanced-loss","repo_kind":"official","path":"src/cifar_main.py","file_url":"https://github.com/richardaecn/class-balanced-loss/blob/HEAD/src/cifar_main.py","link_basis":"first_harvest_node","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":"10fc348fea580bf2"}},{"code_sha256_prefix":"667cea6bb6608b7b","entry":"local_device_setter","repo":"richardaecn/class-balanced-loss","repo_kind":"official","path":"src/cifar_utils.py","file_url":"https://github.com/richardaecn/class-balanced-loss/blob/HEAD/src/cifar_utils.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":"667cea6bb6608b7b"}},{"code_sha256_prefix":"a8d0a5e19105636a","entry":"model_fn","repo":"richardaecn/class-balanced-loss","repo_kind":"official","path":"tpu/models/experimental/cifar_keras/cifar_keras.py","file_url":"https://github.com/richardaecn/class-balanced-loss/blob/HEAD/tpu/models/experimental/cifar_keras/cifar_keras.py","link_basis":"first_harvest_node","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":"a8d0a5e19105636a"}},{"code_sha256_prefix":"7634c2c31837e3f5","entry":"model_fn","repo":"richardaecn/class-balanced-loss","repo_kind":"official","path":"tpu/models/experimental/dcgan/dcgan_main.py","file_url":"https://github.com/richardaecn/class-balanced-loss/blob/HEAD/tpu/models/experimental/dcgan/dcgan_main.py","link_basis":"first_harvest_node","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":"7634c2c31837e3f5"}},{"code_sha256_prefix":"f3d3946d06874d2a","entry":"noise_input_fn","repo":"richardaecn/class-balanced-loss","repo_kind":"official","path":"tpu/models/experimental/dcgan/dcgan_main.py","file_url":"https://github.com/richardaecn/class-balanced-loss/blob/HEAD/tpu/models/experimental/dcgan/dcgan_main.py","link_basis":"first_harvest_node","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":"f3d3946d06874d2a"}},{"code_sha256_prefix":"1863a653dad9ca35","entry":"parser","repo":"richardaecn/class-balanced-loss","repo_kind":"official","path":"tpu/models/experimental/dcgan/cifar_input.py","file_url":"https://github.com/richardaecn/class-balanced-loss/blob/HEAD/tpu/models/experimental/dcgan/cifar_input.py","link_basis":"first_harvest_node","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":"1863a653dad9ca35"}},{"code_sha256_prefix":"35ae8c0dce858108","entry":"read_json","repo":"richardaecn/class-balanced-loss","repo_kind":"official","path":"src/data_utils.py","file_url":"https://github.com/richardaecn/class-balanced-loss/blob/HEAD/src/data_utils.py","link_basis":"first_harvest_node","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":"35ae8c0dce858108"}},{"code_sha256_prefix":"162b6ba3306530cc","entry":"read_pickle_from_file","repo":"richardaecn/class-balanced-loss","repo_kind":"official","path":"src/data_utils.py","file_url":"https://github.com/richardaecn/class-balanced-loss/blob/HEAD/src/data_utils.py","link_basis":"first_harvest_node","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":"162b6ba3306530cc"}},{"code_sha256_prefix":"7137e8ae47a966ce","entry":"read_pickle_from_file","repo":"richardaecn/class-balanced-loss","repo_kind":"official","path":"src/generate_cifar_tfrecords.py","file_url":"https://github.com/richardaecn/class-balanced-loss/blob/HEAD/src/generate_cifar_tfrecords.py","link_basis":"first_harvest_node","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":"7137e8ae47a966ce"}},{"code_sha256_prefix":"c20afab5ec1e1d08","entry":"sort_input","repo":"richardaecn/class-balanced-loss","repo_kind":"official","path":"src/generate_cifar_tfrecords_im.py","file_url":"https://github.com/richardaecn/class-balanced-loss/blob/HEAD/src/generate_cifar_tfrecords_im.py","link_basis":"first_harvest_node","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":"c20afab5ec1e1d08"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}