{"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/training-data-efficient-image-transformers","title":"Training data-efficient image transformers & distillation through attention","arxiv_id":"2012.12877","date":"2020-12-23","proceeding":null,"authors":["Hugo Touvron","Matthieu Cord","Matthijs Douze","Francisco Massa","Alexandre Sablayrolles","Hervé Jégou"],"abstract":"Recently, neural networks purely based on attention were shown to address image understanding tasks such as image classification. However, these visual transformers are pre-trained with hundreds of millions of images using an expensive infrastructure, thereby limiting their adoption. In this work, we produce a competitive convolution-free transformer by training on Imagenet only. We train them on a single computer in less than 3 days. Our reference vision transformer (86M parameters) achieves top-1 accuracy of 83.1% (single-crop evaluation) on ImageNet with no external data. More importantly, we introduce a teacher-student strategy specific to transformers. It relies on a distillation token ensuring that the student learns from the teacher through attention. We show the interest of this token-based distillation, especially when using a convnet as a teacher. This leads us to report results competitive with convnets for both Imagenet (where we obtain up to 85.2% accuracy) and when transferring to other tasks. We share our code and models.","url_abs":"https://arxiv.org/abs/2012.12877v2","url_pdf":"https://arxiv.org/pdf/2012.12877v2.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":"training-data-efficient-image-transformers","repo_url":"https://github.com/facebookresearch/deit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/rwightman/pytorch-image-models","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/Burf/VisionTransformer-Tensorflow2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/IMvision12/keras-vision-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/TACJu/TransFG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/UdbhavPrasad072300/Transformer-Implementations","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/affjljoo3581/deit3-jax","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/ahmedelmahy/myownvit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/aiot-mlsys-lab/famba-v","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/alessiomora/unlearning_fl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/asrafulashiq/deit-custom","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/bshantam97/Attention_Based_Networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/cogtoolslab/physics-benchmarking-neurips2021","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/gatech-eic/vitcod","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/holdfire/CLS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/holdfire/FAS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/huggingface/transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/hustvl/vim","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/jacobgil/vit-explain","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/liuxingwt/CLS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/moein-shariatnia/Pix2Seq","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/nus-hpc-ai-lab/dyvm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/omihub777/vit-cifar","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/open-edge-platform/geti","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/s-chh/patchrot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/skchen1993/TrangFG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/smu-ivpl/DeepfakeDetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/tianhai123/vit-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/ttt496/vit-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/wangyz1608/knowledge-distillation-via-nd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/zhuhanqing/lightening-transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/BR-IDL/PaddleViT/blob/main/image_classification/DeiT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/Oguzhanercan/Vision-Transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/PaddlePaddle/PLSC/tree/master/task/classification/deit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/PaddlePaddle/PaddleClas","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/alibaba/EasyCV","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/code-implementation1/Code1/tree/main/DeiT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/backbone/DeiT.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://github.com/open-edge-platform/training_extensions","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"training-data-efficient-image-transformers","repo_url":"https://gitlab.com/birder/birder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"document-image-classification","task_name":"Document Image Classification"},{"task_slug":"document-layout-analysis","task_name":"Document Layout Analysis"},{"task_slug":"efficient-vits","task_name":"Efficient ViTs"},{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"adamw","method_name":"AdamW"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"cutmix","method_name":"CutMix"},{"method_slug":"deit","method_name":"DeiT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":null,"method_name":null},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":null,"method_name":null},{"method_slug":"fixres","method_name":"FixRes"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"mixup","method_name":"Mixup"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"randaugment","method_name":"RandAugment"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"stochastic-depth","method_name":"Stochastic Depth"},{"method_slug":null,"method_name":null},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/document-image-classification-on-rvl-cdip","task":"Document Image Classification","dataset":"RVL-CDIP","model":"DeiT-B","rank_in_archive_order":30,"of":31,"metrics":{"Accuracy":"90.32%","Parameters":" 87M"},"uses_additional_data":false},{"leaderboard":"/sota/document-layout-analysis-on-publaynet-val","task":"Document Layout Analysis","dataset":"PubLayNet val","model":"DeiT-B","rank_in_archive_order":10,"of":15,"metrics":{"Figure":"0.957","List":" 0.921","Overall":"0.932","Table":"0.972","Text":"0.934","Title":"0.874"},"uses_additional_data":false},{"leaderboard":"/sota/efficient-vits-on-imagenet-1k-with-deit-s","task":"Efficient ViTs","dataset":"ImageNet-1K (with DeiT-S)","model":"Base (DeiT-S)","rank_in_archive_order":12,"of":41,"metrics":{"GFLOPs":"4.6","Top 1 Accuracy":"79.8"},"uses_additional_data":false},{"leaderboard":"/sota/efficient-vits-on-imagenet-1k-with-deit-t","task":"Efficient ViTs","dataset":"ImageNet-1K (with DeiT-T)","model":"Base (DeiT-T)","rank_in_archive_order":7,"of":22,"metrics":{"GFLOPs":"1.2","Top 1 Accuracy":"72.2"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-oxford","task":"Fine-Grained Image Classification","dataset":"Oxford 102 Flowers","model":"DeiT-B","rank_in_archive_order":10,"of":25,"metrics":{"Accuracy":"98.8%","PARAMS":"86M"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-stanford","task":"Fine-Grained Image Classification","dataset":"Stanford Cars","model":"DeiT-B","rank_in_archive_order":65,"of":83,"metrics":{"Accuracy":"93.3%","PARAMS":"86M"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"DeiT-B","rank_in_archive_order":14,"of":265,"metrics":{"Percentage correct":"99.1"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"DeiT-B","rank_in_archive_order":22,"of":211,"metrics":{"PARAMS":"86M","Percentage correct":"90.8"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-flowers-102","task":"Image Classification","dataset":"Flowers-102","model":"DeiT-B","rank_in_archive_order":21,"of":52,"metrics":{"Accuracy":"98.8%","PARAMS":"86M"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"DeiT-B 384","rank_in_archive_order":251,"of":1060,"metrics":{"Number of params":"87M","Top 1 Accuracy":"85.2%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"DeiT-B","rank_in_archive_order":341,"of":1060,"metrics":{"Number of params":"86M","Top 1 Accuracy":"84.2%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"DeiT-B","rank_in_archive_order":524,"of":1060,"metrics":{"Number of params":"22M","Top 1 Accuracy":"82.6%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"DeiT-B","rank_in_archive_order":910,"of":1060,"metrics":{"Number of params":"5M","Top 1 Accuracy":"76.6%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet-real","task":"Image Classification","dataset":"ImageNet ReaL","model":"DeiT-B-384","rank_in_archive_order":24,"of":57,"metrics":{"Accuracy":"89.3%","Params":"86M"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet-real","task":"Image Classification","dataset":"ImageNet ReaL","model":"DeiT-B","rank_in_archive_order":26,"of":57,"metrics":{"Accuracy":"88.7%","Params":"86M"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet-real","task":"Image Classification","dataset":"ImageNet ReaL","model":"DeiT-S","rank_in_archive_order":36,"of":57,"metrics":{"Accuracy":"86.8%","Params":"22M"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet-real","task":"Image Classification","dataset":"ImageNet ReaL","model":"DeiT-Ti","rank_in_archive_order":49,"of":57,"metrics":{"Accuracy":"82.1%","Params":"5M"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-inaturalist-2018","task":"Image Classification","dataset":"iNaturalist 2018","model":"DeiT-B","rank_in_archive_order":18,"of":60,"metrics":{"Top-1 Accuracy":"79.5%"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2012.12877","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.12877"}},"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/rwightman/pytorch-image-models","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/facebookresearch/deit","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huggingface/transformers","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/omihub777/vit-cifar","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/UdbhavPrasad072300/Transformer-Implementations","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gatech-eic/vitcod","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PLSC/tree/master/task/classification/deit","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/liuxingwt/CLS","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BR-IDL/PaddleViT/blob/main/image_classification/DeiT","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhuhanqing/lightening-transformer","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bshantam97/Attention_Based_Networks","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/smu-ivpl/DeepfakeDetection","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ttt496/vit-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aiot-mlsys-lab/famba-v","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleClas","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/code-implementation1/Code1/tree/main/DeiT","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TACJu/TransFG","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/skchen1993/TrangFG","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alibaba/EasyCV","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IMvision12/keras-vision-models","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/backbone/DeiT.py","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/asrafulashiq/deit-custom","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wangyz1608/knowledge-distillation-via-nd","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/open-edge-platform/training_extensions","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Burf/VisionTransformer-Tensorflow2","reach":null}],"summary":{"ran":9,"ran_fixture":2,"ran_honours":1,"unverified":7},"by_repo_kind":{"listed":{"samples":18,"ran":11,"repositories":8}},"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":3,"samples":[{"code_sha256_prefix":"c0bfabc05e380222","entry":"Attention","repo":"alibaba/EasyCV","repo_kind":"listed","path":"easycv/models/backbones/vision_transformer.py","file_url":"https://github.com/alibaba/EasyCV/blob/HEAD/easycv/models/backbones/vision_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c0bfabc05e380222"}},{"code_sha256_prefix":"b42ba639d4f94082","entry":"DistillationLoss","repo":"hustvl/vim","repo_kind":"listed","path":"vim/losses.py","file_url":"https://github.com/hustvl/vim/blob/HEAD/vim/losses.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":"b42ba639d4f94082"}},{"code_sha256_prefix":"fee0f891e0558ff8","entry":"DistilledVisionTransformer","repo":"holdfire/FAS","repo_kind":"listed","path":"models/deit.py","file_url":"https://github.com/holdfire/FAS/blob/HEAD/models/deit.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":"fee0f891e0558ff8"}},{"code_sha256_prefix":"c713760d26bf0a45","entry":"DropPath","repo":"alibaba/EasyCV","repo_kind":"listed","path":"easycv/models/backbones/vision_transformer.py","file_url":"https://github.com/alibaba/EasyCV/blob/HEAD/easycv/models/backbones/vision_transformer.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":"c713760d26bf0a45"}},{"code_sha256_prefix":"e089d779e4638b42","entry":"Encoder","repo":"moein-shariatnia/Pix2Seq","repo_kind":"listed","path":"model.py","file_url":"https://github.com/moein-shariatnia/Pix2Seq/blob/HEAD/model.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":"e089d779e4638b42"}},{"code_sha256_prefix":"64505a0b6aa5e3d4","entry":"Mlp","repo":"alibaba/EasyCV","repo_kind":"listed","path":"easycv/models/backbones/vision_transformer.py","file_url":"https://github.com/alibaba/EasyCV/blob/HEAD/easycv/models/backbones/vision_transformer.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":"64505a0b6aa5e3d4"}},{"code_sha256_prefix":"295ab55989f9e8fe","entry":"MultiHeadSelfAttention","repo":"omihub777/vit-cifar","repo_kind":"listed","path":"dw_vit.py","file_url":"https://github.com/omihub777/vit-cifar/blob/HEAD/dw_vit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"295ab55989f9e8fe"}},{"code_sha256_prefix":"9e38671b1e2518ec","entry":"TransformerEncoder","repo":"omihub777/vit-cifar","repo_kind":"listed","path":"dw_vit.py","file_url":"https://github.com/omihub777/vit-cifar/blob/HEAD/dw_vit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9e38671b1e2518ec"}},{"code_sha256_prefix":"5bcbd988b672cf32","entry":"_no_grad_trunc_normal_","repo":"alibaba/EasyCV","repo_kind":"listed","path":"easycv/models/backbones/vision_transformer.py","file_url":"https://github.com/alibaba/EasyCV/blob/HEAD/easycv/models/backbones/vision_transformer.py","link_basis":"first_harvest_node","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":"5bcbd988b672cf32"}},{"code_sha256_prefix":"c1c79ef7fd065038","entry":"con_loss","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"c1c79ef7fd065038"}},{"code_sha256_prefix":"c4a17f13fadc2630","entry":"hydra","repo":"alibaba/EasyCV","repo_kind":"listed","path":"easycv/models/backbones/vision_transformer.py","file_url":"https://github.com/alibaba/EasyCV/blob/HEAD/easycv/models/backbones/vision_transformer.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":"c4a17f13fadc2630"}},{"code_sha256_prefix":"462cf9fa4898bc51","entry":"trunc_normal_","repo":"alibaba/EasyCV","repo_kind":"listed","path":"easycv/models/backbones/vision_transformer.py","file_url":"https://github.com/alibaba/EasyCV/blob/HEAD/easycv/models/backbones/vision_transformer.py","link_basis":"first_harvest_node","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":"462cf9fa4898bc51"}},{"code_sha256_prefix":"bc7c311c2770067a","entry":"Block","repo":"alibaba/EasyCV","repo_kind":"listed","path":"easycv/models/backbones/vision_transformer.py","file_url":"https://github.com/alibaba/EasyCV/blob/HEAD/easycv/models/backbones/vision_transformer.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":"bc7c311c2770067a"}},{"code_sha256_prefix":"4eae8cfd26a7bed5","entry":"DeiT","repo":"UdbhavPrasad072300/Transformer-Implementations","repo_kind":"listed","path":"transformer_package/models/transformer.py","file_url":"https://github.com/UdbhavPrasad072300/Transformer-Implementations/blob/HEAD/transformer_package/models/transformer.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":"4eae8cfd26a7bed5"}},{"code_sha256_prefix":"fa8c4e7bc2b8d354","entry":"DepthwiseViT","repo":"omihub777/vit-cifar","repo_kind":"listed","path":"dw_vit.py","file_url":"https://github.com/omihub777/vit-cifar/blob/HEAD/dw_vit.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":"fa8c4e7bc2b8d354"}},{"code_sha256_prefix":"2de7c7e2fe313b48","entry":"DistilledVisionTransformer","repo":"asrafulashiq/deit-custom","repo_kind":"listed","path":"models.py","file_url":"https://github.com/asrafulashiq/deit-custom/blob/HEAD/models.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":"2de7c7e2fe313b48"}},{"code_sha256_prefix":"c152c68202903a9f","entry":"ValueError","repo":"alibaba/EasyCV","repo_kind":"listed","path":"easycv/models/backbones/vision_transformer.py","file_url":"https://github.com/alibaba/EasyCV/blob/HEAD/easycv/models/backbones/vision_transformer.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":"c152c68202903a9f"}},{"code_sha256_prefix":"a4ea24ce126312f8","entry":"VisionTransformer","repo":"alibaba/EasyCV","repo_kind":"listed","path":"easycv/models/backbones/vision_transformer.py","file_url":"https://github.com/alibaba/EasyCV/blob/HEAD/easycv/models/backbones/vision_transformer.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":"a4ea24ce126312f8"}},{"code_sha256_prefix":"d90ec8f4e83b1d6a","entry":"_add_distilation_arguments","repo":"code-implementation1/Code1","repo_kind":"listed","path":"DeiT/src/args.py","file_url":"https://github.com/code-implementation1/Code1/blob/HEAD/DeiT/src/args.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":"d90ec8f4e83b1d6a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}