{"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/model-rubik-s-cube-twisting-resolution-depth","title":"Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets","arxiv_id":"2010.14819","date":"2020-10-28","proceeding":null,"authors":["Kai Han","Yunhe Wang","Qiulin Zhang","Wei zhang","Chunjing Xu","Tong Zhang"],"abstract":"To obtain excellent deep neural architectures, a series of techniques are carefully designed in EfficientNets. The giant formula for simultaneously enlarging the resolution, depth and width provides us a Rubik's cube for neural networks. So that we can find networks with high efficiency and excellent performance by twisting the three dimensions. This paper aims to explore the twisting rules for obtaining deep neural networks with minimum model sizes and computational costs. Different from the network enlarging, we observe that resolution and depth are more important than width for tiny networks. Therefore, the original method, i.e., the compound scaling in EfficientNet is no longer suitable. To this end, we summarize a tiny formula for downsizing neural architectures through a series of smaller models derived from the EfficientNet-B0 with the FLOPs constraint. Experimental results on the ImageNet benchmark illustrate that our TinyNet performs much better than the smaller version of EfficientNets using the inversed giant formula. For instance, our TinyNet-E achieves a 59.9% Top-1 accuracy with only 24M FLOPs, which is about 1.9% higher than that of the previous best MobileNetV3 with similar computational cost. Code will be available at https://github.com/huawei-noah/ghostnet/tree/master/tinynet_pytorch, and https://gitee.com/mindspore/mindspore/tree/master/model_zoo/research/cv/tinynet.","url_abs":"https://arxiv.org/abs/2010.14819v2","url_pdf":"https://arxiv.org/pdf/2010.14819v2.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":"model-rubik-s-cube-twisting-resolution-depth","repo_url":"https://github.com/huawei-noah/CV-backbones","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"model-rubik-s-cube-twisting-resolution-depth","repo_url":"https://github.com/huawei-noah/ghostnet/tree/master/tinynet_pytorch","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"model-rubik-s-cube-twisting-resolution-depth","repo_url":"https://github.com/james77777778/keras-image-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"model-rubik-s-cube-twisting-resolution-depth","repo_url":"https://github.com/jiajunhua/CV-Backbones","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"model-rubik-s-cube-twisting-resolution-depth","repo_url":"https://github.com/rwightman/pytorch-image-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"model-rubik-s-cube-twisting-resolution-depth","repo_url":"https://github.com/2023-MindSpore-1/ms-code-217/tree/main/tinynet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"model-rubik-s-cube-twisting-resolution-depth","repo_url":"https://github.com/MindSpore-paper-code-2/code3/tree/main/tinynet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"model-rubik-s-cube-twisting-resolution-depth","repo_url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/mobilenetv3_family","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"model-rubik-s-cube-twisting-resolution-depth","repo_url":"https://github.com/mindspore-ai/models/tree/master/research/cv/tinynet","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":"rubik-s-cube","task_name":"Rubik's Cube"}],"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":"ghost-bottleneck","method_name":"Ghost Bottleneck"},{"method_slug":"ghost-module","method_name":"Ghost Module"},{"method_slug":"ghostnet","method_name":"GhostNet"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"hard-swish","method_name":"Hard Swish"},{"method_slug":"inverted-residual-block","method_name":"Inverted Residual Block"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"rmsprop","method_name":"RMSProp"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"relu6","method_name":"ReLU6"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"squeeze-and-excitation-block","method_name":"Squeeze-and-Excitation Block"},{"method_slug":"tinynet","method_name":"TinyNet"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"TinyNet (GhostNet-A)","rank_in_archive_order":759,"of":1060,"metrics":{"GFLOPs":"0.591","Number of params":"11.9M","Top 1 Accuracy":"79.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"TinyNet-A + RA","rank_in_archive_order":866,"of":1060,"metrics":{"GFLOPs":"0.339","Number of params":"5.1M","Top 1 Accuracy":"77.7%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.14819","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.14819"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/mobilenetv3_family","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-paper-code-2/code3/tree/main/tinynet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-1/ms-code-217/tree/main/tinynet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/james77777778/keras-image-models","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/tinynet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huawei-noah/CV-backbones","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huawei-noah/ghostnet/tree/master/tinynet_pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jiajunhua/CV-Backbones","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"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":1,"samples":[{"code_sha256_prefix":"345a84870c4c0e35","entry":"_gen_tinynet","repo":"jiajunhua/CV-Backbones","repo_kind":"listed","path":"tinynet_pytorch/tinynet.py","file_url":"https://github.com/jiajunhua/CV-Backbones/blob/HEAD/tinynet_pytorch/tinynet.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":"345a84870c4c0e35"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}