{"id":13526143,"url":"https://github.com/edouardoyallon/pyscatwave","last_synced_at":"2025-04-09T09:07:48.954Z","repository":{"id":54491398,"uuid":"86152173","full_name":"edouardoyallon/pyscatwave","owner":"edouardoyallon","description":"Fast Scattering Transform with CuPy/PyTorch","archived":false,"fork":false,"pushed_at":"2020-02-22T23:17:37.000Z","size":3187,"stargazers_count":297,"open_issues_count":1,"forks_count":48,"subscribers_count":16,"default_branch":"master","last_synced_at":"2025-04-02T06:09:40.609Z","etag":null,"topics":["deep-learning","pytorch","scattering-transform"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/1703.08961","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/edouardoyallon.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2017-03-25T11:21:50.000Z","updated_at":"2025-01-23T05:56:54.000Z","dependencies_parsed_at":"2022-08-13T17:40:22.403Z","dependency_job_id":null,"html_url":"https://github.com/edouardoyallon/pyscatwave","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/edouardoyallon%2Fpyscatwave","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/edouardoyallon%2Fpyscatwave/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/edouardoyallon%2Fpyscatwave/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/edouardoyallon%2Fpyscatwave/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/edouardoyallon","download_url":"https://codeload.github.com/edouardoyallon/pyscatwave/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248008630,"owners_count":21032556,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","pytorch","scattering-transform"],"created_at":"2024-08-01T06:01:25.724Z","updated_at":"2025-04-09T09:07:48.919Z","avatar_url":"https://github.com/edouardoyallon.png","language":"Python","funding_links":[],"categories":["Python (1887)","Python","PyTorch论文推荐","Paper implementations｜论文实现","Paper implementations","Paper Implementations"],"sub_categories":["Other libraries｜其他库:","Other libraries:"],"readme":"Announcement \n==========\n\n11/18\n\nThis package is no longer supported. We have now released kymatio: http://www.kymat.io/ , https://github.com/kymatio/kymatio which includes 1D-2D-3D fast, optimized, differentiable Scattering Transform and subsumes all the behavior of pyscatwave. Among other things you can now more easily use differentiable 2d scattering and use the CPU if desired. kymatio will be well supported with a substantially larger development team than pyscatwave.\n\n07/18\n\nWe just released a differentiable 2D Scattering example in the master. It is not memory efficient yet, neither fast.\n\n\nPyScatWave\n==========\n\nCuPy/PyTorch Scattering implementation\n\nA scattering network is a Convolutional Network with filters predefined to be wavelets that are not learned and it can be used in vision task such as classification of images. The scattering transform can drastically reduce the spatial resolution of the input (e.g. 224x224-\u003e14x14) with demonstrably neglible loss in dicriminative power.   \n\nThe software uses PyTorch + NumPy FFT on CPU, and PyTorch + CuPy + CuFFT on GPU.\n\n\n\nPrevious (lua-based) versions of the code can be found at \u003chttps://github.com/edouardoyallon/scatwave\u003e\n\nIf using this code for your research please cite our paper:\n\nE. Oyallon, E. Belilovsky, S. Zagoruyko [*Scaling the Scattering Transform: Deep Hybrid Networks*](https://arxiv.org/abs/1703.08961)\n\nYou can find experiments from the paper in the following repository:\nhttps://github.com/edouardoyallon/scalingscattering/\n\nWe used PyTorch for running experiments in \u003chttps://arxiv.org/abs/1703.08961\u003e,\nbut it is possible to use scattering with other frameworks (e.g. Chainer, Theano or Tensorflow) if one copies Scattering outputs to CPU (or run on CPU and convert to `numpy.ndarray` via `.numpy()`).\n\n## Benchmarks\nWe do some simple timings and comparisons to the previous (multi-core CPU) implementation of scattering (ScatnetLight). We benchmark the software using a 1080 GPU. Below we show input sizes (WxHx3xBatchSize) and speed:\n\n32 × 32 × 3 × 128 (J=2)- 0.03s (speed of 8x vs ScatNetLight)\n\n256 × 256 × 3 × 128 (J=2) - 0.71 s (speed up of 225x vs ScatNetLight)\n\n## Installation\n\nThe software was tested on Linux with anaconda Python 2.7 and\nvarious GPUs, including Titan X, 1080s, 980s, K20s, and Titan X Pascal.\n\nThe first step is to install pytorch following instructions from\n\u003chttp://pytorch.org\u003e, then you can run `pip`:\n\n```\npip install -r requirements.txt\npython setup.py install\n```\n\n## Usage\n\nExample:\n\n```python\nimport torch\nfrom scatwave.scattering import Scattering\n\nscat = Scattering(M=32, N=32, J=2).cuda()\nx = torch.randn(1, 3, 32, 32).cuda()\n\nprint scat(x).size()\n```\n\n\n## Contribution\n\nAll contributions are welcome.\n\n\n## Authors\n\nEdouard Oyallon, Eugene Belilovsky, Sergey Zagoruyko\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fedouardoyallon%2Fpyscatwave","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fedouardoyallon%2Fpyscatwave","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fedouardoyallon%2Fpyscatwave/lists"}