{"id":21622587,"url":"https://github.com/jpuigcerver/nnutils","last_synced_at":"2025-04-11T11:12:36.337Z","repository":{"id":55962716,"uuid":"113714836","full_name":"jpuigcerver/nnutils","owner":"jpuigcerver","description":"CPU \u0026 CUDA implementation of several neural network utils","archived":false,"fork":false,"pushed_at":"2022-11-07T19:53:36.000Z","size":221,"stargazers_count":5,"open_issues_count":1,"forks_count":7,"subscribers_count":5,"default_branch":"pytorch-1.6.0","last_synced_at":"2024-04-25T22:01:59.742Z","etag":null,"topics":["cuda","deep-learning","neural-networks","openmp","pytorch"],"latest_commit_sha":null,"homepage":"","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jpuigcerver.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2017-12-10T01:50:30.000Z","updated_at":"2023-06-07T03:41:35.000Z","dependencies_parsed_at":"2022-08-15T10:20:45.248Z","dependency_job_id":null,"html_url":"https://github.com/jpuigcerver/nnutils","commit_stats":null,"previous_names":[],"tags_count":3,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jpuigcerver%2Fnnutils","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jpuigcerver%2Fnnutils/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jpuigcerver%2Fnnutils/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jpuigcerver%2Fnnutils/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jpuigcerver","download_url":"https://codeload.github.com/jpuigcerver/nnutils/tar.gz/refs/heads/pytorch-1.6.0","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248381791,"owners_count":21094528,"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":["cuda","deep-learning","neural-networks","openmp","pytorch"],"created_at":"2024-11-25T00:09:13.996Z","updated_at":"2025-04-11T11:12:36.314Z","avatar_url":"https://github.com/jpuigcerver.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# nnutils\n\n[![Build Status](https://travis-ci.org/jpuigcerver/nnutils.svg?branch=master)](https://travis-ci.org/jpuigcerver/nnutils)\n\nImplementation of different neural network-related utilities for\nCPUs and GPUs (CUDA).\n\nSo far, most of the utils are related to my need of working with images of\ndifferent sizes grouped into batches with padding.\n\n## Included utils\n\n- Masking images by size\n\nIf you are grouping images of different sizes into batches padded with zeros,\nyou may need to mask the output/input tensors after/before some layers.\nThis layer is very handy in these cases.\n\n- Adaptive pooling\n\nAdaptive pooling layers included in several packages like Torch or PyTorch\nassume that all images in the batch have the same size. My implementation\ntakes into account the size of each individual image within the batch to\napply the adaptive pooling. Current layers include: Average and maximum\nadaptive pooling.\n\n## Requirements\n\n### Minimum:\n- C++14 compiler (tested with GCC 6.4.0 and 7.5.0).\n- [CMake 3.0](https://cmake.org/).\n\n### Recommended:\n- For GPU support: [CUDA Toolkit](https://developer.nvidia.com/cuda-zone).\n- For running tests: [Google Test](https://github.com/google/googletest).\n\n### PyTorch bindings:\n- Python: 3.6, 3.7 and 3.8.\n- [PyTorch 1.6.0](http://pytorch.org/).\n\n## Installation\n\nThe installation process should be pretty straightforward assuming that you\nhave correctly installed the required libraries and tools.\n\n### PyTorch bindings (recommended)\n\n```bash\ngit clone https://github.com/jpuigcerver/nnutils.git\ncd nnutils/pytorch\npython setup.py build\npython setup.py install\n```\n\n### Standalone C++ library\n\n```bash\ngit clone https://github.com/jpuigcerver/nnutils.git\nmkdir -p nnutils/build\ncd nnutils/build\ncmake ..\nmake\nmake install\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjpuigcerver%2Fnnutils","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjpuigcerver%2Fnnutils","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjpuigcerver%2Fnnutils/lists"}