{"id":22850267,"url":"https://github.com/unipr-org/deep-neural-network","last_synced_at":"2025-05-07T04:45:22.837Z","repository":{"id":238994923,"uuid":"792264133","full_name":"unipr-org/deep-neural-network","owner":"unipr-org","description":"Deep Neural Network Library: A flexible C++ library for building, training, and using deep neural networks. Modular, easy-to-use, and high-performance.","archived":false,"fork":false,"pushed_at":"2024-05-27T06:25:49.000Z","size":23540,"stargazers_count":4,"open_issues_count":0,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-05-07T04:45:18.819Z","etag":null,"topics":["artificial-intelligence","artificial-neural-networks","cpp","deep-neural-networks","machine-learning"],"latest_commit_sha":null,"homepage":"","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/unipr-org.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-04-26T10:03:29.000Z","updated_at":"2025-01-24T13:06:56.000Z","dependencies_parsed_at":null,"dependency_job_id":"a6796650-eb2f-49a1-8a3a-9e4d39668e84","html_url":"https://github.com/unipr-org/deep-neural-network","commit_stats":null,"previous_names":["unipr-org/deep-neural-network"],"tags_count":0,"template":true,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/unipr-org%2Fdeep-neural-network","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/unipr-org%2Fdeep-neural-network/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/unipr-org%2Fdeep-neural-network/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/unipr-org%2Fdeep-neural-network/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/unipr-org","download_url":"https://codeload.github.com/unipr-org/deep-neural-network/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252816520,"owners_count":21808702,"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":["artificial-intelligence","artificial-neural-networks","cpp","deep-neural-networks","machine-learning"],"created_at":"2024-12-13T05:07:01.327Z","updated_at":"2025-05-07T04:45:22.816Z","avatar_url":"https://github.com/unipr-org.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Deep Neural Network\n\n## Dependencies\n\n- [spdlog](https://github.com/gabime/spdlog)\n- [doxygen](https://www.doxygen.nl/)\n\n## How to compile\n\n```bash\nmkdir build\ncd build\ncmake ..\nmake\n```\n\nTo turn on all types of logs use `cmake -DDEBUG=ON`.\n\n## How to add and run tests\nFilenames of tests **must** be compliant to the following patterns:\n\n| Source | Input |\n| ------------- | -------------- |\n| `test_*.cpp` | `test_*.txt` |\n\nand all tests must be in the `test` directory.\n\nAfter the compilation phase, inside the `build` directory run, you can run all tests with:\n\n```bash\nctest # -V for verbose output\n```\n\nTo execute a single test: \n\n```bash\n./test/test_\u003ctest_name\u003e\n```\n\nor refer to the CMake [doc](https://cmake.org/cmake/help/book/mastering-cmake/chapter/Testing%20With%20CMake%20and%20CTest.html#testing-using-ctest).\n\n### Example test\nYou can run an example test with:\n```bash\n./test/test_DefaultTrainer\n```\n\n---\n\n## Generate documentation\n\nSimply run in the build directory\n\n```bash\nmake documentation\n```\n\nand look for the `index.html` inside `doc/html/`.\n\n---\n\n## TODO-List\n\n- [x] Utilizzo di C++ 11\n- [x] Implementare classi astratte (interfacce)\n- [x] Cambiare nomi variabili private (`_`)\n- [x] Funzioni inline\n- [x] Rimozione classe Connection\n- [x] Rimuovere `bool isBias`\n- [x] Utilizzo namespace e alias\n- [x] Const correctess \n- [x] Operator []\n- [x] Salvataggio stato rete\n- [x] Funzione caricamento pesi\n- [x] Caricamento struttura rete da file\n- [x] Classe Loader\n- [x] Adattare metodi per il salvataggio e caricamento della rete nella classe Loader\n- [x] Algoritmo di backpropagation\n- [x] Generazione training e test set\n- [x] Lettura training set\n- [x] Libreria matematica\n- [x] Sistemare scelta del passo per l'algoritmo di back-prop\n- [x] Ridirigere l'output della compilazione di doxygen da qualche altra parte\n- [x] Algoritmo di testing\n- [x] Implementare funzione test e statistiche\n- [x] Metodo getActivationFunction che restituisce g() e con una mappa otteniamo g’()\n- [ ] Parallelizzazione (`thread`)\n- [ ] Scrivere la documentazione mancante\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Funipr-org%2Fdeep-neural-network","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Funipr-org%2Fdeep-neural-network","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Funipr-org%2Fdeep-neural-network/lists"}