{"id":16871801,"url":"https://github.com/desh2608/cacgmm","last_synced_at":"2026-04-20T09:34:05.603Z","repository":{"id":57663701,"uuid":"475207786","full_name":"desh2608/cacgmm","owner":"desh2608","description":"GPU-based CACGMM trainer in CuPy","archived":false,"fork":false,"pushed_at":"2022-04-11T17:08:02.000Z","size":12,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-07-03T08:54:41.657Z","etag":null,"topics":["blind-source-separation"],"latest_commit_sha":null,"homepage":"","language":"Python","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/desh2608.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":"2022-03-28T23:09:29.000Z","updated_at":"2025-06-24T01:57:21.000Z","dependencies_parsed_at":"2022-08-28T00:11:51.119Z","dependency_job_id":null,"html_url":"https://github.com/desh2608/cacgmm","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/desh2608/cacgmm","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/desh2608%2Fcacgmm","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/desh2608%2Fcacgmm/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/desh2608%2Fcacgmm/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/desh2608%2Fcacgmm/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/desh2608","download_url":"https://codeload.github.com/desh2608/cacgmm/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/desh2608%2Fcacgmm/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":269606235,"owners_count":24446147,"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","status":"online","status_checked_at":"2025-08-09T02:00:10.424Z","response_time":111,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["blind-source-separation"],"created_at":"2024-10-13T15:09:46.961Z","updated_at":"2026-04-20T09:34:00.577Z","avatar_url":"https://github.com/desh2608.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# GPU-based CACGMM trainer in CuPy\n\nThis package adapts the complex angular GMM model and trainer from [pb_bss](https://github.com/fgnt/pb_bss) \nusing [CuPy](https://github.com/cupy/cupy) for accelerated inference on the GPU.\n\nAt the moment, it is meant to be used with the [GSS](https://github.com/desh2608/gss) toolkit, but\nit can also be used as a general CACGMM trainer tool.\n\n## Installation\n\n```bash\n\u003e pip install cupy-cuda102  # modify according to your CUDA version (https://docs.cupy.dev/en/stable/install.html#installing-cupy)\n\u003e pip install cacgmm-gpu\n```\n\n## Usage\n\n```python\nfrom cacgmm.cacgmm_trainer import CACGMMTrainer\n\nimport cupy as cp\n\nsource_activity = cp.random.rand(2, 1000)\nsource_activity = source_activity / cp.sum(initialization, keepdims=True, axis=0)\n\ninitialization = cp.repeat(source_activity[None, ...], 513, axis=0)  # F x K x T\nsource_active_mask = cp.repeat(source_activity[None, ...], 513, axis=0)\nX = cp.random.rand(4, 1000, 513)    # D x T x F\n\ncacGMM = CACGMMTrainer()\n\ncur = cacGMM.fit(\n    y=X.T,\n    initialization=initialization,\n    iterations=10,\n    source_activity_mask=source_active_mask,\n)\n\naffiliation = cur.predict(X.T, source_activity_mask=source_active_mask) # \nposterior = affiliation.transpose(1, 2, 0)  # K x T x F\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdesh2608%2Fcacgmm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdesh2608%2Fcacgmm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdesh2608%2Fcacgmm/lists"}