{ "info": { "author": "Ivan Sorokin", "author_email": "sorokin.ivan@inbox.ru", "bugtrack_url": null, "classifiers": [ "Development Status :: 4 - Beta", "Intended Audience :: Developers", "Intended Audience :: Education", "Intended Audience :: Science/Research", "License :: OSI Approved :: MIT License", "Programming Language :: Python :: 3", "Programming Language :: Python :: 3.5", "Programming Language :: Python :: 3.6", "Programming Language :: Python :: 3.7", "Topic :: Scientific/Engineering", "Topic :: Scientific/Engineering :: Artificial Intelligence", "Topic :: Software Development", "Topic :: Software Development :: Libraries", "Topic :: Software Development :: Libraries :: Python Modules" ], "description": "# PyTorch bindings for CUDA-Warp Recurrent Neural Aligner\n\n\n```python\ndef rna_loss(\n log_probs, # type: torch.FloatTensor\n labels, # type: torch.IntTensor\n frames_lengths, # type: torch.IntTensor\n labels_lengths, # type: torch.IntTensor\n average_frames=False, # type: bool\n reduction=None, # type: Optional[AnyStr]\n blank=0, # type: int\n):\n \"\"\"The CUDA-Warp Recurrent Neural Aligner loss.\n\n Args:\n log_probs (torch.Tensor): Input tensor (float) with shape\n (T, N, U, V) where T is the maximum number of input frames, N is the\n minibatch size, U is the maximum number of output labels and V is\n the vocabulary of labels (including the blank).\n labels (torch.IntTensor): Tensor with shape (N, U-1) representing the\n reference labels for all samples in the minibatch.\n frames_lengths (torch.IntTensor): Tensor with shape (N,) representing the\n number of frames for each sample in the minibatch.\n labels_lengths (torch.IntTensor): Tensor with shape (N,) representing the\n length of the transcription for each sample in the minibatch.\n average_frames (bool, optional): Specifies whether the loss of each\n sample should be divided by its number of frames. Default: ``False''.\n reduction (string, optional): Specifies the type of reduction.\n Default: None.\n blank (int, optional): label used to represent the blank symbol.\n Default: 0.\n \"\"\"\n # type: (...) -> torch.Tensor\n```\n\n## Requirements\n\n- C++11 compiler (tested with GCC 5.4).\n- Python: 3.5, 3.6, 3.7 (tested with version 3.6).\n- [PyTorch](http://pytorch.org/) >= 1.0.0 (tested with version 1.1.0).\n- [CUDA Toolkit](https://developer.nvidia.com/cuda-zone) (tested with version 10.0).\n\n\n\n## Install\n\nCurrently, there is no compiled version of the package. The following setup instructions compile the package from the source code locally.\n\n### From Pypi\n\n```bash\npip install warp_rna\n```\n\n### From GitHub\n\n```bash\ngit clone https://github.com/1ytic/warp-rna\ncd warp-rna/pytorch_binding\npython setup.py install\n```", "description_content_type": "text/markdown", "docs_url": null, "download_url": "", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "https://github.com/1ytic/warp-rna/tree/master/pytorch_binding", "keywords": "", "license": "MIT", "maintainer": "", "maintainer_email": "", "name": "warp-rna", "package_url": "https://pypi.org/project/warp-rna/", "platform": "", "project_url": "https://pypi.org/project/warp-rna/", "project_urls": { "Homepage": "https://github.com/1ytic/warp-rna/tree/master/pytorch_binding" }, "release_url": "https://pypi.org/project/warp-rna/0.1.0/", "requires_dist": null, "requires_python": "", "summary": "PyTorch bindings for CUDA-Warp Recurrent Neural Aligner", "version": "0.1.0" }, "last_serial": 5672570, "releases": { "0.0.1": [ { "comment_text": "", "digests": { "md5": "a47183f79153097a8ff6b958a257ec7b", "sha256": "f99805d70ae82efb35f3155d17297011f9e715bbe20f83dcdd6dac4058ccd188" }, "downloads": -1, "filename": "warp_rna-0.0.1.tar.gz", "has_sig": false, "md5_digest": "a47183f79153097a8ff6b958a257ec7b", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 8347, "upload_time": "2019-08-11T07:45:55", "url": "https://files.pythonhosted.org/packages/0b/01/fbcdc84dabd2686337af7a97b50b7ff8b3c6ff5461762595e3df1c053467/warp_rna-0.0.1.tar.gz" } ], "0.0.2": [ { "comment_text": "", "digests": { "md5": "075bc50a38ea5ee7c05f5a18bea79bc2", "sha256": "b2e457aa8ee2a098331540acea03d924f62b76661bdbbbbfa7965ea5af77fa48" }, "downloads": -1, "filename": "warp_rna-0.0.2.tar.gz", "has_sig": false, "md5_digest": "075bc50a38ea5ee7c05f5a18bea79bc2", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 9346, "upload_time": "2019-08-11T07:50:54", "url": "https://files.pythonhosted.org/packages/6d/4b/5f8788dc301fad8f9f76bac6c04746a8fec59700282a27582062fc674947/warp_rna-0.0.2.tar.gz" } ], "0.1.0": [ { "comment_text": "", "digests": { "md5": "36dc65771308276cb03895cd4b888860", "sha256": "5e93ace031aeeba5b2f0b4d2225b873e62a2eb43e9cc07cb19df9cf4b9c52e3a" }, "downloads": -1, "filename": "warp_rna-0.1.0.tar.gz", "has_sig": false, "md5_digest": "36dc65771308276cb03895cd4b888860", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 9153, "upload_time": "2019-08-13T16:00:58", "url": "https://files.pythonhosted.org/packages/21/8e/5672b361a170ae6d20cbf50e021a9d5456210ccfd12b916abc632ea0f551/warp_rna-0.1.0.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "36dc65771308276cb03895cd4b888860", "sha256": "5e93ace031aeeba5b2f0b4d2225b873e62a2eb43e9cc07cb19df9cf4b9c52e3a" }, "downloads": -1, "filename": "warp_rna-0.1.0.tar.gz", "has_sig": false, "md5_digest": "36dc65771308276cb03895cd4b888860", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 9153, "upload_time": "2019-08-13T16:00:58", "url": "https://files.pythonhosted.org/packages/21/8e/5672b361a170ae6d20cbf50e021a9d5456210ccfd12b916abc632ea0f551/warp_rna-0.1.0.tar.gz" } ] }