# singleline_models
<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->
## Install
``` sh
pip install singleline_models
```
## Models
### Sketch RNN
[PyTorch](https://pytorch.org) implementation of the SketchRNN paper, [A
Neural Representation of Sketch
Drawings](https://arxiv.org/abs/1704.03477).
Sketch RNN learns to reconstruct stroke-based drawings, by predicting a
series of strokes. It uses a sequence-to-sequence LSTM model, with
gaussian mixture heads to produce a sequence of stroke coordinates.
### Datasets
- `data/quickdraw/`: Sample data from [Quick, Draw!
Dataset](https://github.com/googlecreativelab/quickdraw-dataset)
- `data/look/`: Custom dataset of single-line drawings by @andrewlook
All data is stored in stroke-3 format, meaning a list with three
columns:
- `delta_x`
- `delta_y`
- `lift_pen` (if `1`, “lift the pen” and start a new stroke; otherwise
`0`)
### Acknowledgements
- [PyTorch Sketch
RNN](https://github.com/alexis-jacq/Pytorch-Sketch-RNN) project by
[Alexis David Jacq](https://github.com/alexis-jacq)
- [Annotated Sketch RNN in
PyTorch](https://nn.labml.ai/sketch_rnn/index.html) by
[LabML](https://nn.labml.ai/)
- [Tensorflow
SketchRNN](https://github.com/magenta/magenta/blob/main/magenta/models/sketch_rnn/README.md)
by [Magenta Team](https://magenta.tensorflow.org/) and [David
Ha](https://github.com/hardmaru)
- [sketch-rnn-datasets](https://github.com/hardmaru/sketch-rnn-datasets)
by [David Ha](https://github.com/hardmaru)
- [SketchRNN-Pytorch](https://github.com/OhataKenji/SketchRNN-Pytorch)
by [OhataKenji](https://github.com/OhataKenji)
### Improvements
- [x] Log epoch and learning rate
- [x] LR decay
- [x] ETA decay (for KL loss)
- [x] Dropout
- [x] Layer Normalization
- [x] Recurrent Dropout
Raw data
{
"_id": null,
"home_page": "https://github.com/andrewlook/singleline_models",
"name": "singleline-models",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": "",
"keywords": "nbdev jupyter notebook python",
"author": "Andrew Look",
"author_email": "andrew.m.look@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/0b/92/b9ab1a933381fb4c0f1eba6d9152036b0e38bcfbaf9fd95769117cc2b1a8/singleline_models-0.0.2.tar.gz",
"platform": null,
"description": "# singleline_models\n\n<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->\n\n## Install\n\n``` sh\npip install singleline_models\n```\n\n## Models\n\n### Sketch RNN\n\n[PyTorch](https://pytorch.org) implementation of the SketchRNN paper, [A\nNeural Representation of Sketch\nDrawings](https://arxiv.org/abs/1704.03477).\n\nSketch RNN learns to reconstruct stroke-based drawings, by predicting a\nseries of strokes. It uses a sequence-to-sequence LSTM model, with\ngaussian mixture heads to produce a sequence of stroke coordinates.\n\n\n\n### Datasets\n\n- `data/quickdraw/`: Sample data from [Quick, Draw!\n Dataset](https://github.com/googlecreativelab/quickdraw-dataset)\n- `data/look/`: Custom dataset of single-line drawings by @andrewlook\n\nAll data is stored in stroke-3 format, meaning a list with three\ncolumns:\n\n- `delta_x`\n- `delta_y`\n- `lift_pen` (if `1`, \u201clift the pen\u201d and start a new stroke; otherwise\n `0`)\n\n\n\n### Acknowledgements\n\n- [PyTorch Sketch\n RNN](https://github.com/alexis-jacq/Pytorch-Sketch-RNN) project by\n [Alexis David Jacq](https://github.com/alexis-jacq)\n- [Annotated Sketch RNN in\n PyTorch](https://nn.labml.ai/sketch_rnn/index.html) by\n [LabML](https://nn.labml.ai/)\n- [Tensorflow\n SketchRNN](https://github.com/magenta/magenta/blob/main/magenta/models/sketch_rnn/README.md)\n by [Magenta Team](https://magenta.tensorflow.org/) and [David\n Ha](https://github.com/hardmaru)\n- [sketch-rnn-datasets](https://github.com/hardmaru/sketch-rnn-datasets)\n by [David Ha](https://github.com/hardmaru)\n- [SketchRNN-Pytorch](https://github.com/OhataKenji/SketchRNN-Pytorch)\n by [OhataKenji](https://github.com/OhataKenji)\n\n### Improvements\n\n- [x] Log epoch and learning rate\n- [x] LR decay\n- [x] ETA decay (for KL loss)\n- [x] Dropout\n- [x] Layer Normalization\n- [x] Recurrent Dropout\n\n\n",
"bugtrack_url": null,
"license": "Apache Software License 2.0",
"summary": "ML Models for Single-Line Drawings",
"version": "0.0.2",
"project_urls": {
"Homepage": "https://github.com/andrewlook/singleline_models"
},
"split_keywords": [
"nbdev",
"jupyter",
"notebook",
"python"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "8795886fead8aa7e990d52327f578673e3084b53fb310ac5bd9ab5875b03917b",
"md5": "cf7b2a2b2a259d33849bf3fb3b5ed493",
"sha256": "4e42933d9cf39c66bb3cea527bbd485c536de5b24281ce5822896110f76c1b1f"
},
"downloads": -1,
"filename": "singleline_models-0.0.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "cf7b2a2b2a259d33849bf3fb3b5ed493",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 47307,
"upload_time": "2024-02-29T20:28:05",
"upload_time_iso_8601": "2024-02-29T20:28:05.543993Z",
"url": "https://files.pythonhosted.org/packages/87/95/886fead8aa7e990d52327f578673e3084b53fb310ac5bd9ab5875b03917b/singleline_models-0.0.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "0b92b9ab1a933381fb4c0f1eba6d9152036b0e38bcfbaf9fd95769117cc2b1a8",
"md5": "3442f540de607b0d4b211a099cca9be8",
"sha256": "a0dd54afaf7bd7e4a503a729b1af1d27f25ca1f521d1f591476ba30c94f6a99b"
},
"downloads": -1,
"filename": "singleline_models-0.0.2.tar.gz",
"has_sig": false,
"md5_digest": "3442f540de607b0d4b211a099cca9be8",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 37684,
"upload_time": "2024-02-29T20:28:06",
"upload_time_iso_8601": "2024-02-29T20:28:06.730408Z",
"url": "https://files.pythonhosted.org/packages/0b/92/b9ab1a933381fb4c0f1eba6d9152036b0e38bcfbaf9fd95769117cc2b1a8/singleline_models-0.0.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-02-29 20:28:06",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "andrewlook",
"github_project": "singleline_models",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "singleline-models"
}
JSON
