{
    "info": {
        "author": "Guild AI",
        "author_email": "packages@guild.ai",
        "bugtrack_url": null,
        "classifiers": [],
        "description": "gpkg.object-detect.models\n#########################\n\n*Object detection models (Guild AI)*\n\nModels\n######\n\nfaster-rcnn-resnet-101\n======================\n\n*Faster RCNN with ResNet 101*\n\nOperations\n^^^^^^^^^^\n\ndetect\n------\n\n*Detect images using a trained detector*\n\nFlags\n`````\n\n**images**\n  *Directory containing images to detect (required)*\n\nevaluate\n--------\n\n*Evaluate a trained detector*\n\nFlags\n`````\n\n**eval-examples**\n  *Number of examples to evaluate (all available)*\n\nexport-and-freeze\n-----------------\n\n*Export a detection graph with checkpoint weights*\n\nFlags\n`````\n\n**step**\n  *Checkpoint step to use for the frozen graph (latest checkpoint)*\n\ntrain\n-----\n\n*Train detector from scratch*\n\nFlags\n`````\n\n**batch-size**\n  *Number of examples in each training batch*\n\n**clones**\n  *Number of model clones. (1)\n\n  This flag has no effect unless `legacy` is `yes`.\n\n  Set this value to the number of available GPUs for multi-GPU training.\n\n  *\n\n**eval-examples**\n  *Number of examples to evaluate after training (all available)\n\n  This flag has no effect if `legacy` is `yes` (legacy train does not\n  perform evaluation).\n\n  *\n\n**legacy**\n  *Use legacy training for object detection (no)\n\n  Multi GPU support is only available with legacy training.\n\n  Unlike default training, legacy training does not perform an evaluation\n  after training.\n\n  Choices:\n    yes  Use legacy training (select for multi GPU support)\n    no   Use default training (does not support multiple GPUs)\n\n  *\n\n**quantize**\n  *Whether or not to quantize model weights (no)*\n\n**quantize-delay**\n  *Number of steps to train before quantizing*\n\n**train-steps**\n  *Number of steps to train (train indefinitely)*\n\ntransfer-learn\n--------------\n\n*Train detector using transfer learning*\n\nFlags\n`````\n\n**batch-size**\n  *Number of examples in each training batch*\n\n**clones**\n  *Number of model clones. (1)\n\n  This flag has no effect unless `legacy` is `yes`.\n\n  Set this value to the number of available GPUs for multi-GPU training.\n\n  *\n\n**eval-examples**\n  *Number of examples to evaluate after training (all available)\n\n  This flag has no effect if `legacy` is `yes` (legacy train does not\n  perform evaluation).\n\n  *\n\n**legacy**\n  *Use legacy training for object detection (no)\n\n  Multi GPU support is only available with legacy training.\n\n  Unlike default training, legacy training does not perform an evaluation\n  after training.\n\n  Choices:\n    yes  Use legacy training (select for multi GPU support)\n    no   Use default training (does not support multiple GPUs)\n\n  *\n\n**quantize**\n  *Whether or not to quantize model weights (no)*\n\n**quantize-delay**\n  *Number of steps to train before quantizing*\n\n**train-steps**\n  *Number of steps to train (train indefinitely)*\n\n\nfaster-rcnn-resnet-50\n=====================\n\n*Faster RCNN with ResNet 50*\n\nOperations\n^^^^^^^^^^\n\ndetect\n------\n\n*Detect images using a trained detector*\n\nFlags\n`````\n\n**images**\n  *Directory containing images to detect (required)*\n\nevaluate\n--------\n\n*Evaluate a trained detector*\n\nFlags\n`````\n\n**eval-examples**\n  *Number of examples to evaluate (all available)*\n\nexport-and-freeze\n-----------------\n\n*Export a detection graph with checkpoint weights*\n\nFlags\n`````\n\n**step**\n  *Checkpoint step to use for the frozen graph (latest checkpoint)*\n\ntrain\n-----\n\n*Train detector from scratch*\n\nFlags\n`````\n\n**batch-size**\n  *Number of examples in each training batch*\n\n**clones**\n  *Number of model clones. (1)\n\n  This flag has no effect unless `legacy` is `yes`.\n\n  Set this value to the number of available GPUs for multi-GPU training.\n\n  *\n\n**eval-examples**\n  *Number of examples to evaluate after training (all available)\n\n  This flag has no effect if `legacy` is `yes` (legacy train does not\n  perform evaluation).\n\n  *\n\n**legacy**\n  *Use legacy training for object detection (no)\n\n  Multi GPU support is only available with legacy training.\n\n  Unlike default training, legacy training does not perform an evaluation\n  after training.\n\n  Choices:\n    yes  Use legacy training (select for multi GPU support)\n    no   Use default training (does not support multiple GPUs)\n\n  *\n\n**quantize**\n  *Whether or not to quantize model weights (no)*\n\n**quantize-delay**\n  *Number of steps to train before quantizing*\n\n**train-steps**\n  *Number of steps to train (train indefinitely)*\n\ntransfer-learn\n--------------\n\n*Train detector using transfer learning*\n\nFlags\n`````\n\n**batch-size**\n  *Number of examples in each training batch*\n\n**clones**\n  *Number of model clones. (1)\n\n  This flag has no effect unless `legacy` is `yes`.\n\n  Set this value to the number of available GPUs for multi-GPU training.\n\n  *\n\n**eval-examples**\n  *Number of examples to evaluate after training (all available)\n\n  This flag has no effect if `legacy` is `yes` (legacy train does not\n  perform evaluation).\n\n  *\n\n**legacy**\n  *Use legacy training for object detection (no)\n\n  Multi GPU support is only available with legacy training.\n\n  Unlike default training, legacy training does not perform an evaluation\n  after training.\n\n  Choices:\n    yes  Use legacy training (select for multi GPU support)\n    no   Use default training (does not support multiple GPUs)\n\n  *\n\n**quantize**\n  *Whether or not to quantize model weights (no)*\n\n**quantize-delay**\n  *Number of steps to train before quantizing*\n\n**train-steps**\n  *Number of steps to train (train indefinitely)*\n\n\npet-images\n==========\n\n*Annotated images from Oxford-IIIT pet dataset*\n\nOperations\n^^^^^^^^^^\n\nprepare\n-------\n\n*Prepares pet images for training*\n\n\nssd-mobilenet-v2\n================\n\n*SSD with MobileNet v2*\n\nOperations\n^^^^^^^^^^\n\ndetect\n------\n\n*Detect images using a trained detector*\n\nFlags\n`````\n\n**images**\n  *Directory containing images to detect (required)*\n\nevaluate\n--------\n\n*Evaluate a trained detector*\n\nFlags\n`````\n\n**eval-examples**\n  *Number of examples to evaluate (all available)*\n\nexport-and-freeze\n-----------------\n\n*Export a detection graph with checkpoint weights*\n\nFlags\n`````\n\n**step**\n  *Checkpoint step to use for the frozen graph (latest checkpoint)*\n\n**tflite**\n  *Whether or not to export graph with support for TensorFlow Lite (no)\n\n  Choices:\n    yes  Export graph with support for TensorFlow Lite\n    no   Export graph normally\n\n  *\n\ntrain\n-----\n\n*Train detector from scratch*\n\nFlags\n`````\n\n**batch-size**\n  *Number of examples in each training batch*\n\n**clones**\n  *Number of model clones. (1)\n\n  This flag has no effect unless `legacy` is `yes`.\n\n  Set this value to the number of available GPUs for multi-GPU training.\n\n  *\n\n**eval-examples**\n  *Number of examples to evaluate after training (all available)\n\n  This flag has no effect if `legacy` is `yes` (legacy train does not\n  perform evaluation).\n\n  *\n\n**legacy**\n  *Use legacy training for object detection (no)\n\n  Multi GPU support is only available with legacy training.\n\n  Unlike default training, legacy training does not perform an evaluation\n  after training.\n\n  Choices:\n    yes  Use legacy training (select for multi GPU support)\n    no   Use default training (does not support multiple GPUs)\n\n  *\n\n**quantize**\n  *Whether or not to quantize model weights (no)*\n\n**quantize-delay**\n  *Number of steps to train before quantizing*\n\n**train-steps**\n  *Number of steps to train (train indefinitely)*\n\ntransfer-learn\n--------------\n\n*Train detector using transfer learning*\n\nFlags\n`````\n\n**batch-size**\n  *Number of examples in each training batch*\n\n**clones**\n  *Number of model clones. (1)\n\n  This flag has no effect unless `legacy` is `yes`.\n\n  Set this value to the number of available GPUs for multi-GPU training.\n\n  *\n\n**eval-examples**\n  *Number of examples to evaluate after training (all available)\n\n  This flag has no effect if `legacy` is `yes` (legacy train does not\n  perform evaluation).\n\n  *\n\n**legacy**\n  *Use legacy training for object detection (no)\n\n  Multi GPU support is only available with legacy training.\n\n  Unlike default training, legacy training does not perform an evaluation\n  after training.\n\n  Choices:\n    yes  Use legacy training (select for multi GPU support)\n    no   Use default training (does not support multiple GPUs)\n\n  *\n\n**quantize**\n  *Whether or not to quantize model weights (no)*\n\n**quantize-delay**\n  *Number of steps to train before quantizing*\n\n**train-steps**\n  *Number of steps to train (train indefinitely)*\n\n\nvoc-2008-images\n===============\n\n*Visual Object Classes Challenge 2008 images*\n\nOperations\n^^^^^^^^^^\n\nprepare\n-------\n\n*Prepare images annotated using Pascal VOC format*\n\nFlags\n`````\n\n**random-seed**\n  *Seed used for train/validation split (randomly generated)*\n\n**val-split**\n  *Percentage of images reserved for validation (30)*\n\n\nvoc-annotated-images\n====================\n\n*Images annotated using Pascal VOC format*\n\nOperations\n^^^^^^^^^^\n\nprepare\n-------\n\n*Prepare images annotated using Pascal VOC format*\n\nFlags\n`````\n\n**annotations**\n  *Directory containing image annotations (required)*\n\n**images**\n  *Directory containing images to prepare (required)*\n\n**random-seed**\n  *Seed used for train/validation split (randomly generated)*\n\n**val-split**\n  *Percentage of images reserved for validation (30)*\n\n\n\n",
        "description_content_type": "",
        "docs_url": null,
        "download_url": "",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/guildai/packages/tree/master/gpkg/object_detect/models",
        "keywords": "gpkg",
        "license": "Apache 2.0",
        "maintainer": "",
        "maintainer_email": "",
        "name": "gpkg.object-detect.models",
        "package_url": "https://pypi.org/project/gpkg.object-detect.models/",
        "platform": "",
        "project_url": "https://pypi.org/project/gpkg.object-detect.models/",
        "project_urls": {
            "Homepage": "https://github.com/guildai/packages/tree/master/gpkg/object_detect/models"
        },
        "release_url": "https://pypi.org/project/gpkg.object-detect.models/0.5.1/",
        "requires_dist": [
            "gpkg.object-detect"
        ],
        "requires_python": "",
        "summary": "Object detection models (Guild AI)",
        "version": "0.5.1"
    },
    "last_serial": 4453885,
    "releases": {
        "0.5.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "aee7cfce7d73412350ef4d650e01d5f7",
                    "sha256": "b08d3afdf3d51c6e7e50ad324e557975d3a211eef4192e42daab478c214a9e3c"
                },
                "downloads": -1,
                "filename": "gpkg.object_detect.models-0.5.1-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "aee7cfce7d73412350ef4d650e01d5f7",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 6240,
                "upload_time": "2018-11-05T17:28:33",
                "url": "https://files.pythonhosted.org/packages/2f/f4/94f1f0b43c12f9f7a6c3015568bcd5f087fccedbf6b0c336c88948410f83/gpkg.object_detect.models-0.5.1-py2.py3-none-any.whl"
            }
        ],
        "0.5.1.dev1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "e1bc256a805040843dc55195fea6f2b6",
                    "sha256": "73244d5aeb7ec121be50a132c3fe4eda78e5875211b395d0248194dc4cd8e8f0"
                },
                "downloads": -1,
                "filename": "gpkg.object_detect.models-0.5.1.dev1-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "e1bc256a805040843dc55195fea6f2b6",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 6187,
                "upload_time": "2018-11-02T12:07:13",
                "url": "https://files.pythonhosted.org/packages/54/cc/29f76892ab6dd98682ecd5297261b3a998cc9dc1402e8ac2a5d2f08b2b41/gpkg.object_detect.models-0.5.1.dev1-py2.py3-none-any.whl"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "aee7cfce7d73412350ef4d650e01d5f7",
                "sha256": "b08d3afdf3d51c6e7e50ad324e557975d3a211eef4192e42daab478c214a9e3c"
            },
            "downloads": -1,
            "filename": "gpkg.object_detect.models-0.5.1-py2.py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "aee7cfce7d73412350ef4d650e01d5f7",
            "packagetype": "bdist_wheel",
            "python_version": "py2.py3",
            "requires_python": null,
            "size": 6240,
            "upload_time": "2018-11-05T17:28:33",
            "url": "https://files.pythonhosted.org/packages/2f/f4/94f1f0b43c12f9f7a6c3015568bcd5f087fccedbf6b0c336c88948410f83/gpkg.object_detect.models-0.5.1-py2.py3-none-any.whl"
        }
    ]
}