{
    "info": {
        "author": "Congcong Li",
        "author_email": "luffy.lcc@gmail.com",
        "bugtrack_url": null,
        "classifiers": [
            "License :: OSI Approved :: MIT License",
            "Operating System :: OS Independent",
            "Programming Language :: Python :: 3",
            "Topic :: Scientific/Engineering :: Artificial Intelligence"
        ],
        "description": "# High quality, fast, modular reference implementation of SSD in PyTorch 1.0\n\n\nThis repository implements [SSD (Single Shot MultiBox Detector)](https://arxiv.org/abs/1512.02325). The implementation is heavily influenced by the projects [ssd.pytorch](https://github.com/amdegroot/ssd.pytorch), [pytorch-ssd](https://github.com/qfgaohao/pytorch-ssd) and [maskrcnn-benchmark](https://github.com/facebookresearch/maskrcnn-benchmark). This repository aims to be the code base for researches based on SSD.\n\n<div align=\"center\">\n  <img src=\"figures/004545.jpg\" width=\"500px\" />\n  <p>Example SSD output (ssd300_voc0712).</p>\n</div>\n\n| Losses        | Learning rate | Metrics |\n| :-----------: |:-------------:| :------:|\n| ![losses](figures/losses.png) | ![lr](figures/lr.png) | ![metric](figures/metrics.png) |\n\n## Highlights\n\n- **PyTorch 1.0**: Support PyTorch 1.0 or higher.\n- **Multi-GPU training and inference**: We use `DistributedDataParallel`, you can train or test with arbitrary GPU(s), the training schema will change accordingly.\n- **Modular**: And you own modules without pain. We abstract `backbone`,`Detector`, `BoxHead`, `BoxPredictor`, etc. You can replace every component with your own code without change the code base. For example, You can add [EfficientNet](https://github.com/lukemelas/EfficientNet-PyTorch) as backbone, just add `efficient_net.py` (ALREADY ADDED) and register it, specific it in the config file, It's done!\n- **CPU support for inference**: runs on CPU in inference time.\n- **Smooth and enjoyable training procedure**: we save the state of model, optimizer, scheduler, training iter, you can stop your training and resume training exactly from the save point without change your training `CMD`.\n- **Batched inference**: can perform inference using multiple images per batch per GPU.\n- **Evaluating during training**: eval you model every `eval_step` to check performance improving or not.\n- **Metrics Visualization**: visualize metrics details in tensorboard, like AP, APl, APm and APs for COCO dataset or mAP and 20 categories' AP for VOC dataset.\n- **Auto download**: load pre-trained weights from URL and cache it.\n## Installation\n### Requirements\n\n1. Python3\n1. PyTorch 1.0 or higher\n1. yacs\n1. [Vizer](https://github.com/lufficc/Vizer)\n1. GCC >= 4.9\n1. OpenCV\n\n\n### Step-by-step installation\n\n```bash\ngit clone https://github.com/lufficc/SSD.git\ncd SSD\n#Required packages\npip install torch torchvision yacs tqdm opencv-python vizer\n\n# Optional packages\n# If you want visualize loss curve. Default is enabled. Disable by using --use_tensorboard 0 when training.\npip install tensorboardX\n\n# If you train coco dataset, must install cocoapi.\ncd ~/github\ngit clone https://github.com/cocodataset/cocoapi.git\ncd cocoapi/PythonAPI\npython setup.py build_ext install\n```\n\n### Build\n\nNMS build is not necessary, as we provide a python-like nms, but is very slower than build-version.\n```bash\n# For faster inference you need to build nms, this is needed when evaluating. Only training doesn't need this.\ncd ext\npython build.py build_ext develop\n```\n\n## Train\n\n### Setting Up Datasets\n#### Pascal VOC\n\nFor Pascal VOC dataset, make the folder structure like this:\n```\nVOC_ROOT\n|__ VOC2007\n    |_ JPEGImages\n    |_ Annotations\n    |_ ImageSets\n    |_ SegmentationClass\n|__ VOC2012\n    |_ JPEGImages\n    |_ Annotations\n    |_ ImageSets\n    |_ SegmentationClass\n|__ ...\n```\nWhere `VOC_ROOT` default is `datasets` folder in current project, you can create symlinks to `datasets` or `export VOC_ROOT=\"/path/to/voc_root\"`.\n\n#### COCO\n\nFor COCO dataset, make the folder structure like this:\n```\nCOCO_ROOT\n|__ annotations\n    |_ instances_valminusminival2014.json\n    |_ instances_minival2014.json\n    |_ instances_train2014.json\n    |_ instances_val2014.json\n    |_ ...\n|__ train2014\n    |_ <im-1-name>.jpg\n    |_ ...\n    |_ <im-N-name>.jpg\n|__ val2014\n    |_ <im-1-name>.jpg\n    |_ ...\n    |_ <im-N-name>.jpg\n|__ ...\n```\nWhere `COCO_ROOT` default is `datasets` folder in current project, you can create symlinks to `datasets` or `export COCO_ROOT=\"/path/to/coco_root\"`.\n\n### Single GPU training\n\n```bash\n# for example, train SSD300:\npython train.py --config-file configs/vgg_ssd300_voc0712.yaml\n```\n### Multi-GPU training\n\n```bash\n# for example, train SSD300 with 4 GPUs:\nexport NGPUS=4\npython -m torch.distributed.launch --nproc_per_node=$NGPUS train.py --config-file configs/vgg_ssd300_voc0712.yaml SOLVER.WARMUP_FACTOR 0.03333 SOLVER.WARMUP_ITERS 1000\n```\nThe configuration files that I provide assume that we are running on single GPU. When changing number of GPUs, hyper-parameter (lr, max_iter, ...) will also changed according to this paper: [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://arxiv.org/abs/1706.02677).\n\n## Evaluate\n\n### Single GPU evaluating\n\n```bash\n# for example, evaluate SSD300:\npython test.py --config-file configs/vgg_ssd300_voc0712.yaml\n```\n\n### Multi-GPU evaluating\n\n```bash\n# for example, evaluate SSD300 with 4 GPUs:\nexport NGPUS=4\npython -m torch.distributed.launch --nproc_per_node=$NGPUS test.py --config-file configs/vgg_ssd300_voc0712.yaml\n```\n\n## Demo\n\nPredicting image in a folder is simple:\n```bash\npython demo.py --config-file configs/vgg_ssd300_voc0712.yaml --images_dir demo\n```\nThen the predicted images with boxes, scores and label names will saved to `demo/result` folder.\n\n## MODEL ZOO\n### Origin Paper:\n\n|         | VOC2007 test | coco test-dev2015 |\n| :-----: | :----------: |   :----------:    |\n| SSD300* |     77.2     |      25.1         |\n| SSD512* |     79.8     |      28.8         |\n\n### COCO:\n\n| Backbone       | Input Size  |          box AP                  | Model Size |  Download |\n| :------------: | :----------:|   :--------------------------:   | :--------: | :-------: |\n|  VGG16         |     300     |          25.2                    |  262MB     | [model](https://github.com/lufficc/SSD/releases/download/1.2/vgg_ssd300_coco_trainval35k.pth)   |\n|  VGG16         |     512     |          xx.x                    |  xxx.xMB   |           |\n|  Mobilenet V2  |     320     |          xx.x                    |  xxx.xMB   |           |\n\n### PASCAL VOC:\n\n| Backbone         | Input Size  |          mAP                     | Model Size | Download  |\n| :--------------: | :----------:|   :--------------------------:   | :--------: | :-------: |\n|  VGG16           |     300     |          77.6                    |   201MB    | [model](https://github.com/lufficc/SSD/releases/download/1.2/vgg_ssd300_voc0712.pth)  |\n|  VGG16           |     512     |          xx.x                    |   xxx.xMB  |            |\n|  Mobilenet V2    |     320     |          68.8                    |   25.5MB   | [model](https://github.com/lufficc/SSD/releases/download/1.2/mobilenet_v2_ssd320_voc0712.pth) |\n|  EfficientNet-B3 |     300     |          73.9                    |   97.1MB   | [model](https://github.com/lufficc/SSD/releases/download/1.2/efficient_net_b3_ssd300_voc0712.pth) |\n\n## Troubleshooting\nIf you have issues running or compiling this code, we have compiled a list of common issues in [TROUBLESHOOTING.md](TROUBLESHOOTING.md). If your issue is not present there, please feel free to open a new issue.",
        "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/lufficc/SSD",
        "keywords": "",
        "license": "MIT",
        "maintainer": "",
        "maintainer_email": "",
        "name": "torch-ssd",
        "package_url": "https://pypi.org/project/torch-ssd/",
        "platform": "",
        "project_url": "https://pypi.org/project/torch-ssd/",
        "project_urls": {
            "Homepage": "https://github.com/lufficc/SSD"
        },
        "release_url": "https://pypi.org/project/torch-ssd/1.2.0/",
        "requires_dist": null,
        "requires_python": ">=3.6",
        "summary": "High quality, fast, modular reference implementation of SSD in PyTorch",
        "version": "1.2.0",
        "yanked": false,
        "yanked_reason": null
    },
    "last_serial": 6043876,
    "releases": {
        "1.2.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "eda2d99b6d1546aa25bdb54944a9744e",
                    "sha256": "05b26c5531ef9ba8685f857e15badd0cad2e1f30b8df809e3fbe4a8ba42d1b43"
                },
                "downloads": -1,
                "filename": "torch-ssd-1.2.0.linux-x86_64.tar.gz",
                "has_sig": false,
                "md5_digest": "eda2d99b6d1546aa25bdb54944a9744e",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": ">=3.6",
                "size": 89756,
                "upload_time": "2019-10-28T21:03:36",
                "upload_time_iso_8601": "2019-10-28T21:03:36.700568Z",
                "url": "https://files.pythonhosted.org/packages/15/e3/7f49d959ed3b241a5f822eed1ed83debbc30ab0c27cd788c467e7cc4d2e3/torch-ssd-1.2.0.linux-x86_64.tar.gz",
                "yanked": false,
                "yanked_reason": null
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "eda2d99b6d1546aa25bdb54944a9744e",
                "sha256": "05b26c5531ef9ba8685f857e15badd0cad2e1f30b8df809e3fbe4a8ba42d1b43"
            },
            "downloads": -1,
            "filename": "torch-ssd-1.2.0.linux-x86_64.tar.gz",
            "has_sig": false,
            "md5_digest": "eda2d99b6d1546aa25bdb54944a9744e",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.6",
            "size": 89756,
            "upload_time": "2019-10-28T21:03:36",
            "upload_time_iso_8601": "2019-10-28T21:03:36.700568Z",
            "url": "https://files.pythonhosted.org/packages/15/e3/7f49d959ed3b241a5f822eed1ed83debbc30ab0c27cd788c467e7cc4d2e3/torch-ssd-1.2.0.linux-x86_64.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "vulnerabilities": []
}