{
  "id": 165736,
  "title": "TF Object Detection API officially supports TensorFlow 2",
  "url": "/competitions/global-wheat-detection/discussion/165736",
  "author_name": "tn",
  "post_date": "2020-07-10T23:35:13.684000",
  "votes": 6,
  "comment_count": 0,
  "views": 0,
  "content": "<p><a href=\"https://github.com/tensorflow/models/tree/master/research/object_detection\">[GitHub] TensorFlow Object Detection API</a></p>\n\n<p><a href=\"https://blog.tensorflow.org/2020/07/tensorflow-2-meets-object-detection-api.html\">[TensorFlow Blog] TensorFlow 2 meets the Object Detection API</a></p>\n\n<blockquote>\n  <p>A suite of TF2 compatible (Keras-based) models; this includes migrations of our most popular TF1 models (e.g., SSD with MobileNet, RetinaNet, Faster R-CNN, Mask R-CNN), as well as a few new architectures for which we will only maintain TF2 implementations: (1) CenterNet - a simple and effective anchor-free architecture based on the recent Objects as Points paper by Zhou et al, and (2) EfficientDet --- a recent family of SOTA models discovered with the help of Neural Architecture Search.</p>\n</blockquote>",
  "messages": [
    {
      "id": 923503,
      "postDate": "2020-07-10T23:35:13.683Z",
      "content": "<p><a href=\"https://github.com/tensorflow/models/tree/master/research/object_detection\">[GitHub] TensorFlow Object Detection API</a></p>\n\n<p><a href=\"https://blog.tensorflow.org/2020/07/tensorflow-2-meets-object-detection-api.html\">[TensorFlow Blog] TensorFlow 2 meets the Object Detection API</a></p>\n\n<blockquote>\n  <p>A suite of TF2 compatible (Keras-based) models; this includes migrations of our most popular TF1 models (e.g., SSD with MobileNet, RetinaNet, Faster R-CNN, Mask R-CNN), as well as a few new architectures for which we will only maintain TF2 implementations: (1) CenterNet - a simple and effective anchor-free architecture based on the recent Objects as Points paper by Zhou et al, and (2) EfficientDet --- a recent family of SOTA models discovered with the help of Neural Architecture Search.</p>\n</blockquote>",
      "rawMarkdown": "[[GitHub] TensorFlow Object Detection API](https://github.com/tensorflow/models/tree/master/research/object_detection)\n\n[[TensorFlow Blog] TensorFlow 2 meets the Object Detection API](https://blog.tensorflow.org/2020/07/tensorflow-2-meets-object-detection-api.html)\n&gt; A suite of TF2 compatible (Keras-based) models; this includes migrations of our most popular TF1 models (e.g., SSD with MobileNet, RetinaNet, Faster R-CNN, Mask R-CNN), as well as a few new architectures for which we will only maintain TF2 implementations: (1) CenterNet - a simple and effective anchor-free architecture based on the recent Objects as Points paper by Zhou et al, and (2) EfficientDet --- a recent family of SOTA models discovered with the help of Neural Architecture Search.",
      "votes": 5
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "923503": "[[GitHub] TensorFlow Object Detection API](https://github.com/tensorflow/models/tree/master/research/object_detection)\n\n[[TensorFlow Blog] TensorFlow 2 meets the Object Detection API](https://blog.tensorflow.org/2020/07/tensorflow-2-meets-object-detection-api.html)\n&gt; A suite of TF2 compatible (Keras-based) models; this includes migrations of our most popular TF1 models (e.g., SSD with MobileNet, RetinaNet, Faster R-CNN, Mask R-CNN), as well as a few new architectures for which we will only maintain TF2 implementations: (1) CenterNet - a simple and effective anchor-free architecture based on the recent Objects as Points paper by Zhou et al, and (2) EfficientDet --- a recent family of SOTA models discovered with the help of Neural Architecture Search."
  }
}