Please use this thread to post any external data and pre-trained models you use for your solution. Reminder, disclosure is required one week prior to the submission deadline.
", "messages": [ { "id": 366840, "postDate": "2018-08-06T16:06:27.153Z", "content": "Please use this thread to post any external data and pre-trained models you use for your solution. Reminder, disclosure is required one week prior to the submission deadline.
", "rawMarkdown": "Please use this thread to post any external data and pre-trained models you use for your solution. Reminder, disclosure is required one week prior to the submission deadline.", "votes": 4 }, { "id": 370647, "postDate": "2018-08-15T07:44:11.680Z", "content": "just out of curiosity... can you please point me to where in the rules this is mentioned?
", "rawMarkdown": "just out of curiosity... can you please point me to where in the rules this is mentioned?", "votes": 1, "replies": [ { "id": 371781, "postDate": "2018-08-17T15:46:26.950Z", "content": "Hi Moshel,
\n\nUnder Section A, Competition-Specific Rules: \"The following provision supersedes General Rules Section 7.C. below: “You may use data, other than the Competition Data, as allowed on the Competition Website to develop and test your models and Submissions; provided, you have the right and authority to use such external data for the purposes of the Competition, and to share such data with Sponsor and Kaggle as may be required.\"\"
", "rawMarkdown": "Hi Moshel,\n\nUnder Section A, Competition-Specific Rules: \"The following provision supersedes General Rules Section 7.C. below: “You may use data, other than the Competition Data, as allowed on the Competition Website to develop and test your models and Submissions; provided, you have the right and authority to use such external data for the purposes of the Competition, and to share such data with Sponsor and Kaggle as may be required.\"\"" } ] }, { "id": 367157, "postDate": "2018-08-07T07:49:16.037Z", "content": "I am using the Open Images-trained model as fine_tune_checkpoint:\nhttp://download.tensorflow.org/models/object_detection/faster_rcnn_inception_resnet_v2_atrous_oid_2018_01_28.tar.gz
Same tools as I am using for the VRD track (comment copied from the other discussion forum):
\n\nI am not planning on using external data (that is apart from the data from object detection track but not sure this would qualify as external) . I am still in the exploratory phase and not sure if I will have time to work more on this, but if I do, I will most likely use a pretrained model (or a couple of models) from either of the following sources:
\n\nNot sure if more information would be required - please let me know if that would be the case.
", "rawMarkdown": "Same tools as I am using for the VRD track (comment copied from the other discussion forum):\n\nI am not planning on using external data (that is apart from the data from object detection track but not sure this would qualify as external) . I am still in the exploratory phase and not sure if I will have time to work more on this, but if I do, I will most likely use a pretrained model (or a couple of models) from either of the following sources:\n\n 1. [Tensorflow detection model zoo][1] / [Tensorflow pretrained models][2]\n 2. Pretrained models that come with the [fastai][3] library (resnet18, resnet34, resnet50, resnet101, resnet152, vgg16, \n vgg19, resnetxt50, resnext101, resnext101_64, wrn, inceptionresnet_2, inception_4, dn121, dn161, dn169, dn201).\n 3. Any of the pretrained models from [here][4] and [here][5], in particular the [darknet53.conv.74][6]\n 4. pretrained models in PyTorch from this [repository][7]\n\nNot sure if more information would be required - please let me know if that would be the case.\n\n\n [1]: https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md\n [2]: https://github.com/tensorflow/models/tree/master/research/slim\n [3]: https://github.com/fastai/fastai\n [4]: https://pjreddie.com/darknet/imagenet/\n [5]: https://pjreddie.com/darknet/yolo/\n [6]: https://pjreddie.com/media/files/darknet53.conv.74\n [7]: https://github.com/Cadene/pretrained-models.pytorch" }, { "id": 377600, "postDate": "2018-08-29T12:26:26.693Z", "content": "We use pretrained models from following repos:
\n\nhttps://github.com/soeaver/caffe-model
\n\nhttps://github.com/KaimingHe/deep-residual-networks
\n\nhttps://github.com/Cadene/pretrained-models.pytorch
\n\nhttps://github.com/msracver/Deformable-ConvNets
\n\nOpen Images Dataset V4 https://storage.googleapis.com/openimages/web/download.html
", "rawMarkdown": "We use pretrained models from following repos:\n\nhttps://github.com/soeaver/caffe-model\n\nhttps://github.com/KaimingHe/deep-residual-networks\n\nhttps://github.com/Cadene/pretrained-models.pytorch\n\nhttps://github.com/msracver/Deformable-ConvNets\n\nOpen Images Dataset V4 https://storage.googleapis.com/openimages/web/download.html" }, { "id": 376550, "postDate": "2018-08-27T18:05:13.740Z", "content": "We used this Pretrained model: http://download.tensorflow.org/models/object_detection/faster_rcnn_inception_resnet_v2_atrous_oid_2018_01_28.tar.gz
", "rawMarkdown": "We used this Pretrained model: http://download.tensorflow.org/models/object_detection/faster_rcnn_inception_resnet_v2_atrous_oid_2018_01_28.tar.gz" }, { "id": 376224, "postDate": "2018-08-27T04:13:17.373Z", "content": "Started with Pretrained model: http://download.tensorflow.org/models/object_detection/faster_rcnn_inception_resnet_v2_atrous_oid_2018_01_28.tar.gz
", "rawMarkdown": "Started with Pretrained model: http://download.tensorflow.org/models/object_detection/faster_rcnn_inception_resnet_v2_atrous_oid_2018_01_28.tar.gz" }, { "id": 376210, "postDate": "2018-08-27T02:57:33.813Z", "content": "Datasets involved: Open Images V4, COCO, ImageNet; Models pretrained with MXNet and TensorFlow
", "rawMarkdown": "Datasets involved: [Open Images V4](https://storage.googleapis.com/openimages/web/download.html), [COCO](http://cocodataset.org/#home), [ImageNet](http://image-net.org/); Models pretrained with [MXNet](https://github.com/honghuis/mxnet_det/tree/master) and [TensorFlow](https://github.com/tensorflow/models/tree/master/research/object_detection)" }, { "id": 375425, "postDate": "2018-08-25T06:57:56.887Z", "content": "We use pretrained models provided by
\n\n\n\nWe use datasets provided by:
\n\n", "rawMarkdown": "We use pretrained models provided by \n\n1. [Tensorflow pretrianed model](https://github.com/tensorflow/models/tree/master/research/slim)\n\n2. [MXNet Gluon Model Zoo](http://mxnet.apache.org/api/python/gluon/model_zoo.html) and [MXNet DMLC](http://data.dmlc.ml)\n\n3. [Detectron](https://github.com/facebookresearch/Detectron/blob/master/MODEL_ZOO.md)\n\n4. [SENet](https://github.com/hujie-frank/SENet)\n\nWe use datasets provided by:\n\n1. [Open Images Dataset V4](https://storage.googleapis.com/openimages/web/download.html)\n\n2. [ImageNet](http://image-net.org/download-images)\n\n3. [COCO](http://cocodataset.org/#download)\n" }, { "id": 375324, "postDate": "2018-08-24T23:34:47.613Z", "content": "Pretrained Model: Detectron Model Zoo https://github.com/facebookresearch/Detectron/blob/master/MODEL_ZOO.md
\n\nOpen Images Dataset V4 https://storage.googleapis.com/openimages/web/download.html
\n\nImageNet http://image-net.org/download-images
\n\nCOCO http://cocodataset.org/#download
", "rawMarkdown": "Pretrained Model: Detectron Model Zoo https://github.com/facebookresearch/Detectron/blob/master/MODEL_ZOO.md\n\nOpen Images Dataset V4 https://storage.googleapis.com/openimages/web/download.html\n\nImageNet http://image-net.org/download-images\n\nCOCO http://cocodataset.org/#download" }, { "id": 374994, "postDate": "2018-08-24T10:35:45.500Z", "content": "Pretrained Model: Detectron Model Zoo https://github.com/facebookresearch/Detectron/blob/master/MODEL_ZOO.md
\n\nOpen Images Dataset V4 https://storage.googleapis.com/openimages/web/download.html
\n\nImageNet http://image-net.org/download-images
\n\nCOCO http://cocodataset.org/#download
", "rawMarkdown": "Pretrained Model: Detectron Model Zoo https://github.com/facebookresearch/Detectron/blob/master/MODEL_ZOO.md\n\nOpen Images Dataset V4 https://storage.googleapis.com/openimages/web/download.html\n\nImageNet http://image-net.org/download-images\n\nCOCO http://cocodataset.org/#download" }, { "id": 374937, "postDate": "2018-08-24T08:24:53.880Z", "content": "May or may not use pretrained models and datasets mentioned in:
\n\nTensorFlow Object Detection
\n(Open Images dataset, COCO dataset, Oxford-IIIT Pets dataset, model zoo, etc.)
\nhttps://github.com/tensorflow/models/tree/master/research/object_detection
Darknet
\n(ImageNet dataset, YOLO, etc.)
\nhttps://pjreddie.com/darknet
ImageAI
\nhttps://github.com/OlafenwaMoses/ImageAI
ChainerCV
\nhttps://github.com/chainer/chainercv
External Data and Pre-Trained Model Disclosure Thread (a bit of recursion here ;) )
\nhttps://www.kaggle.com/c/google-ai-open-images-object-detection-track/discussion/62741
we might use any of the following:\nGoogle zoo and object detection tutorials\nKeras zoo\nYolov3 weights from darknet, code from https://github.com/qqwweee/keras-yolo3\nRetinanet from https://github.com/fizyr/keras-retinanet\nDlib\nTiny faces from https://github.com/cydonia999/Tiny_Faces_in_Tensorflow\nhttps://github.com/ipazc/mtcnn\nNeptune.ml open solution\nDetecteron models (caffe2)\nmxnet/gluon models\nChainer zoo
", "rawMarkdown": "we might use any of the following:\nGoogle zoo and object detection tutorials\nKeras zoo\nYolov3 weights from darknet, code from https://github.com/qqwweee/keras-yolo3\nRetinanet from https://github.com/fizyr/keras-retinanet\nDlib\nTiny faces from https://github.com/cydonia999/Tiny_Faces_in_Tensorflow\nhttps://github.com/ipazc/mtcnn\nNeptune.ml open solution\nDetecteron models (caffe2)\nmxnet/gluon models\nChainer zoo\n" }, { "id": 374779, "postDate": "2018-08-23T19:36:16.087Z", "content": "models from torchvision.models are used: https://pytorch.org/docs/0.4.0/torchvision/models.html
", "rawMarkdown": "models from torchvision.models are used: https://pytorch.org/docs/0.4.0/torchvision/models.html" }, { "id": 374773, "postDate": "2018-08-23T19:14:23.723Z", "content": "Keras model zoo: https://keras.io/applications/
", "rawMarkdown": "Keras model zoo: https://keras.io/applications/" }, { "id": 374771, "postDate": "2018-08-23T19:04:17.993Z", "content": "I may try \nTensorflow model zoo: https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md Pytorch model zoo: https://pytorch.org/docs/stable/torchvision/models.html Keras model zoo: https://keras.io/applications/\nand vgg16 based pretrianed model here
", "rawMarkdown": "I may try \nTensorflow model zoo: https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md Pytorch model zoo: https://pytorch.org/docs/stable/torchvision/models.html Keras model zoo: https://keras.io/applications/\nand vgg16 based pretrianed model [here][1]\n [1]: http://cs.stanford.edu/people/jcjohns/densecap/densecap-pretrained-vgg16.t7.zip" }, { "id": 374734, "postDate": "2018-08-23T17:25:57.233Z", "content": "I plan to use models from:\n1. Tensorflow model zoo: https://github.com/tensorflow/models/blob/master/research/object_detection/\n2. Keras model zoo: https://keras.io/applications/
", "rawMarkdown": "I plan to use models from:\n1. Tensorflow model zoo: https://github.com/tensorflow/models/blob/master/research/object_detection/\n2. Keras model zoo: https://keras.io/applications/" }, { "id": 374634, "postDate": "2018-08-23T12:49:43.907Z", "content": "Tensorflow model zoo: https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md\nPytorch model zoo: https://pytorch.org/docs/stable/torchvision/models.html\nKeras model zoo: https://keras.io/applications/
", "rawMarkdown": "Tensorflow model zoo: https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md\nPytorch model zoo: https://pytorch.org/docs/stable/torchvision/models.html\nKeras model zoo: https://keras.io/applications/" }, { "id": 374602, "postDate": "2018-08-23T11:30:09.550Z", "content": "Will be using the Open Images-trained model from tensorflow model zoo: http://download.tensorflow.org/models/object_detection/faster_rcnn_inception_resnet_v2_atrous_oid_2018_01_28.tar.gz
", "rawMarkdown": "Will be using the Open Images-trained model from tensorflow model zoo: http://download.tensorflow.org/models/object_detection/faster_rcnn_inception_resnet_v2_atrous_oid_2018_01_28.tar.gz" }, { "id": 374556, "postDate": "2018-08-23T09:42:48.067Z", "content": "Pretrained models:
\n\nData (images and annotations):
\n\nI will perhaps use one or more pre-trained model(s) from either of the following sources:
\n\nPre-trained model on Open Image dataset for detection/fine_tune_checkpoint: http://download.tensorflow.org/models/object_detection/faster_rcnn_inception_resnet_v2_atrous_oid_2018_01_28.tar.gz
\n\nYOLO pre-trained model: https://pjreddie.com/darknet/yolo/
\n\nPre-trained model from ImageAI:
\n\nhttps://github.com/OlafenwaMoses/ImageAI/releases/download/1.0/resnet50_coco_best_v2.0.1.h5
\n\nhttps://github.com/OlafenwaMoses/ImageAI/releases/download/1.0/yolo.h5
\n\nhttps://github.com/OlafenwaMoses/ImageAI/releases/download/1.0/tiny-yolo.h5
\n\nPre-trained models from https://pjreddie.com/darknet/imagenet/.
", "rawMarkdown": "I will perhaps use one or more pre-trained model(s) from either of the following sources:\n\nPre-trained model on Open Image dataset for detection/fine_tune_checkpoint: http://download.tensorflow.org/models/object_detection/faster_rcnn_inception_resnet_v2_atrous_oid_2018_01_28.tar.gz\n\nYOLO pre-trained model: https://pjreddie.com/darknet/yolo/\n\nPre-trained model from ImageAI:\n\nhttps://github.com/OlafenwaMoses/ImageAI/releases/download/1.0/resnet50_coco_best_v2.0.1.h5\n\nhttps://github.com/OlafenwaMoses/ImageAI/releases/download/1.0/yolo.h5\n\nhttps://github.com/OlafenwaMoses/ImageAI/releases/download/1.0/tiny-yolo.h5\n\nPre-trained models from https://pjreddie.com/darknet/imagenet/." }, { "id": 373580, "postDate": "2018-08-21T15:40:55.883Z", "content": "I am using Detectron (https://github.com/facebookresearch/Detectron) which begins its training runs by initializing itself to some pretrained models as listed in the configs directory (https://github.com/facebookresearch/Detectron/tree/master/configs), e.g. https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/47261647/R-50-GN.pkl
", "rawMarkdown": "I am using Detectron (https://github.com/facebookresearch/Detectron) which begins its training runs by initializing itself to some pretrained models as listed in the configs directory (https://github.com/facebookresearch/Detectron/tree/master/configs), e.g. https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/47261647/R-50-GN.pkl" }, { "id": 371702, "postDate": "2018-08-17T13:22:40.410Z", "content": "Keras resnet pretrained on imagenet and tf faster_rcnn_inception_resnet_v2_atrous_oid weights if I get that to work ;)
", "rawMarkdown": "Keras resnet pretrained on imagenet and tf faster_rcnn_inception_resnet_v2_atrous_oid weights if I get that to work ;)" }, { "id": 375296, "postDate": "2018-08-24T22:34:45.017Z", "rawMarkdown": "", "isDeleted": true } ], "comments": [ { "id": 370647, "author_name": "Moshel", "author_url": "", "post_date": "2018-08-15T07:44:11.680000", "content": "just out of curiosity... can you please point me to where in the rules this is mentioned?
", "votes": 1, "replies": [ { "id": 371781, "author_name": "Addison Howard", "author_url": "", "post_date": "2018-08-17T15:46:26.950000", "content": "Hi Moshel,
\n\nUnder Section A, Competition-Specific Rules: \"The following provision supersedes General Rules Section 7.C. below: “You may use data, other than the Competition Data, as allowed on the Competition Website to develop and test your models and Submissions; provided, you have the right and authority to use such external data for the purposes of the Competition, and to share such data with Sponsor and Kaggle as may be required.\"\"
", "votes": 0, "replies": [] } ] }, { "id": 367157, "author_name": "Tony Y.", "author_url": "", "post_date": "2018-08-07T07:49:16.037000", "content": "I am using the Open Images-trained model as fine_tune_checkpoint:\nhttp://download.tensorflow.org/models/object_detection/faster_rcnn_inception_resnet_v2_atrous_oid_2018_01_28.tar.gz
Same tools as I am using for the VRD track (comment copied from the other discussion forum):
\n\nI am not planning on using external data (that is apart from the data from object detection track but not sure this would qualify as external) . I am still in the exploratory phase and not sure if I will have time to work more on this, but if I do, I will most likely use a pretrained model (or a couple of models) from either of the following sources:
\n\nNot sure if more information would be required - please let me know if that would be the case.
", "votes": 0, "replies": [] }, { "id": 377600, "author_name": "", "author_url": "", "post_date": "2018-08-29T12:26:26.693000", "content": "We use pretrained models from following repos:
\n\nhttps://github.com/soeaver/caffe-model
\n\nhttps://github.com/KaimingHe/deep-residual-networks
\n\nhttps://github.com/Cadene/pretrained-models.pytorch
\n\nhttps://github.com/msracver/Deformable-ConvNets
\n\nOpen Images Dataset V4 https://storage.googleapis.com/openimages/web/download.html
", "votes": 0, "replies": [] }, { "id": 376550, "author_name": "syhan", "author_url": "", "post_date": "2018-08-27T18:05:13.740000", "content": "We used this Pretrained model: http://download.tensorflow.org/models/object_detection/faster_rcnn_inception_resnet_v2_atrous_oid_2018_01_28.tar.gz
", "votes": 0, "replies": [] }, { "id": 376224, "author_name": "Tim H", "author_url": "", "post_date": "2018-08-27T04:13:17.373000", "content": "Started with Pretrained model: http://download.tensorflow.org/models/object_detection/faster_rcnn_inception_resnet_v2_atrous_oid_2018_01_28.tar.gz
", "votes": 0, "replies": [] }, { "id": 376210, "author_name": "Honghui Shi", "author_url": "", "post_date": "2018-08-27T02:57:33.813000", "content": "Datasets involved: Open Images V4, COCO, ImageNet; Models pretrained with MXNet and TensorFlow
", "votes": 0, "replies": [] }, { "id": 375425, "author_name": "YuntaoChen", "author_url": "", "post_date": "2018-08-25T06:57:56.887000", "content": "We use pretrained models provided by
\n\n\n\nWe use datasets provided by:
\n\n", "votes": 0, "replies": [] }, { "id": 375324, "author_name": "xiteng", "author_url": "", "post_date": "2018-08-24T23:34:47.613000", "content": "Pretrained Model: Detectron Model Zoo https://github.com/facebookresearch/Detectron/blob/master/MODEL_ZOO.md
\n\nOpen Images Dataset V4 https://storage.googleapis.com/openimages/web/download.html
\n\nImageNet http://image-net.org/download-images
\n\nCOCO http://cocodataset.org/#download
", "votes": 0, "replies": [] }, { "id": 374994, "author_name": "LabMen 000", "author_url": "", "post_date": "2018-08-24T10:35:45.500000", "content": "Pretrained Model: Detectron Model Zoo https://github.com/facebookresearch/Detectron/blob/master/MODEL_ZOO.md
\n\nOpen Images Dataset V4 https://storage.googleapis.com/openimages/web/download.html
\n\nImageNet http://image-net.org/download-images
\n\nCOCO http://cocodataset.org/#download
", "votes": 0, "replies": [] }, { "id": 374937, "author_name": "vecxoz", "author_url": "", "post_date": "2018-08-24T08:24:53.880000", "content": "May or may not use pretrained models and datasets mentioned in:
\n\nTensorFlow Object Detection
\n(Open Images dataset, COCO dataset, Oxford-IIIT Pets dataset, model zoo, etc.)
\nhttps://github.com/tensorflow/models/tree/master/research/object_detection
Darknet
\n(ImageNet dataset, YOLO, etc.)
\nhttps://pjreddie.com/darknet
ImageAI
\nhttps://github.com/OlafenwaMoses/ImageAI
ChainerCV
\nhttps://github.com/chainer/chainercv
External Data and Pre-Trained Model Disclosure Thread (a bit of recursion here ;) )
\nhttps://www.kaggle.com/c/google-ai-open-images-object-detection-track/discussion/62741
we might use any of the following:\nGoogle zoo and object detection tutorials\nKeras zoo\nYolov3 weights from darknet, code from https://github.com/qqwweee/keras-yolo3\nRetinanet from https://github.com/fizyr/keras-retinanet\nDlib\nTiny faces from https://github.com/cydonia999/Tiny_Faces_in_Tensorflow\nhttps://github.com/ipazc/mtcnn\nNeptune.ml open solution\nDetecteron models (caffe2)\nmxnet/gluon models\nChainer zoo
", "votes": 0, "replies": [] }, { "id": 374779, "author_name": "YuanXu", "author_url": "", "post_date": "2018-08-23T19:36:16.087000", "content": "models from torchvision.models are used: https://pytorch.org/docs/0.4.0/torchvision/models.html
", "votes": 0, "replies": [] }, { "id": 374773, "author_name": "Chia-Ta Tsai", "author_url": "", "post_date": "2018-08-23T19:14:23.723000", "content": "Keras model zoo: https://keras.io/applications/
", "votes": 0, "replies": [] }, { "id": 374771, "author_name": "Kishore M", "author_url": "", "post_date": "2018-08-23T19:04:17.993000", "content": "I may try \nTensorflow model zoo: https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md Pytorch model zoo: https://pytorch.org/docs/stable/torchvision/models.html Keras model zoo: https://keras.io/applications/\nand vgg16 based pretrianed model here
", "votes": 0, "replies": [] }, { "id": 374734, "author_name": "Giri Gopalan", "author_url": "", "post_date": "2018-08-23T17:25:57.233000", "content": "I plan to use models from:\n1. Tensorflow model zoo: https://github.com/tensorflow/models/blob/master/research/object_detection/\n2. Keras model zoo: https://keras.io/applications/
", "votes": 0, "replies": [] }, { "id": 374634, "author_name": "Kyle Lee", "author_url": "", "post_date": "2018-08-23T12:49:43.907000", "content": "Tensorflow model zoo: https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md\nPytorch model zoo: https://pytorch.org/docs/stable/torchvision/models.html\nKeras model zoo: https://keras.io/applications/
", "votes": 0, "replies": [] }, { "id": 374602, "author_name": "Deepanshu", "author_url": "", "post_date": "2018-08-23T11:30:09.550000", "content": "Will be using the Open Images-trained model from tensorflow model zoo: http://download.tensorflow.org/models/object_detection/faster_rcnn_inception_resnet_v2_atrous_oid_2018_01_28.tar.gz
", "votes": 0, "replies": [] }, { "id": 374556, "author_name": "iwiwi", "author_url": "", "post_date": "2018-08-23T09:42:48.067000", "content": "Pretrained models:
\n\nData (images and annotations):
\n\nI will perhaps use one or more pre-trained model(s) from either of the following sources:
\n\nPre-trained model on Open Image dataset for detection/fine_tune_checkpoint: http://download.tensorflow.org/models/object_detection/faster_rcnn_inception_resnet_v2_atrous_oid_2018_01_28.tar.gz
\n\nYOLO pre-trained model: https://pjreddie.com/darknet/yolo/
\n\nPre-trained model from ImageAI:
\n\nhttps://github.com/OlafenwaMoses/ImageAI/releases/download/1.0/resnet50_coco_best_v2.0.1.h5
\n\nhttps://github.com/OlafenwaMoses/ImageAI/releases/download/1.0/yolo.h5
\n\nhttps://github.com/OlafenwaMoses/ImageAI/releases/download/1.0/tiny-yolo.h5
\n\nPre-trained models from https://pjreddie.com/darknet/imagenet/.
", "votes": 0, "replies": [] }, { "id": 373580, "author_name": "particlebbq", "author_url": "", "post_date": "2018-08-21T15:40:55.883000", "content": "I am using Detectron (https://github.com/facebookresearch/Detectron) which begins its training runs by initializing itself to some pretrained models as listed in the configs directory (https://github.com/facebookresearch/Detectron/tree/master/configs), e.g. https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/47261647/R-50-GN.pkl
", "votes": 0, "replies": [] }, { "id": 371702, "author_name": "Mukesh", "author_url": "", "post_date": "2018-08-17T13:22:40.410000", "content": "Keras resnet pretrained on imagenet and tf faster_rcnn_inception_resnet_v2_atrous_oid weights if I get that to work ;)
", "votes": 0, "replies": [] }, { "id": 375296, "author_name": "", "author_url": "", "post_date": "2018-08-24T22:34:45.017000", "content": "", "votes": 0, "replies": [] } ], "raw_markdown_by_id": { "366840": "Please use this thread to post any external data and pre-trained models you use for your solution. Reminder, disclosure is required one week prior to the submission deadline.", "370647": "just out of curiosity... can you please point me to where in the rules this is mentioned?", "367157": "I am using the Open Images-trained model as `fine_tune_checkpoint`:\nhttp://download.tensorflow.org/models/object_detection/faster_rcnn_inception_resnet_v2_atrous_oid_2018_01_28.tar.gz", "367634": "Same tools as I am using for the VRD track (comment copied from the other discussion forum):\n\nI am not planning on using external data (that is apart from the data from object detection track but not sure this would qualify as external) . I am still in the exploratory phase and not sure if I will have time to work more on this, but if I do, I will most likely use a pretrained model (or a couple of models) from either of the following sources:\n\n 1. [Tensorflow detection model zoo][1] / [Tensorflow pretrained models][2]\n 2. Pretrained models that come with the [fastai][3] library (resnet18, resnet34, resnet50, resnet101, resnet152, vgg16, \n vgg19, resnetxt50, resnext101, resnext101_64, wrn, inceptionresnet_2, inception_4, dn121, dn161, dn169, dn201).\n 3. Any of the pretrained models from [here][4] and [here][5], in particular the [darknet53.conv.74][6]\n 4. pretrained models in PyTorch from this [repository][7]\n\nNot sure if more information would be required - please let me know if that would be the case.\n\n\n [1]: https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md\n [2]: https://github.com/tensorflow/models/tree/master/research/slim\n [3]: https://github.com/fastai/fastai\n [4]: https://pjreddie.com/darknet/imagenet/\n [5]: https://pjreddie.com/darknet/yolo/\n [6]: https://pjreddie.com/media/files/darknet53.conv.74\n [7]: https://github.com/Cadene/pretrained-models.pytorch", "377600": "We use pretrained models from following repos:\n\nhttps://github.com/soeaver/caffe-model\n\nhttps://github.com/KaimingHe/deep-residual-networks\n\nhttps://github.com/Cadene/pretrained-models.pytorch\n\nhttps://github.com/msracver/Deformable-ConvNets\n\nOpen Images Dataset V4 https://storage.googleapis.com/openimages/web/download.html", "376550": "We used this Pretrained model: http://download.tensorflow.org/models/object_detection/faster_rcnn_inception_resnet_v2_atrous_oid_2018_01_28.tar.gz", "376224": "Started with Pretrained model: http://download.tensorflow.org/models/object_detection/faster_rcnn_inception_resnet_v2_atrous_oid_2018_01_28.tar.gz", "376210": "Datasets involved: [Open Images V4](https://storage.googleapis.com/openimages/web/download.html), [COCO](http://cocodataset.org/#home), [ImageNet](http://image-net.org/); Models pretrained with [MXNet](https://github.com/honghuis/mxnet_det/tree/master) and [TensorFlow](https://github.com/tensorflow/models/tree/master/research/object_detection)", "375425": "We use pretrained models provided by \n\n1. [Tensorflow pretrianed model](https://github.com/tensorflow/models/tree/master/research/slim)\n\n2. [MXNet Gluon Model Zoo](http://mxnet.apache.org/api/python/gluon/model_zoo.html) and [MXNet DMLC](http://data.dmlc.ml)\n\n3. [Detectron](https://github.com/facebookresearch/Detectron/blob/master/MODEL_ZOO.md)\n\n4. [SENet](https://github.com/hujie-frank/SENet)\n\nWe use datasets provided by:\n\n1. [Open Images Dataset V4](https://storage.googleapis.com/openimages/web/download.html)\n\n2. [ImageNet](http://image-net.org/download-images)\n\n3. [COCO](http://cocodataset.org/#download)\n", "375324": "Pretrained Model: Detectron Model Zoo https://github.com/facebookresearch/Detectron/blob/master/MODEL_ZOO.md\n\nOpen Images Dataset V4 https://storage.googleapis.com/openimages/web/download.html\n\nImageNet http://image-net.org/download-images\n\nCOCO http://cocodataset.org/#download", "374994": "Pretrained Model: Detectron Model Zoo https://github.com/facebookresearch/Detectron/blob/master/MODEL_ZOO.md\n\nOpen Images Dataset V4 https://storage.googleapis.com/openimages/web/download.html\n\nImageNet http://image-net.org/download-images\n\nCOCO http://cocodataset.org/#download", "374937": "May or may not use pretrained models and datasets mentioned in: \n\n1. TensorFlow Object Detection \n(Open Images dataset, COCO dataset, Oxford-IIIT Pets dataset, model zoo, etc.) \n[https://github.com/tensorflow/models/tree/master/research/object_detection](https://github.com/tensorflow/models/tree/master/research/object_detection)\n\n2. Darknet \n(ImageNet dataset, YOLO, etc.) \n[https://pjreddie.com/darknet](https://pjreddie.com/darknet)\n\n3. ImageAI \n[https://github.com/OlafenwaMoses/ImageAI](https://github.com/OlafenwaMoses/ImageAI)\n\n4. ChainerCV \n[https://github.com/chainer/chainercv](https://github.com/chainer/chainercv)\n\n5. External Data and Pre-Trained Model Disclosure Thread (a bit of recursion here ;) ) \n[https://www.kaggle.com/c/google-ai-open-images-object-detection-track/discussion/62741](https://www.kaggle.com/c/google-ai-open-images-object-detection-track/discussion/62741)\n\n", "374811": "we might use any of the following:\nGoogle zoo and object detection tutorials\nKeras zoo\nYolov3 weights from darknet, code from https://github.com/qqwweee/keras-yolo3\nRetinanet from https://github.com/fizyr/keras-retinanet\nDlib\nTiny faces from https://github.com/cydonia999/Tiny_Faces_in_Tensorflow\nhttps://github.com/ipazc/mtcnn\nNeptune.ml open solution\nDetecteron models (caffe2)\nmxnet/gluon models\nChainer zoo\n", "374779": "models from torchvision.models are used: https://pytorch.org/docs/0.4.0/torchvision/models.html", "374773": "Keras model zoo: https://keras.io/applications/", "374771": "I may try \nTensorflow model zoo: https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md Pytorch model zoo: https://pytorch.org/docs/stable/torchvision/models.html Keras model zoo: https://keras.io/applications/\nand vgg16 based pretrianed model [here][1]\n [1]: http://cs.stanford.edu/people/jcjohns/densecap/densecap-pretrained-vgg16.t7.zip", "374734": "I plan to use models from:\n1. Tensorflow model zoo: https://github.com/tensorflow/models/blob/master/research/object_detection/\n2. Keras model zoo: https://keras.io/applications/", "374634": "Tensorflow model zoo: https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md\nPytorch model zoo: https://pytorch.org/docs/stable/torchvision/models.html\nKeras model zoo: https://keras.io/applications/", "374602": "Will be using the Open Images-trained model from tensorflow model zoo: http://download.tensorflow.org/models/object_detection/faster_rcnn_inception_resnet_v2_atrous_oid_2018_01_28.tar.gz", "374556": "Pretrained models:\n\n - ChainerCV pretrained models https://github.com/chainer/chainercv (links to weight files are available in code, e.g., https://github.com/chainer/chainercv/blob/d8f903acbc6e3369a9871aa175893fa5c0f3946c/chainercv/links/model/resnet/resnet.py#L115-L116)\n - deep-residual-networks https://github.com/KaimingHe/deep-residual-networks\n - pretrained-models.pytorch https://github.com/Cadene/pretrained-models.pytorch\n - SENet https://github.com/hujie-frank/SENet\n - TensorFlow-Slim image classification model library https://github.com/tensorflow/models/blob/master/research/slim/README.md\n\nData (images and annotations):\n\n - Open Images Dataset V4 https://storage.googleapis.com/openimages/web/download.html\n - ImageNet http://image-net.org/download-images\n - COCO http://cocodataset.org/#download", "374256": "I will perhaps use one or more pre-trained model(s) from either of the following sources:\n\nPre-trained model on Open Image dataset for detection/fine_tune_checkpoint: http://download.tensorflow.org/models/object_detection/faster_rcnn_inception_resnet_v2_atrous_oid_2018_01_28.tar.gz\n\nYOLO pre-trained model: https://pjreddie.com/darknet/yolo/\n\nPre-trained model from ImageAI:\n\nhttps://github.com/OlafenwaMoses/ImageAI/releases/download/1.0/resnet50_coco_best_v2.0.1.h5\n\nhttps://github.com/OlafenwaMoses/ImageAI/releases/download/1.0/yolo.h5\n\nhttps://github.com/OlafenwaMoses/ImageAI/releases/download/1.0/tiny-yolo.h5\n\nPre-trained models from https://pjreddie.com/darknet/imagenet/.", "373580": "I am using Detectron (https://github.com/facebookresearch/Detectron) which begins its training runs by initializing itself to some pretrained models as listed in the configs directory (https://github.com/facebookresearch/Detectron/tree/master/configs), e.g. https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/47261647/R-50-GN.pkl", "371702": "Keras resnet pretrained on imagenet and tf faster_rcnn_inception_resnet_v2_atrous_oid weights if I get that to work ;)", "375296": "" } }