If you use external data, per this announcement, include a link to the data here!
It must be freely publicly available.
I plan to use the following pretrained models:DenseNet: https ://github.com/flyyufelix/DenseNet-KerasResNet-101: https ://gist.github.com/flyyufelix/65018873f8cb2bbe95f429c474aa1294ResNet-152: https ://gist.github.com/flyyufelix/7e2eafb149f72f4d38dd661882c554a6SqueezeNet: https ://github.com/rcmalli/keras-squeezenetInception v4: https ://github.com/titu1994/Inception-v4/releasesVGG16: https ://gist.github.com/baraldilorenzo/07d7802847aaad0a35d3VGG19: https ://gist.github.com/baraldilorenzo/8d096f48a1be4a2d660dOther Keras models: https ://keras.io/applications/
I plan to use pre-trained VGG-16 referenced here https://github.com/amdegroot/ssd.pytorch#training-ssd and pre-trained pytorch models http://pytorch.org/docs/master/torchvision/models.html
Using keras weights from https ://keras.io/applications/
In addition to listed pretrained models:
DenseNet: https ://github.com/flyyufelix/DenseNet-Kerasand other Keras models: https ://keras.io/applications/
I'm also using
Using this: https://github.com/tensorflow/models/tree/master/research/object_detection
I am using pretrained pytorch models from https://github.com/pytorch/vision
I'm planning to use this https://github.com/yhenon/keras-frcnnAnd the models referenced here: https://github.com/fchollet/deep-learning-models
I am using pretrained 'imagenet' weights for VGG-16 from KERAS applications here: https://keras.io/applications/#vgg16
Trying to use: vgg1, vgg2, mobilenet, resnet, pva, densenet.
I am also using pytorch/vision models.
Pretrained keras weights from https ://keras.io/applications/
Should we post the pretrained models we are using, even if they were already posted?Just in case, I've tried some of the pytorch models already mentioned.