A couple of pre-trained tensorflow models for android demos.
A version of the VGG16 net for tensorflow. Converted from Caffee.
A version of the VGG16 net for deeplearning4j.
An implementation of GoogLeNet for deeplearning4j. The main hallmark of this architecture is the improved utilization of the computing resources inside the network.
A version of the AlexNet implemented for the framework Deeplearning4j.
A version of the FaceNet implemented for the framework Deeplearning4j.
An unsupervised system which learns an excellent representation of sentiment, despite being trained only to predict the next character in the text of Amazon reviews.
A general approach for learning many image-to-image tasks.
CNN trained on Places Database could be directly used for scene recognition, while the deep scene features from the higher level layer of CNN could be used as generic features for visual recognition.
The VGG-Face CNN descriptors are computed using our CNN implementation based on the VGG-Very-Deep-16 CNN architecture as described in the paper and are evaluated on the Labeled Faces in the Wild and the YouTube Faces dataset.