TensorFlow has five main repositories with a number of selected models. They're a bit established and it's very easy to use them with the TensorFlow framework.
The different examples for the repositories are as follows:
- Image to text models, which allow what's happening on the image to be described
- Image captioning, which classifies the image
- Deep speech, which allows speech to be recognized
- Text summarization, which allows you to make a summary of the text article
- Vid2depth, which produces a depth map based on the video stream