I’d like to test DL4J with some heavy tasks like SSD to compare to other framework. So I want to know whether or not DL4J supports SSD modeling and training? If not, is there a plan to support it?
There is no example of building SSD in DL4J.
However, all building blocks for SSD are supported in DL4J. So there shouldn’t be anything that stops you from building it yourself, or - more likely - import it from Keras or Tensorflow.
Here are some examples on how to import things from other frameworks: https://github.com/eclipse/deeplearning4j-examples/blob/master/tensorflow-keras-import-examples/README.md