are the 3 models training together or independently? Where can we get the multi-task training script? Because i saw you used them for prediction, independently:
self.RNet = mx.model.FeedForward.load(models[1], 1, ctx=ctx)
self.ONet = mx.model.FeedForward.load(models[2], 1, ctx=ctx)
self.LNet = mx.model.FeedForward.load(models[3], 1, ctx=ctx)
if together is needed, how can we construct the mxnet code to train them together ?
are the 3 models training together or independently? Where can we get the multi-task training script? Because i saw you used them for prediction, independently:
if together is needed, how can we construct the mxnet code to train them together ?