We can also save the network to disk under a new name. We will simulate a call to mx.save_checkpoint, which is run by the neural network during the training process:
mx.save_checkpoint(nnet, "weights/inception-v3/InceptionV3-FE", mx.OptimizationState(1, 0, 0, 0))
Your new network will be located in weights/inception-v3 and consists of two files:
- InceptionV3-FE-symbol.json
- InceptionV3-FE-0000.params
You can reuse it anytime by instantiating it from a 0 checkpoint.