Keras (Tensorflow) Implementation of MNasNet and an example for training and evaluating it on the MNIST dataset. Check also the eager execution implementation.
A Tensorflow Keras implementation (Graph and eager execution) of Mnasnet: MnasNet: Platform-Aware Neural Architecture Search for Mobile.
- Python 2.7+
- Tensorflow-gpu 1.10
Train the MNasNet model on the MNIST dataset! just execute:
For checking and inspecting the Mnasnet model described in the paper, execute:
Train it with eager execution
Train the MNasNet (eager) model on the MNIST dataset! just execute:
The eager execution implementation also outputs logs on Tensorboard. For its visualization:
tensorboard --logdir=train_log:./logs/train, test_log:./logs/test
MnasNet for... Semantic Segmentation!
In this other repository, FC-Mnasnet I added a decoder to the MnasNet architecture in order to turn it into a semantic segmentation model.