1 code implementation • 10 Sep 2019 • Mostafa Elhoushi, Ye Henry Tian, Zihao Chen, Farhan Shafiq, Joey Yiwei Li
In our approach, we train the model from scratch (i. e., randomly initialized weights) with its original architecture for a small number of epochs, then the model is decomposed, and then continue training the decomposed model till the end.
1 code implementation • 30 May 2019 • Mostafa Elhoushi, Zihao Chen, Farhan Shafiq, Ye Henry Tian, Joey Yiwei Li
This family of neural network architectures (that use convolutional shifts and fully connected shifts) is referred to as DeepShift models.
no code implementations • 18 Dec 2017 • Farhan Shafiq, Takato Yamada, Antonio T. Vilchez, Sakyasingha Dasgupta
In this paper, we present an automatic flow from trained TensorFlow models to FPGA system on chip implementation of binarized CNN.