DSCnet: Replicating Lidar Point Clouds with Deep Sensor Cloning

no code implementations • 17 Nov 2018 • Paden Tomasello, Sammy Sidhu, Anting Shen, Matthew W. Moskewicz, Nobie Redmon, Gayatri Joshi, Romi Phadte, Paras Jain, Forrest Iandola

Recently, autonomous vehicles have created a demand for depth information, which is often obtained using hardware sensors such as Light detection and ranging (LIDAR).

Autonomous Vehicles Depth Estimation +4

A Metaprogramming and Autotuning Framework for Deploying Deep Learning Applications

no code implementations • 21 Nov 2016 • Matthew W. Moskewicz, Ali Jannesari, Kurt Keutzer

On Qualcomm GPUs, we show that our framework enables productive development of target-specific optimizations, and achieves reasonable absolute performance.

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

50 code implementations • 24 Feb 2016 • Forrest N. Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, William J. Dally, Kurt Keutzer

(2) Smaller DNNs require less bandwidth to export a new model from the cloud to an autonomous car.

Image Classification Model Compression +1

FireCaffe: near-linear acceleration of deep neural network training on compute clusters

no code implementations • CVPR 2016 • Forrest N. Iandola, Khalid Ashraf, Matthew W. Moskewicz, Kurt Keutzer

Therefore, the key consideration here is to reduce communication overhead wherever possible, while not degrading the accuracy of the DNN models that we train.

Image Classification