#SqueezeNet New Version
Institute: UC Berkeley
URL: https://arxiv.org/pdf/1803.10615.pdf
Code: https://github.com/amirgholami/SqueezeNext
https://github.com/luuuyi/SqueezeNext.PyTorch (He is not the author.), pytorch
Author: http://amirgholami.org/
Summary
In this work, we introduce SqueezeNext, a new family of neural network architectures. SqueezeNext matches AlexNet's accuracy on the ImageNet with 112x fewer parameters, and its deeper variant exceeds VGG-19's accuracy with only 4.4 Million parameters, (31x smaller). SqueezeNext also achieves better top-5 classification accuracy with 1.3x fewer parameters as compared to MobileNet, while avoiding depthwise-separable convolutions that have poor arithmetic intensity. Using hardware simulation results for power and inference speed on an embedded system, guided us to optimize the baseline model that is 2.59x/8.26x faster and 2.25x/7.5x more energy efficient as compared to SqueezeNet/AlexNet without any accuracy degradation.
#SqueezeNet New Version
Institute: UC Berkeley
URL: https://arxiv.org/pdf/1803.10615.pdf
Code: https://github.com/amirgholami/SqueezeNext
https://github.com/luuuyi/SqueezeNext.PyTorch (He is not the author.), pytorch
Author: http://amirgholami.org/
Summary
In this work, we introduce SqueezeNext, a new family of neural network architectures. SqueezeNext matches AlexNet's accuracy on the ImageNet with 112x fewer parameters, and its deeper variant exceeds VGG-19's accuracy with only 4.4 Million parameters, (31x smaller). SqueezeNext also achieves better top-5 classification accuracy with 1.3x fewer parameters as compared to MobileNet, while avoiding depthwise-separable convolutions that have poor arithmetic intensity. Using hardware simulation results for power and inference speed on an embedded system, guided us to optimize the baseline model that is 2.59x/8.26x faster and 2.25x/7.5x more energy efficient as compared to SqueezeNet/AlexNet without any accuracy degradation.