Evaluating Training Time of Inception-v3 and Resnet-50,101 Models using TensorFlow across CPU and GPU
K. V. Sai Sundar, Lokeshwar Rao Bonta, Anil Kumar Reddy B., Pallav Kumar Baruah, S Siva Sankara · 2018 Second International Conference on Electronics, Communication and Aerospace Technology (ICECA) · 2018
The performance of Deep Learning models has been the region of interest for a number of researchers over the past five years. Accuracy and Speed have invariably been the indicators in this regard. With the foray of GPUs into this field it becomes necessary to evaluate the performance of the same, keeping CPUs too in the perspective. In this work we present a brief comparison of the training times of a couple of architectures across multiple hardware platforms.