# Fixed Point Quantization of Deep Convolutional Networks Source: [Fixed Point Quantization of Deep Convolutional Networks]() Collection index: [llms.txt]() Data updated: 2025-10-25T20:21:33.904Z Authors: Darryl D. Lin, Sachin S. Talathi, V. Sreekanth Annapureddy Published: 2015-11-19T21:37:06.000Z ## Abstract In recent years increasingly complex architectures for deep convolution networks (DCNs) have been proposed to boost the performance on image recognition tasks. However, the gains in performance have come at a cost of substantial increase in computation and model storage resources. Fixed point implementation of DCNs has the potential to alleviate some of these complexities and facilitate potential deployment on embedded hardware. In this paper, we propose a quantizer design for fixed point implementation of DCNs. We formulate and solve an optimization problem to identify optimal fixed point bit-width allocation across DCN layers. Our experiments show that in comparison to equal bit-width settings, the fixed point DCNs with optimized bit width allocation offer \>20% reduction in the model size without any loss in accuracy on CIFAR-10 benchmark. We also demonstrate that fine-tuning can further enhance the accuracy of fixed point DCNs beyond that of the original floating point model. In doing so, we report a new state-of-the-art fixed point performance of 6.78% error-rate on CIFAR-10 benchmark. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on ImageNet (val) (Accuracy, Size, and Memory)](): Image Classification; ImageNet (val); Model Size (Mbits): 127.3. ## Original sources and implementation [Original paper]() [PDF]()