Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding
نویسندگان
چکیده
Deep Compression is a three stage compression pipeline: pruning, quantization and Huffman coding. Pruning reduces the number of weights by 10x, quantization further improves the compression rate between 27x and 31x. Huffman coding gives more compression: between 35x and 49x. The compression rate already included the metadata for sparse representation. Deep Compression doesn’t incur loss of accuracy.
منابع مشابه
A Deep Neural Network Compression Pipeline: Pruning, Quantization, Huffman Encoding
Neural networks are both computationally intensive and memory intensive, making them difficult to deploy on embedded systems with limited hardware resources. To address this limitation, We introduce a three stage pipeline: pruning, quantization and Huffman encoding, that work together to reduce the storage requirement of neural networks by 35× to 49× without affecting their accuracy. Our method...
متن کاملUniversal Deep Neural Network Compression
Compression of deep neural networks (DNNs) for memoryand computation-efficient compact feature representations becomes a critical problem particularly for deployment of DNNs on resource-limited platforms. In this paper, we investigate lossy compression of DNNs by weight quantization and lossless source coding for memory-efficient inference. Whereas the previous work addressed non-universal scal...
متن کاملTowards the Limit of Network Quantization
Network quantization is one of network compression techniques to reduce the redundancy of deep neural networks. It reduces the number of distinct network parameter values by quantization in order to save the storage for them. In this paper, we design network quantization schemes that minimize the performance loss due to quantization given a compression ratio constraint. We analyze the quantitat...
متن کاملEfficient Inferencing of Compressed Deep Neural Networks
Large number of weights in deep neural networks makes the models difficult to be deployed in low memory environments such as, mobile phones, IOT edge devices as well as “inferencing as a service” environments on cloud. Prior work has considered reduction in the size of the models, through compression techniques like pruning, quantization, Huffman encoding etc. However, efficient inferencing usi...
متن کاملCompressing Low Precision Deep Neural Networks Using Sparsity-Induced Regularization in Ternary Networks
A low precision deep neural network training technique for producing sparse, ternary neural networks is presented. The technique incorporates hardware implementation costs during training to achieve significant model compression for inference. Training involves three stages: network training using L2 regularization and a quantization threshold regularizer, quantization pruning, and finally retr...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1510.00149 شماره
صفحات -
تاریخ انتشار 2015