An Analysis of Deep Neural Network Models for Practical Applications
read the original abstract
Since the emergence of Deep Neural Networks (DNNs) as a prominent technique in the field of computer vision, the ImageNet classification challenge has played a major role in advancing the state-of-the-art. While accuracy figures have steadily increased, the resource utilisation of winning models has not been properly taken into account. In this work, we present a comprehensive analysis of important metrics in practical applications: accuracy, memory footprint, parameters, operations count, inference time and power consumption. Key findings are: (1) power consumption is independent of batch size and architecture; (2) accuracy and inference time are in a hyperbolic relationship; (3) energy constraint is an upper bound on the maximum achievable accuracy and model complexity; (4) the number of operations is a reliable estimate of the inference time. We believe our analysis provides a compelling set of information that helps design and engineer efficient DNNs.
This paper has not been read by Pith yet.
Forward citations
Cited by 8 Pith papers
-
New pointwise convolution in Deep Neural Networks through Extremely Fast and Non Parametric Transforms
Replacing pointwise convolutions with DWHT yields a model with 79.1% fewer parameters, 48.4% fewer FLOPs, and 1.49% higher accuracy than MobileNet-V1 on CIFAR-100.
-
Green Prompting: Characterizing Prompt-driven Energy Costs of LLM Inference
Empirical tests on three LLMs show prompt semantics and task keywords drive inference energy costs more than length, with varying patterns by task.
-
Comparison of Neural Network Architectures for Spectrum Sensing
Empirical comparison finds CNN, RNN and BiRNN achieve similar detection performance with abundant data and resources while FC performs worse except under strict complexity constraints.
-
Benchmarking Physical Performance of Neural Inference Circuits
Authors apply a consistent methodology to benchmark physical performance metrics across neural network architectures and device technologies, identifying promising combinations.
-
DEEP-GAP: Deep-learning Evaluation of Execution Parallelism in GPU Architectural Performance
L4 delivers up to 4.4x higher throughput than T4 for ResNet models, peaks at batch sizes 16-32, and INT8 yields up to 58x gains over CPU baselines.
-
A Transfer Learning Evaluation of Deep Neural Networks for Image Classification
Empirical comparison of transfer learning performance across eleven pre-trained models on five image datasets using accuracy, time, and size metrics.
-
Modern CNNs for IoT Based Farms
A survey of state-of-the-art CNN architectures for agricultural IoT applications that proposes a tailored classification taxonomy and reviews existing research to guide architecture selection.
-
Deep Learning in the Automotive Industry: Recent Advances and Application Examples
An overview of deep learning applications and challenges in the automotive industry, covering ADAS, automated driving, virtual sensing, and data-driven development.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.