优化FCN用于资源有限的设备,使用量子化和稀疏性增强.
Muhammad Faizan-Khan1, Nisar Ali2, Raja Hashim Ali3
1Departament d'Enginyeria Electrònica, Elèctrica i Automàtica, Universitat Rovira i Virgili, Tarragona, Spain. muhammadfaizan.khan@urv.cat.
Scientific reports
|August 4, 2025
概括
这项研究优化了完全卷积网络 (FCN) 以在有限的设备上实时使用. 全层量化和重新训练显著提高了可达40%的稀疏性,同时保持了89.3%的像素精度.
科学领域:
- 计算机科学 计算机科学
- 人工智能的人工智能
- 机器学习 机器学习
背景情况:
- 资源有限的设备对于部署复杂的深度学习模型,如完全卷积网络 (FCN) 提出了挑战.
- 之前的研究集中在像VGG-16这样的量子化架构上,在FCN-8中对全面的层级量子化进行了有限的探索.
研究的目的:
- 优化FCN,以便在资源有限的设备上实时部署.
- 调查FCN-8架构的全面层级量化技术.
主要方法:
- 提出了一种创新的方法,使用全层定量化与误差最小化算法.
- 采用灵敏度分析来优化网络权重的固定点表示.
- 利用再培训来维持量子化后的网络性能.
主要成果:
- 在极端量子化条件下实现了高达40%的显著网络稀疏性.
- 保持了网络性能,获得了89.3%的像素精度.
- 在图像分类和语义细分任务中都表现出有效性.
结论:
- 全层量化和再训练对于降低网络复杂性是有效的.
- 这种方法成功地保持了FCN的高精度,用于资源有限的设备上的实时应用.
关键词:
深度学习是一种深度学习.固定点定量化定量化定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点定点完全卷积网络的网络完全卷积.灵敏度分析是一种灵敏度分析.相关概念视频
Reducing Line Loss
193
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
193
Linear Approximation in Frequency Domain
131
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
131
Downsampling
255
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
255
Sequence Networks of Rotating Machines
142
A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
142
Ampere-Maxwell's Law: Problem-Solving
754
A parallel-plate capacitor with capacitance C, whose plates have area A and separation distance d, is connected to a resistor R and a battery of voltage V. The current starts to flow at t = 0. What is the displacement current between the capacitor plates at time t? From the properties of the capacitor, what is the corresponding real current?
To solve the problem, we can use the equations from the analysis of an RC circuit and Maxwell's version of Ampère's law.
For the first part of...
To solve the problem, we can use the equations from the analysis of an RC circuit and Maxwell's version of Ampère's law.
For the first part of...
754
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
101
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
101


