泰勒系列基于扩展的视觉变压器模型
概括
一个新的泰勒系列扩展 (TSE) 视觉变压器可以降低内存使用量,同时保持精度. 这种基于TSE的模型显著提高了GPU的部署性能和延迟,即使与模型压缩技术相结合.
科学领域:
- 计算机视觉 计算机视觉
- 机器学习 机器学习
- 深度学习 (Deep Learning) 是一种深度学习.
背景情况:
- 泰勒序列扩展 (TSE) 使用有限序列近似非线性函数.
- 视觉转换器是用于图像分析的强大的深度学习模型.
- 纯粹的视觉转换器可以是计算密集型和要求内存的.
研究的目的:
- 设计一种基于TSE的新型视觉变压器,可以减少内存足迹和计算成本.
- 与标准视觉变压器相比,以保持或提高精度.
- 为了提高部署性能和延迟.
主要方法:
- 开发了一个基于TSE的视觉转换器块,灵感来自第一阶泰勒数列项.
- 嵌入可学习的TSE系数和有限的乘法,以近似的天真变压器操作.
- 在训练动态扩张能力的过程中引入了泰勒跳槽机制.
主要成果:
- 基于TSE的模型在A100和AGX Orin GPU上实现了部署延迟 (1.30-1.45×) 的显著提升,精度损失微不足道.
- 在ImageNet分类,COCO检测和ADE20K细分任务中观察到性能增长.
- 与模型压缩相结合,TSE优化进一步提高了延迟和吞吐量,分别达到1.87×和3.61×.
结论:
- 基于TSE的视觉转换器为天真模型提供了一个有效的替代方案,可以减少记忆负担而不会牺牲准确性.
- 该模型展示了强大的动态扩展能力和显著的现实世界部署优势.
- 基于TSE的优化与模型压缩是直角的,从而实现了协同性能改进.
相关概念视频
Transformers with Off-Nominal Turns Ratios
142
In scenarios involving parallel transformers with disparate ratings, developing per-unit models requires accommodating off-nominal turns ratios. This situation arises when the selected base voltages are not proportional to the transformer’s voltage ratings. Consider a transformer where the rated voltages are related by the term a. If the chosen voltage bases satisfy a relationship involving term b, term c is defined as the ratio of these bases. This ratio is then substituted into the...
142
Types Of Transformers
952
Transformers can provide desired voltages to a circuit by modifying the number of turns in the secondary windings.
If the ratio of the number of turns in the secondary winding to that of the primary winding is greater than one, then the transformer is said to be a step-up transformer. In a step-up transformer, the voltage at the secondary winding is greater than the voltage applied at the primary winding.
However, if this ratio is less than one, the transformer is said to be a step-down...
If the ratio of the number of turns in the secondary winding to that of the primary winding is greater than one, then the transformer is said to be a step-up transformer. In a step-up transformer, the voltage at the secondary winding is greater than the voltage applied at the primary winding.
However, if this ratio is less than one, the transformer is said to be a step-down...
952
Equivalent Circuits for Practical Transformers
400
The practical equivalent circuits of single-phase two-winding transformers exhibit significant deviations from their idealized versions due to the inherent properties of winding resistance and finite core permeability. These properties result in real and reactive power losses, affecting the transformer's performance. Understanding these deviations is crucial for designing more efficient transformers.
In a practical transformer, each winding exhibits resistance and leakage reactance. The...
In a practical transformer, each winding exhibits resistance and leakage reactance. The...
400
Three-Winding Transformers
215
Three identical single-phase transformers can be configured to form a three-phase transformer connection, which involves high-voltage and low-voltage windings. The high-voltage windings are denoted by capital letters A-B-C, while the low-voltage windings are labeled with lowercase letters a-b-c, representing their respective phases. This notation helps distinguish between the high and low voltage sides of the transformer.
In the per-unit equivalent circuit of a grounded Y-Y three-phase...
In the per-unit equivalent circuit of a grounded Y-Y three-phase...
215
Per-Unit Sequence Models
73
An ideal Y-Y transformer, grounded through neutral impedances, displays per-unit sequence networks akin to those of a single-phase ideal transformer when subjected to balanced positive- or negative-sequence currents. These currents do not produce neutral currents, and their associated voltage drops.
Zero-sequence currents, which are identical in magnitude and phase, generate a neutral current, resulting in voltage drops across the neutral impedance and the low-voltage winding. If the...
Zero-sequence currents, which are identical in magnitude and phase, generate a neutral current, resulting in voltage drops across the neutral impedance and the low-voltage winding. If the...
73
The Ideal Transformer
360
In single-phase two-winding transformers, two windings are coiled around a magnetic core characterized by cross-sectional area A and magnetic permeability μ. A phasor current i1 enters the left winding while i2 exits the right winding, establishing the fundamental working of the transformer through electromagnetic principles.
Ampere's Law forms the basis of understanding the magnetic field within the transformer. It states that the integral of the magnetic field intensity's...
Ampere's Law forms the basis of understanding the magnetic field within the transformer. It states that the integral of the magnetic field intensity's...
360


