 PyTorch Release NotesRN-08516-001_v23.07 | July 2023 PyTorch Release Notes PyTorch RN-08516-001_v23.07 | ii Table of Contents Chapter 1. PyTorch Overview..................................................... based on PyTorch 0.4.1. PyTorch 0.4.1 is released and included with this container. See the release notes at https://github.com/ pytorch/pytorch/releases for significant changes from PyTorch 0.4. ‣ Apex0 码力 | 365 页 | 2.94 MB | 1 年前3 PyTorch Release NotesRN-08516-001_v23.07 | July 2023 PyTorch Release Notes PyTorch RN-08516-001_v23.07 | ii Table of Contents Chapter 1. PyTorch Overview..................................................... based on PyTorch 0.4.1. PyTorch 0.4.1 is released and included with this container. See the release notes at https://github.com/ pytorch/pytorch/releases for significant changes from PyTorch 0.4. ‣ Apex0 码力 | 365 页 | 2.94 MB | 1 年前3
 Lecture Notes on Linear RegressionLecture Notes on Linear Regression Feng Li fli@sdu.edu.cn Shandong University, China 1 Linear Regression Problem In regression problem, we aim at predicting a continuous target value given an input0 码力 | 6 页 | 455.98 KB | 1 年前3 Lecture Notes on Linear RegressionLecture Notes on Linear Regression Feng Li fli@sdu.edu.cn Shandong University, China 1 Linear Regression Problem In regression problem, we aim at predicting a continuous target value given an input0 码力 | 6 页 | 455.98 KB | 1 年前3
 Lecture Notes on Support Vector MachineLecture Notes on Support Vector Machine Feng Li fli@sdu.edu.cn Shandong University, China 1 Hyperplane and Margin In a n-dimensional space, a hyper plane is defined by ωT x + b = 0 (1) where ω ∈ Rn0 码力 | 18 页 | 509.37 KB | 1 年前3 Lecture Notes on Support Vector MachineLecture Notes on Support Vector Machine Feng Li fli@sdu.edu.cn Shandong University, China 1 Hyperplane and Margin In a n-dimensional space, a hyper plane is defined by ωT x + b = 0 (1) where ω ∈ Rn0 码力 | 18 页 | 509.37 KB | 1 年前3
 Lecture Notes on Gaussian Discriminant Analysis, NaiveLecture Notes on Gaussian Discriminant Analysis, Naive Bayes and EM Algorithm Feng Li fli@sdu.edu.cn Shandong University, China 1 Bayes’ Theorem and Inference Bayes’ theorem is stated mathematically0 码力 | 19 页 | 238.80 KB | 1 年前3 Lecture Notes on Gaussian Discriminant Analysis, NaiveLecture Notes on Gaussian Discriminant Analysis, Naive Bayes and EM Algorithm Feng Li fli@sdu.edu.cn Shandong University, China 1 Bayes’ Theorem and Inference Bayes’ theorem is stated mathematically0 码力 | 19 页 | 238.80 KB | 1 年前3
 QCon北京2018-《从键盘输入到神经网络--深度学习在彭博的应用》-李碧野to 2018 © 2018 Bloomberg Finance L.P. All rights reserved. Final Notes © 2018 Bloomberg Finance L.P. All rights reserved. Final Notes Deep Learning can achieve superhuman accuracy for the right problems0 码力 | 64 页 | 13.45 MB | 1 年前3 QCon北京2018-《从键盘输入到神经网络--深度学习在彭博的应用》-李碧野to 2018 © 2018 Bloomberg Finance L.P. All rights reserved. Final Notes © 2018 Bloomberg Finance L.P. All rights reserved. Final Notes Deep Learning can achieve superhuman accuracy for the right problems0 码力 | 64 页 | 13.45 MB | 1 年前3
 动手学深度学习 v2.0表12.4.1和 表12.4.2中的小结来自Eliot Eshelman163,他们将数字的更新版本保存到GitHub gist164。 表12.4.1: 常见延迟。 Action Time Notes L1 cache reference/hit 1.5 ns 4 cycles Floating‐point add/mult/FMA 1.5 ns 4 cycles continues on com/eshelman/343a1c46cb3fba142c1afdcdeec17646 12.4. 硬件 525 表 12.4.1 – continued from previous page Action Time Notes L2 cache reference/hit 5 ns 12 ~ 17 cycles Branch mispredict 6 ns 15 ~ 20 cycles L3 cache hit (unshared (seek+rotation) 10 ms Send packet CA‐>Netherlands‐>CA 150 ms 表12.4.2: NVIDIA Tesla GPU的延迟. Action Time Notes GPU Shared Memory access 30 ns 30~90 cycles (bank conflicts add latency) GPU Global Memory access0 码力 | 797 页 | 29.45 MB | 1 年前3 动手学深度学习 v2.0表12.4.1和 表12.4.2中的小结来自Eliot Eshelman163,他们将数字的更新版本保存到GitHub gist164。 表12.4.1: 常见延迟。 Action Time Notes L1 cache reference/hit 1.5 ns 4 cycles Floating‐point add/mult/FMA 1.5 ns 4 cycles continues on com/eshelman/343a1c46cb3fba142c1afdcdeec17646 12.4. 硬件 525 表 12.4.1 – continued from previous page Action Time Notes L2 cache reference/hit 5 ns 12 ~ 17 cycles Branch mispredict 6 ns 15 ~ 20 cycles L3 cache hit (unshared (seek+rotation) 10 ms Send packet CA‐>Netherlands‐>CA 150 ms 表12.4.2: NVIDIA Tesla GPU的延迟. Action Time Notes GPU Shared Memory access 30 ns 30~90 cycles (bank conflicts add latency) GPU Global Memory access0 码力 | 797 页 | 29.45 MB | 1 年前3
 【PyTorch深度学习-龙龙老师】-测试版202112Statistics, Fort Lauderdale, FL, USA, 2011. [3] J. Mizera-Pietraszko 和 P. Pichappan, Lecture Notes in Real-Time Intelligent Systems, Springer International Publishing, 2017.0 码力 | 439 页 | 29.91 MB | 1 年前3 【PyTorch深度学习-龙龙老师】-测试版202112Statistics, Fort Lauderdale, FL, USA, 2011. [3] J. Mizera-Pietraszko 和 P. Pichappan, Lecture Notes in Real-Time Intelligent Systems, Springer International Publishing, 2017.0 码力 | 439 页 | 29.91 MB | 1 年前3
共 7 条
- 1













