Keras: 基于 Python 的深度学习库 Keras: The Python Deep Learning library* Author: Keras-Team Contributor: 万 震 (WAN Zhen) � wanzhenchn � wanzhen@cqu.edu.cn 2018 年 12 月 24 日 *Copyright © 2018 by Keras-Team Keras-Team 前 言 整理 Keras: 基于 Python 的深度学习库 PDF 版的主要原因在于学习 Keras 深度学习库时方 便本地查阅，下载最新 PDF 版本请访问: https://github.com/wanzhenchn/keras-docs-zh。 感谢 keras-team 所做的中文翻译工作，本文档制作基于此处。 严正声明：本文档可免费用于学习和科学研究，可自由传播，但切勿擅自用于商业用途，由 reason of organizing PDF version based the Chinese Keras Markdown is that it is easy to read locally when learning the Keras Deep Learning Library. For the latest PDF version, please visit https://github

PyTorch is a GPU-accelerated tensor computational framework with a Python front end. Functionality can be easily extended with common Python libraries such as NumPy, SciPy, and Cython. Automatic differentiation Docker 19.03, complete the steps below. The method implemented in your system depends on the DGX OS version that you installed (for DGX systems), the NGC Cloud Image that was provided by a Cloud Service Provider image contains the complete source of the version of PyTorch in /opt/ pytorch. It is prebuilt and installed in the default Python environment (/usr/local/lib/ python3.10/dist-packages/torch) in the container

Keras ii About the Tutorial Keras is an open source deep learning framework for python. It has been developed by an artificial intelligence researcher at Google named Francois Chollet framework. In addition to this, it will be very helpful, if the readers have a sound knowledge of Python and Machine Learning. Copyright & Disclaimer  Copyright 2019 by Tutorials Point (I) Pvt. ................................................................... 3 Keras Installation Using Python ................................................................................................

conda-forge::transformers 1.1.3 从源码安装 pip install git+https://github.com/huggingface/transformers 我们建议您使用 Python3.8 及以上版本和 Pytorch 2.0 及以上版本。 3 Qwen 1.2 快速开始 本指南帮助您快速上手 Qwen1.5 的使用，并提供了如下示例：Hugging Face Transformers API 服务。 首先，确保你已经安装 vLLM>=0.3.0 ： pip install vllm 运行以下代码以构建 vllm 服务。此处我们以 Qwen1.5-7B-Chat 为例： python -m vllm.entrypoints.openai.api_server --model Qwen/Qwen1.5-7B-Chat 然后，您可以使用 create chat interface "content": "Tell me something about large language models."} ], }' 或者您可以按照下面所示的方式，使用 openai Python 包中的 Python 客户端： from openai import OpenAI # Set OpenAI's API key and API base to use vLLM's API server

Pytorch 框架，搭建 好 Pytorch 的开发环境，通过一系列的基础代码练习与演示建立起对深度学习 与 Pytorch 框架的感性认知。 本书内容以 Python 完成全部代码构建与程序演示。本章的主要目标是帮助初 次接触 Python 与 Pytorch 的读者搭建好开发环境，认识与理解 Pytorch 框架 中常见的基础操作函数、学会使用它们完成一些基础的数据处理与流程处理， 为后续内容学习打下良好基础。 Pytorch 介绍与基础知识 1.1 Pytorch 介绍 Pytorch 是开放源代码的机器学习框架，目的是加速从研究 原型到产品开发的过程。其 SDK 主要基于 Python 语言，而 Python 语言作为流行的人工智能开发语言一直很受研究者与 开发者的欢迎。其模型训练支持CPU与GPU、支持分布式训练、 云部署、针对深度学习特定领域有不同的丰富的扩展库。 1.1.1 Pytorch 学习）框架，Pytorch 最初的来源历史可以追溯到另外两个 机器学习框架，第一个是 torch 框架，第二个是 Chainer，实 现了 Eager 模式与自动微分，Pytoch 集成了这两个框架的优 点， 把 Python 语言作为框架的首选编程语言，所以它的名字 是在 torch 的前面加上 Py 之后的 Pytorch。由于 Pytorch 吸 取了之前一些深度学习框架优点，开发难度大大降低、很容易 构

the vertical axis. The rightmost image in the middle row in figure 3-6 is a horizontally flipped version of the central image. # Horizontal Flip transform_and_show(image_path, flip_horizontal=True) Shift inserted word, typically, is a synonym of one of the words in the sentence. Let’s take an example. The python code follows thereafter. Original: We enjoyed our short vacation in Mexico. Transformed: We enjoyed Random Deletion transforms the sentence by deleting a word at random. Here is an example with the python code. Original: We enjoyed our short vacation in Mexico. Transformed: We enjoyed our short vacation

you activate the corresponding environment, you should be able to run Python scripts that uses PyTorch/TensorFlow by the python command: Installing Your Own Miniconda 1. Download Miniconda installer "/export/data/miniconda3/etc/profile.d/conda.csh" conda activate pytorch conda activate tf2 python python_script.py wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh sh Min download speed of pytorch is slow. 4. If PyTorch is successfully installed, then you could see the version of PyTorch by the following command: 5. Verify PyTorch is able to use GPUs. The output should

If you are not familiar with the tensorflow framework, we refer you to the book Deep Learning with Python1. All the code examples in this book are available at the EDL GitHub repository. The code examples 1). x_q = np.minimum(x_q, 2**b - 1) # Return x_q as an unsigned integer. 1 Deep Learning with Python by Francois Chollet # uint8 is the smallest data type supported by numpy. return x_q.astype(np optimized both in hardware and software. Let’s take a look at how we can optimize a slightly easier version of this operation (where D is a vector instead of a matrix) using quantization. Weight Quantization

免地需要使用正式化的 数学符号推导，其中涉及到少量的概率与统计、线性代数、微积分等数学知识，一般要求读 者对这些数学知识有初步印象或了解即可。比起理论基础，读者需要有少量的编程经验，特 别是 Python 语言编程经验，显得更加重要，因为本书更侧重于实用性，而不是堆砌公式。 总的来说，本书适合于大学三年级左右的理工科本科生和研究生，以及其他对人工智能算法 感兴趣的朋友。 本书共 15 章，大体上可分为 5-and-apollo-enterprise-says-it-has- over-130-partners/ 预览版202112 1.5 深度学习框架 13 是一个基于 Python 语言、定位底层运算的计算库，Theano 同时支持 GPU 和 CPU 运 算。由于 Theano 开发效率较低，模型编译时间较长，同时开发人员转投 TensorFlow 等原因，Theano 加速，对神经网络相关层的实现也较欠缺。 ❑ Caffe 由华人贾扬清在 2013 年开发，主要面向使用卷积神经网络的应用场合，并不适 合其它类型的神经网络的应用。Caffe 的主要开发语言是 C++，也提供 Python 语言等 接口，支持 GPU 和 CPU。由于开发时间较早，在业界的知名度较高，2017 年 Facebook 推出了 Caffe 的升级版本 Cafffe2，Caffe2 目前已经融入到 PyTorch

two networks. The one on the left is the original network and the one on the right is its pruned version. Note that the pruned network has fewer nodes and some retained nodes have fewer connections. Let's Sparsity improves compression Let's import the required libraries to start with. We will use the gzip python module for demonstrating compression. The code for this exercise is available as a Jupyter notebook Figure 5-3: 1-D block pruning between two dense layers. The network on the right is the pruned version of the network on the left. The pruned network is a result of pruning the first row of the weight