主讲：龙良曲 Outline ▪ PyTorch的发展 ▪ PyTorch与同类框架 ▪ PyTorch功能演示 Torch ▪ 2002年 Torch ▪ 2011年 Torch7 ▪ Lua PyTorch ▪ 2016.10 发布0.1，THNN后端 ▪ 2018.12 发布1.0 ， CAFFE2后端 ▪ 2019.5 发布1.1 ▪ Facebook AI Research

Cafffe2，Caffe2 目前已经融入到 PyTorch 库中。 ❑ Torch 是一个非常优秀的科学计算库，基于较冷门的编程语言 Lua 开发。Torch 灵活性 较高，容易实现自定义网络层，这也是 PyTorch 继承获得的优良基因。但是由于 Lua 语言使用人群较少，Torch 一直未能获得主流应用。 ❑ MXNet 由华人陈天奇和李沐等人开发，是亚马逊公司的官方深度学习框架。采用了 Anaconda to my PATH environment variable”一项，这样可以通过命令行方式调用 Anaconda 程序。如图 1.23 所示，安装程序 询问是否连带安装 VS Code 软件，选择 Skip 即可。整个安装流程约持续 5 分钟，具体时间 预览版202112 第 1 章 人工智能绪论 18 需依据计算机性能而定。 图 1.22 Anaconda 语言编写程序的方式非常多，可以使用 ipython 或者 ipython notebook 方式 交互式编写代码，也可以利用 Sublime Text、PyCharm 和 VS Code 等综合 IDE 开发中大型 项目。本书推荐使用 PyCharm 编写和调试，使用 VS Code 交互式开发，这两者都可以免费 使用，用户自行下载安装，并配置好 Python 解释器即可。限于篇幅，这里不再赘述。 预览版202112

learning follow right after. The quantization section delves into the implementation details using code samples. We finish with a hands-on project that will walk you through the process of applying quantization contains the symbol-code mapping is transmitted along with the encoded data. Figure 2-1: Huffman Encoding & Huffman Tree. Source When decoding the encoded data, we look up the code from the lookup table back. Since the codes are unique for each symbol (in fact, they are prefix codes: no code is a prefix of some other code, which eliminates ambiguity when decoding), we can easily construct the original sequence

English to Spanish translation model. Let’s dig deeper into each of these categories using examples and code samples. Label Invariant Transformations Label invariant transformations transform samples such These values are clipped to 255. We will discuss some examples of image transformations below. The code samples are provided to bridge the theory and practice gap. We have prepared a few helper functions: image_path = 'file:///whalefin.png' Now, let’s go through the various image transformations with code examples. Rotation rotates the image pixels around the center. It is parameterized by . A positive

/Miniconda3-latest-Linux-x86_64.sh • After Miniconda is installed: conda install pytorch -c pytorch Writing code • Up to you; feel free to use emacs, vim, PyCharm, etc. if you want. • Our recommendations: • Install: 1234:localhost:1234 __@__.cs.princeton.edu • First blank is username, second is hostname Jupyter Notebook VS Code • Install the Python extension. • ???????????? Install the Remote Development extension. • Python Jupyter notebooks by delimiting cells/sections with #%% • Debugging PyTorch code is just like debugging any other Python code: see Piazza @108 for info. Also try Jupyter Lab! Why talk about libraries

 Core Layers  Convolution Layers  Pooling Layers  Recurrent Layers A simple python code to represent a neural network model using sequential model is as follows: from keras.models import your root directory under .keras/keras.json file. Keras backend module can be imported using below code: >>> from keras import backend as k If we are using default backend TensorFlow, then the below call and compute_output_shape completes the creating a customized layer. The final and complete code is as follows: from keras import backend as K from keras.layers import Layer Keras

social media posts, please reference the digital RGB or hex code equivalent. When printing, please use CMYK or the listed Pantone code. For UI button elements, please reference “Color Variations communications. When using digitally, please use the hex code or RGB equivalent. When printing, please use CMYK or the listed Pantone code. 9 Brand Guidelines PyTorch Indigo (Digital+Print) social media posts, please reference the digital RGB or hex code equivalent. When printing, please use CMYK or the listed Pantone code. 9 Brand Guidelines PyTorch Super Light Gray (Digital+Print)

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 here. %%capture import gzip import operator same number of weights pruned. Phew! It feels like we have gone through a lot of talk without much code! In chapter four, we trained a model to predict masks for pets to build snapchat like filters. Let’s prunable block using magnitude-based pruning. Note that the below code is in addition to the original segmentation project in chapter four. The code for this project is available as a Jupyter notebook here.

AutoTokenizer device = "cuda" # the device to load the model onto # Now you do not need to add "trust_remote_code=True" model = AutoModelForCausalLM.from_pretrained( "Qwen/Qwen1.5-7B-Chat", torch_dtype="auto", device_map="auto" AutoTokenizer 借助 TextStreamer ，chat 的流式模式变得非常简单。下面我们将展示一个如何使用它的示例： ... # Reuse the code before `model.generate()` in the last code snippet from transformers import TextStreamer streamer = TextStreamer(tokenizer AutoTokenizer device = "cuda" # the device to load the model onto # Now you do not need to add "trust_remote_code=True" model = AutoModelForCausalLM.from_pretrained( "Qwen/Qwen1.5-7B-Chat", torch_dtype="auto", device_map="auto"

[['efficient deep learning x123!']]).numpy()[0, :4] edl_sequence_output array([ 1, 1379, 1585, 1]) The code snippet above returns indices into the vocabulary we created in the previous step. Let's look up the TFHub14. These embeddings use a 250 dimensional vector to represent a token in the vocabulary. The below code snippet transforms the vocab tokens to their corresponding embeddings. import tensorflow_hub as tfhub word2vec_embeddings tensor should be (vocab_size, embedding_dim), i.e., (5000, 250). The following code snippet will verify that. embedding_dim = 250 # The shape of the word2vec_embeddings would be (vocabulary_size