前言
最近学习了一新概念，叫科学发现和科技发明，科学发现是高于科技发明的，而这个说法我觉得还是挺有道理的，我们总说中国的科技不如欧美，但我们实际感觉上，不论建筑，硬件还是软件，理论，我们都已经高于欧美了，那为什么还说我们不如欧美呢？
科学发现是高于科技发明就很好的解释了这个问题，即，我们的在线支付，建筑行业等等，这些都是科技发明，而不是科学发现，而科学发现是引领科技发明的，而欧美在科学发现上远远领先我们，科技发明上虽然领先的不多，但也有很多大幅领先的，比如chatgpt。
说这些的主要目的是想说明，软件开发也是科技发明，所以这个行业的高手，再高的水平，也就那么回事。
也就是说，即便你是清北的，一旦你进入科技发明的队伍，那也就那么回事了。
神经网络并不难，我的这个系列文章就证明了，你完全不会python，完全没学过算法，一样可以在短时间内学会。我个人感觉，一周到一个月之内，都能学会。
所以，会的不必高人一等的看别人，不会的也不用觉得人家是高水平。
本文内容
本文主要介绍结合神经网络进行机器人开发。
准备工作
运行代码前，我们需要先下载nltk包。
首先安装nltk的包。
pip install nltk 然后下载nltk工具，编写一个py文件，写代码如下：
import nltk nltk.download() 然后使用管理员打开cmd，运行这个py文件。
C:Projectpython_testgithubPythonTestvenvScriptspython.exe C:Projectpython_testgithubPythonTestrobot_nltkdlnltk.py 然后弹出界面如下，修改保存地址：
PS：有资料说可以直接运行 nltk.download('punkt') ，下载我们需要的指定的包，但我没下载成功，我还是全部下载了。
# nltk.download('punkt') #是 NLTK (Natural Language Toolkit) 库中的一个命令，用来下载名为 'punkt' 的资源，通常用于 分词（Tokenization） # nltk.download('popular') #命令会下载 NLTK 中大部分常用的资源,比punkt的资源更多 代码编写
编写model
首先编写一个NeuralNet(model.py)如下：
import torch.nn as nn class NeuralNet(nn.Module): def __init__(self, input_size, hidden_size, num_classes): super(NeuralNet, self).__init__() self.l1 = nn.Linear(input_size, hidden_size) self.l2 = nn.Linear(hidden_size, hidden_size) self.l3 = nn.Linear(hidden_size, num_classes) self.relu = nn.ReLU() def forward(self, x): out = self.l1(x) out = self.relu(out) out = self.l2(out) out = self.relu(out) out = self.l3(out) # no activation and no softmax at the end return out 然后编写一个工具nltk_utils.py如下：
import numpy as np import nltk from nltk.stem.porter import PorterStemmer stemmer = PorterStemmer() def tokenize(sentence): return nltk.word_tokenize(sentence) def stem(word): return stemmer.stem(word.lower()) def bag_of_words(tokenized_sentence, words): sentence_words = [stem(word) for word in tokenized_sentence] bag = np.zeros(len(words), dtype=np.float32) for idx, w in enumerate(words): if w in sentence_words: bag[idx] = 1 return bag a="How long does shipping take?" print(a) a = tokenize(a) print(a) 这个文件可以直接运行，测试工具内函数的应用。
词干化和token化
词干化就是把单词提取成词干。逻辑如下：
words =["0rganize","organizes", "organizing"] stemmed_words =[stem(w) for w in words] print(stemmed_words) 过程如下图：
token化就是把单词转换成token。
下面这段代码就是测试token化。
a="How long does shipping take?" print(a) a = tokenize(a) print(a) token化的逻辑大致如下：
编写测试数据
编写json文件intents.json（英文版）
{ "intents": [ { "tag": "greeting", "patterns": [ "Hi", "Hey", "How are you", "Is anyone there?", "Hello", "Good day" ], "responses": [ "Hey :-)", "Hello, thanks for visiting", "Hi there, what can I do for you?", "Hi there, how can I help?" ] }, { "tag": "goodbye", "patterns": ["Bye", "See you later", "Goodbye"], "responses": [ "See you later, thanks for visiting", "Have a nice day", "Bye! Come back again soon." ] }, { "tag": "thanks", "patterns": ["Thanks", "Thank you", "That's helpful", "Thank's a lot!"], "responses": ["Happy to help!", "Any time!", "My pleasure"] }, { "tag": "items", "patterns": [ "Which items do you have?", "What kinds of items are there?", "What do you sell?" ], "responses": [ "We sell coffee and tea", "We have coffee and tea" ] }, { "tag": "payments", "patterns": [ "Do you take credit cards?", "Do you accept Mastercard?", "Can I pay with Paypal?", "Are you cash only?" ], "responses": [ "We accept VISA, Mastercard and Paypal", "We accept most major credit cards, and Paypal" ] }, { "tag": "delivery", "patterns": [ "How long does delivery take?", "How long does shipping take?", "When do I get my delivery?" ], "responses": [ "Delivery takes 2-4 days", "Shipping takes 2-4 days" ] }, { "tag": "funny", "patterns": [ "Tell me a joke!", "Tell me something funny!", "Do you know a joke?" ], "responses": [ "Why did the hipster burn his mouth? He drank the coffee before it was cool.", "What did the buffalo say when his son left for college? Bison." ] } ] } intents_cn.json中文版数据。
{ "intents": [ { "tag": "greeting", "patterns": [ "你好", "嗨", "您好", "有谁在吗?", "你好呀", "早上好", "下午好", "晚上好" ], "responses": [ "你好！有什么我可以帮忙的吗？", "您好！感谢您的光临。", "嗨！有什么我可以为您效劳的吗？", "早上好！今天怎么样？" ] }, { "tag": "goodbye", "patterns": [ "再见", "拜拜", "下次见", "保重", "晚安" ], "responses": [ "再见！希望很快能再次见到你。", "拜拜！祝你有个愉快的一天。", "保重！下次见。", "晚安，祝你做个好梦！" ] }, { "tag": "thanks", "patterns": [ "谢谢", "感谢", "多谢", "非常感谢" ], "responses": [ "不客气！很高兴能帮到你。", "没问题！随时为您服务。", "别客气！希望能帮到您。", "很高兴能帮忙！" ] }, { "tag": "help", "patterns": [ "你能帮我做什么?", "你能做什么?", "你能帮助我吗?", "我需要帮助", "能帮我一下吗?" ], "responses": [ "我可以帮您回答问题、提供信息，或者进行简单的任务。", "我能帮助您查询信息、安排任务等。", "您可以问我问题，或者让我做一些简单的事情。", "请告诉我您需要的帮助！" ] }, { "tag": "weather", "patterns": [ "今天天气怎么样?", "今天的天气如何?", "天气预报是什么?", "外面冷吗?", "天气好不好?" ], "responses": [ "今天的天气很好，适合外出！", "今天天气有点冷，记得穿暖和点。", "今天天气晴朗，适合去散步。", "天气晴，温度适宜，非常适合外出。" ] }, { "tag": "about", "patterns": [ "你是什么?", "你是谁?", "你是做什么的?", "你能做些什么?" ], "responses": [ "我是一个聊天机器人，可以回答您的问题和帮助您解决问题。", "我是一个智能助手，帮助您完成各种任务。", "我是一个虚拟助手，可以处理简单的任务和查询。", "我可以帮助您获取信息，或者做一些简单的任务。" ] } ] } 训练数据
训练数据逻辑如下：
import numpy as np import random import json import torch import torch.nn as nn from torch.utils.data import Dataset, DataLoader from nltk_utils import bag_of_words, tokenize, stem from model import NeuralNet with open('intents_cn.json', 'r', encoding='utf-8') as f: intents = json.load(f) all_words = [] tags = [] xy = [] # loop through each sentence in our intents patterns for intent in intents['intents']: tag = intent['tag'] # add to tag list tags.append(tag) for pattern in intent['patterns']: # tokenize each word in the sentence w = tokenize(pattern) # add to our words list all_words.extend(w) # add to xy pair xy.append((w, tag)) # stem and lower each word ignore_words = ['?', '.', '!'] all_words = [stem(w) for w in all_words if w not in ignore_words] # remove duplicates and sort all_words = sorted(set(all_words)) tags = sorted(set(tags)) print(len(xy), "patterns") print(len(tags), "tags:", tags) print(len(all_words), "unique stemmed words:", all_words) # create training data X_train = [] y_train = [] for (pattern_sentence, tag) in xy: # X: bag of words for each pattern_sentence bag = bag_of_words(pattern_sentence, all_words) X_train.append(bag) # y: PyTorch CrossEntropyLoss needs only class labels, not one-hot label = tags.index(tag) y_train.append(label) X_train = np.array(X_train) y_train = np.array(y_train) # Hyper-parameters num_epochs = 1000 batch_size = 8 learning_rate = 0.001 input_size = len(X_train[0]) hidden_size = 8 output_size = len(tags) print(input_size, output_size) class ChatDataset(Dataset): def __init__(self): self.n_samples = len(X_train) self.x_data = X_train self.y_data = y_train # support indexing such that dataset[i] can be used to get i-th sample def __getitem__(self, index): return self.x_data[index], self.y_data[index] # we can call len(dataset) to return the size def __len__(self): return self.n_samples dataset = ChatDataset() train_loader = DataLoader(dataset=dataset, batch_size=batch_size, shuffle=True, num_workers=0) device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') model = NeuralNet(input_size, hidden_size, output_size).to(device) # Loss and optimizer criterion = nn.CrossEntropyLoss() optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate) # Train the model for epoch in range(num_epochs): for (words, labels) in train_loader: words = words.to(device) labels = labels.to(dtype=torch.long).to(device) # Forward pass outputs = model(words) # if y would be one-hot, we must apply # labels = torch.max(labels, 1)[1] loss = criterion(outputs, labels) # Backward and optimize optimizer.zero_grad() loss.backward() optimizer.step() if (epoch+1) % 100 == 0: print (f'Epoch [{epoch+1}/{num_epochs}], Loss: {loss.item():.4f}') print(f'final loss: {loss.item():.4f}') data = { "model_state": model.state_dict(), "input_size": input_size, "hidden_size": hidden_size, "output_size": output_size, "all_words": all_words, "tags": tags } FILE = "data.pth" torch.save(data, FILE) print(f'training complete. file saved to {FILE}') 编写使用聊天
编写使用聊天代码如下：
import random import json import torch from model import NeuralNet from nltk_utils import bag_of_words, tokenize device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') with open('intents_cn.json', 'r',encoding='utf-8') as json_data: intents = json.load(json_data) FILE = "data.pth" data = torch.load(FILE) input_size = data["input_size"] hidden_size = data["hidden_size"] output_size = data["output_size"] all_words = data['all_words'] tags = data['tags'] model_state = data["model_state"] model = NeuralNet(input_size, hidden_size, output_size).to(device) model.load_state_dict(model_state) model.eval() bot_name = "电脑" print("Let's chat! (type 'quit' to exit)") while True: # sentence = "do you use credit cards?" sentence = input("我:") if sentence == "quit": break sentence = tokenize(sentence) X = bag_of_words(sentence, all_words) X = X.reshape(1, X.shape[0]) X = torch.from_numpy(X).to(device) output = model(X) _, predicted = torch.max(output, dim=1) tag = tags[predicted.item()] probs = torch.softmax(output, dim=1) prob = probs[0][predicted.item()] if prob.item() > 0.75: for intent in intents['intents']: if tag == intent["tag"]: print(f"{bot_name}: {random.choice(intent['responses'])}") else: print(f"{bot_name}: 我不知道") 运行效果如下：
传送门：
零基础学习人工智能—Python—Pytorch学习—全集
注：此文章为原创，任何形式的转载都请联系作者获得授权并注明出处！
若您觉得这篇文章还不错，请点击下方的【推荐】，非常感谢！
