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:\Project\python_test\github\PythonTest\venv\Scripts\python.exe C:\Project\python_test\github\PythonTest\robot_nltk\dlnltk.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 endreturn out
然后编写一个工具nltk_utils.py如下：
import numpy as np
import nltkfrom 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] = 1return baga="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 jsonimport torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoaderfrom nltk_utils import bag_of_words, tokenize, stem
from model import NeuralNetwith 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 listtags.append(tag)for pattern in intent['patterns']:# tokenize each word in the sentencew = tokenize(pattern)# add to our words listall_words.extend(w)# add to xy pairxy.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_sentencebag = bag_of_words(pattern_sentence, all_words)X_train.append(bag)# y: PyTorch CrossEntropyLoss needs only class labels, not one-hotlabel = 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_trainself.y_data = y_train# support indexing such that dataset[i] can be used to get i-th sampledef __getitem__(self, index):return self.x_data[index], self.y_data[index]# we can call len(dataset) to return the sizedef __len__(self):return self.n_samplesdataset = 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 passoutputs = model(words)# if y would be one-hot, we must apply# labels = torch.max(labels, 1)[1]loss = criterion(outputs, labels)# Backward and optimizeoptimizer.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 jsonimport torchfrom model import NeuralNet
from nltk_utils import bag_of_words, tokenizedevice = 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":breaksentence = 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！
https://www.cnblogs.com/kiba/p/18610399
