在python中制作训练文件时如何解决这个错误

Question

所以我一直在制作 A.I.仅作为业余爱好，在 python 中编码经验为 0 的程序。在制作训练文件时，我遇到了一个错误，我无法解决它。

这是我的训练文件-

import numpy as np
import json
import torch
import torch.nn as nn
from torch.utils.data import Dataset,DataLoader
from NeuralNetwork import bag_of_words , tokenize , stem
from Brain import NeuralNet

with open('intents.json','r') as f:
    intents = json.load(f)

all_words = []
tags = []
xy = []

for intent in intents['intents']:
    tag = intent['tag']
    tags.append(tag)

    for pattern in intent['patterns']:
        w = tokenize(pattern)
        all_words.extend(w)
        xy.append((w,tag))

ignore_words = [',','?','/','.','!']
all_words = [stem(w) for w in all_words if w not in ignore_words]
all_words = sorted(set(all_words))
tags = sorted(set(tags))

x_train = []
y_train = []

for (pattern_sentence,tag) in xy:
    bag = bag_of_words(pattern_sentence,all_words)
    x_train.append(bag)
    
    label = tags.index(tag)
    y_train.append(label)

x_train = np.array(x_train)
y_train = np.array(y_train)

num_epochs = 1000
batch_size = 8
learning_rate = 0.001
input_size = len(x_train[0])
hidden_size = 8
output_size = len(tags)

print("Training the model...")

class ChatDataset(Dataset):

    def __init__(self):
        self.n_samples = len(x_train)
        self.x_data = x_train
        self.y_data = y_train

    def __getitem__(self,index):
        return self.x_data[index],self.y_data[index]

    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=device)
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(),lr=learning_rate)

for epoch in range(num_epochs):
    for (words,labels) in train_loader:
        words = words.to(device)
        labels = labels.to(dtype=torch.long).to(device)
        outputs = model(words)
        loss = criterion(outputs,labels)
        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 = "TrainData.pth"
torch.save(data,FILE)

print(f"Training Completed, File Saved to {FILE}")

这是包含所有神经网络层的程序，我将其命名为 Brain.py-

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(input_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)
        return out

    

这是 VSCode 发送给我的错误-

File "f:/Aryav files/J.A.R.V.I.S/J.A.R.V.I.S. Mark III/Train.py", line 81, in <module>
    outputs = model(words)
  File "C:\Users\user\AppData\Local\Programs\Python\Python38\lib\site-packages\torch\nn\modules\module.py", line 1102, in _call_impl
    return forward_call(*input, **kwargs)
  File "C:\Users\user\AppData\Local\Programs\Python\Python38\lib\site-packages\torch\nn\modules\linear.py", line 103, in forward
    return F.linear(input, self.weight, self.bias)
  File "C:\Users\user\AppData\Local\Programs\Python\Python38\lib\site-packages\torch\nn\functional.py", line 1848, in linear
    return torch._C._nn.linear(input, weight, bias)
RuntimeError: mat1 and mat2 shapes cannot be multiplied (8x8 and 15x8)

我是编程的初学者，所以请告诉我确切的行号。以及我需要替换它的行。谢谢你

Answer 1

参考PyTorch documentation，nn.Linear 有输入大小和输出大小作为参数。

所以，在您的网络中：

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(input_size,hidden_size)
    self.l3 = nn.Linear(hidden_size,num_classes)
    self.relu = nn.ReLU()

l1 获取 input_size 的特征并输出 hidden_size 的特征。 l2 也接受 input_size 的特征并输出 hidden_size 的特征。 只有input_size == hidden_size 才有效，我认为在这种情况下，它是不一样的。

您想要实现的是用hidden_size 节点指定所有隐藏层，对吗？ 然后，一个简单的解决方法是

self.l1 = nn.Linear(input_size,hidden_size)
self.l2 = nn.Linear(hidden_size,hidden_size)
self.l3 = nn.Linear(hidden_size,num_classes)

然后，层之间的输入和输出应该匹配。

旁注，我认为您需要另一个 ReLU 实例。这被认为是不好的，原因发布在here。

Answer 2

在您的第二层中，您将 input_size 作为维度而不是 hidden_​​size（这是您上一层的输出大小）。 在您的模型中使用以下行：

self.l1 = nn.Linear(input_size,hidden_size)
self.l2 = nn.Linear(hidden_size,hidden_size)
self.l3 = nn.Linear(hidden_size,num_classes)