train.py

import json
import numpy as np
from nltk_utils import tokenize, stem, bag_of_words

import torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader
from model import NeuralNet

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

ignore_words = ['.', ',', '!', '?']

all_words = set()
tags = set()
xy = []

for intent in intents['intents']:
    tag = intent['tag']
    tags.add(tag)
    for pattern in intent['patterns']:
        tokens = tokenize(pattern)
        for word in [stem(w) for w in tokens if w not in ignore_words]:
            all_words.add(word)
        xy.append((tokens, tag))

all_words = sorted(all_words)
tags = sorted(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)


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

# Hyperparameters
batch_size = 8
hidden_size = 8
output_size = len(tags)
input_size = len(all_words)
learning_rate = 0.001
num_epochs = 1000
#################

dataset = ChatDataset()
train_loader = DataLoader(dataset=dataset, batch_size=batch_size, shuffle=True)

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)


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
        outputs = model(words)
        loss = criterion(outputs, labels)

        # backward
        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,
    "output_size": output_size,
    "hidden_size": hidden_size,
    "all_words": all_words,
    "tags": tags
}

FILE = "data.pth"
torch.save(data, FILE)
print(f"Training complete. File saved to {FILE}")