NN_training.py

import pickle
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import TensorDataset, DataLoader
from sklearn.model_selection import train_test_split

data_dict = pickle.load(open('./data.pickle', 'rb'))

# Preprocess your data
data = np.array(data_dict['data'])
labels = np.array(data_dict['labels'])

# Convert data to PyTorch tensors
data = torch.tensor(data, dtype=torch.float32)
labels = torch.tensor(labels, dtype=torch.long)

# Function to pad or truncate sequences to a fixed length
def pad_sequences(sequences, maxlen):
    padded_sequences = np.zeros((len(sequences), maxlen))
    for i, seq in enumerate(sequences):
        if len(seq) > maxlen:
            padded_sequences[i, :] = seq[:maxlen]
        else:
            padded_sequences[i, :len(seq)] = seq
    return padded_sequences

# Set the desired fixed length for all sequences
fixed_length = 100  # Adjust this value based on your data

# Pad the sequences to the fixed length
data = torch.tensor(data, dtype=torch.float32)
labels = torch.tensor(labels, dtype=torch.long)

# Split the data into training and test sets
x_train, x_test, y_train, y_test = train_test_split(data, labels, test_size=0.2, random_state=42)

print("x_train shape:", x_train.shape)
print("y_train shape:", y_train.shape)
print("x_test shape:", x_test.shape)
print("y_test shape:", y_test.shape)

# Create TensorDatasets and DataLoaders
train_dataset = TensorDataset(x_train, y_train)
test_dataset = TensorDataset(x_test, y_test)

train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=64, shuffle=False)

# Define your neural network architecture
class NeuralNet(nn.Module):
    def __init__(self, input_size, num_classes):
        super(NeuralNet, self).__init__()
        self.fc1 = nn.Linear(input_size, 128)
        self.relu = nn.ReLU()
        self.fc2 = nn.Linear(128, num_classes)

    def forward(self, x):
        out = self.fc1(x)
        out = self.relu(out)
        out = self.fc2(out)
        return out

# Set device
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

# Hyperparameters
input_size = data.shape[1]
num_classes = len(set(labels.numpy()))
num_epochs = 10
learning_rate = 0.001

# Initialize your neural network
model = NeuralNet(input_size, num_classes).to(device)

# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=learning_rate)

# Train the model
for epoch in range(num_epochs):
    for batch_idx, (data, targets) in enumerate(train_loader):
        # Move data to device
        data = data.to(device)
        targets = targets.to(device)

        # Forward pass
        scores = model(data)
        loss = criterion(scores, targets)

        # Backward pass and optimize
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

    print(f'Epoch {epoch+1}/{num_epochs}, Loss: {loss.item():.4f}')

# Evaluate the model
# Here you would write code to evaluate the model on your test set