inverse_design_demo / main_thermo.py
Rui Wan
add neural network model
14fdcca
import torch
import numpy as np
import matplotlib.pyplot as plt
from Dataset import Dataset
from model import NeuralNetwork
DEVICE = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# Set global plotting parameters
plt.rcParams.update({'font.size': 14,
'figure.figsize': (10, 8),
'lines.linewidth': 2,
'lines.markersize': 6,
'axes.grid': True,
'axes.labelsize': 16,
'legend.fontsize': 14,
'xtick.labelsize': 14,
'ytick.labelsize': 14,
'figure.autolayout': True
})
def set_seed(seed=42):
np.random.seed(seed)
torch.manual_seed(seed)
if torch.cuda.is_available():
torch.cuda.manual_seed_all(seed)
def train_neural_network(model, inputs, outputs, optimizer, epochs=1000, lr_scheduler=None):
model.train()
for epoch in range(epochs):
optimizer.zero_grad()
predictions = model(inputs)
loss = torch.mean(torch.square(predictions - outputs))
loss.backward()
optimizer.step()
if lr_scheduler:
lr_scheduler.step()
if epoch % 100 == 0:
print(f'Epoch {epoch}, Loss: {loss.item()}, Learning Rate: {optimizer.param_groups[0]["lr"]}')
def main():
set_seed(5324)
dataset = Dataset()
inputs = dataset.get_input(normalize=True)
outputs = dataset.get_output(normalize=True)
idx_train = np.random.choice(len(inputs), size=int(0.98 * len(inputs)), replace=False)
idx_test = np.setdiff1d(np.arange(len(inputs)), idx_train)
inputs_train = torch.tensor(inputs[idx_train], dtype=torch.float32).to(DEVICE)
outputs_train = torch.tensor(outputs[idx_train], dtype=torch.float32).to(DEVICE)
inputs_test = torch.tensor(inputs[idx_test], dtype=torch.float32).to(DEVICE)
outputs_test = torch.tensor(outputs[idx_test], dtype=torch.float32).to(DEVICE)
layer_sizes = [inputs.shape[1]] + [64] * 4 + [outputs.shape[1]]
dropout_rate = 0.00
model = NeuralNetwork(layer_sizes, dropout_rate=dropout_rate, activation=torch.nn.ReLU).to(DEVICE)
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=5000, gamma=0.9)
# Create a proper dataset that keeps input-output pairs together
train_dataset = torch.utils.data.TensorDataset(inputs_train, outputs_train)
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=16, shuffle=True)
# Train the model
epochs = 20000
for epoch in range(epochs):
model.train()
for inputs_batch, outputs_batch in train_loader:
inputs_batch = inputs_batch.to(DEVICE)
outputs_batch = outputs_batch.to(DEVICE)
optimizer.zero_grad()
predictions = model(inputs_batch)
loss = torch.mean(torch.square(predictions - outputs_batch))
loss.backward()
optimizer.step()
if lr_scheduler:
lr_scheduler.step()
if epoch % 500 == 0:
train_pred = model(inputs_train)
train_loss = torch.mean(torch.square(train_pred - outputs_train))
test_pred = model(inputs_test)
test_loss = torch.mean(torch.square(test_pred - outputs_test))
print(f'Epoch {epoch}, Train Loss: {train_loss.item():.6f}, Test Loss: {test_loss.item():.6f}')
# print(f'Learning Rate: {optimizer.param_groups[0]["lr"]}')
predictions = model.predict(inputs_test)
test_loss = torch.mean(torch.square(predictions - outputs_test))
print(f'Test Loss: {test_loss.item()}. Samples: {idx_test}')
x = np.arange(0, len(idx_test))
outputs_test = dataset.denormalize_output(outputs_test.cpu().numpy())
predictions = dataset.denormalize_output(predictions.cpu().numpy())
# for sample in outputs_test:
# print(f'Test samples: {sample}')
plt.figure(figsize=(10, 6))
plt.plot(x, outputs_test[:, 0], color='b', linestyle='--', label='True A1')
plt.plot(x, predictions[:, 0], color='b', linestyle='-', label='Predicted A1')
plt.plot(x, outputs_test[:, 1], color='r', linestyle='--', label='True B1')
plt.plot(x, predictions[:, 1], color='r', linestyle='-', label='Predicted B1')
plt.plot(x, outputs_test[:, 2], color='g', linestyle='--', label='True C1')
plt.plot(x, predictions[:, 2], color='g', linestyle='-', label='Predicted C1')
plt.gca().xaxis.set_major_locator(plt.MaxNLocator(integer=True))
plt.xlabel('Sample Index')
plt.xticks(ticks=range(len(idx_test)),labels=idx_test + 1)
plt.ylabel('Springback Angle (Degrees)')
plt.title('Springback Angle Prediction')
plt.legend(loc='upper right')
plt.savefig('springback_angle_prediction.png')
plt.figure(figsize=(10, 6))
plt.plot(x, outputs_test[:, 3], color='m', linestyle='--', label='True Stress(Max)')
plt.plot(x, predictions[:, 3], color='m', linestyle='-', label='Predicted Stress(Max)')
plt.xlabel('Sample Index')
plt.xticks(ticks=range(len(idx_test)),labels=idx_test + 1)
plt.ylabel('Stress (MPa)')
plt.legend(loc='upper left')
plt.savefig('stress_max_prediction.png')
# MSE
mse = np.mean((predictions - outputs_test) ** 2, axis=0)
print(f'Mean Squared Error for A1: {mse[0]:.6f}, B1: {mse[1]:.6f}, C1: {mse[2]:.6f}, Stress(Max): {mse[3]:.6f}')
# R 2 score
ss_ress = np.sum((outputs_test - predictions) ** 2, axis=0)
ss_tots = np.sum((outputs_test - np.mean(outputs_test, axis=0)) ** 2, axis=0)
r2_scores = 1 - ss_ress / ss_tots
print(f'R² Score for A1: {r2_scores[0]:.6f}, B1: {r2_scores[1]:.6f}, C1: {r2_scores[2]:.6f}, Stress(Max): {r2_scores[3]:.6f}')
# Error
# Save the model
model_save_path = './model_checkpoint.pth'
model_config = {'layer_sizes': layer_sizes,
'dropout_rate': dropout_rate
}
checkpoint = {
'model_state_dict': model.state_dict(),
'model_config': model_config
}
torch.save(checkpoint, model_save_path)
# Load the model
# model = NeuralNetwork(layer_sizes)
# model.load_state_dict(torch.load(model_save_path))
def load_model(model_path):
checkpoint = torch.load(model_path)
model_config = checkpoint['model_config']
model = NeuralNetwork(model_config['layer_sizes'], dropout_rate=model_config['dropout_rate'], activation=torch.nn.ReLU).to(DEVICE)
model.load_state_dict(checkpoint['model_state_dict'])
print(f"Model loaded from {model_path}")
return model
if __name__ == "__main__":
main()
# model = load_model('./model_checkpoint.pth').to(torch.device('cpu'))
# data = Dataset()
# data = Dataset()
# print(np.unique(data.df['Fiber_Volume_Fractions'].to_numpy())[:10])
# test_input = torch.tensor([[2, 0.6, 450.0, 100.0, 500.0]], dtype=torch.float32)
# test_output = model.predict((test_input - torch.tensor(data.input_mean)) / torch.tensor(data.input_std))
# test_output = test_output * torch.tensor(data.output_std) + torch.tensor(data.output_mean)
# print(f"Test Prediction for fixed input {test_input.numpy()}: {test_output.numpy()}")