# Train model:
model, loss_data = my_models.train_model(model,
optimizer,
train_loader,
val_loader,
device,
dtype,
epoches=2)
# Save model to file:
torch.save(model.state_dict(), MODEL_PATH + MODEL_NAME)
# Save loss data to file:
np.savetxt(LOSS_PATH + 'data_part_4_train.csv', loss_data, delimiter=',')
fix_loss_data('data_part_4_train.csv')
print('Training is Finished !')
if test:
print('Checking model Accuracy over Test Set...')
if model is None:
# load model:
model = my_models.model_2()
model.load_state_dict(torch.load(MODEL_PATH + MODEL_NAME))
model.eval()
# Check accuracy on test set:
test_acc = my_models.check_accuracy(test_loader, model, device, dtype)
# Saving acc to file
acc_train_data = np.loadtxt(LOSS_PATH + 'data_part_4_train.csv',
delimiter=',')
# Train model:
model, loss_data = my_models.train_model(model,
optimizer,
train_loader,
val_loader,
device,
dtype,
epoches=2,
print_every=5)
# Save model to file:
torch.save(model.state_dict(), MODEL_PATH + MODEL_NAME)
# Save loss data to file:
np.savetxt(LOSS_PATH + 'data_part_4_train.csv', loss_data, delimiter=',')
fix_loss_data('data_part_4_train.csv', SECTION_PATH)
print('Training is Finished !')
if test:
print('Checking model Accuracy over Test Set...')
if model is None:
# load model:
model = my_models.model_2()
model.load_state_dict(torch.load(MODEL_PATH + MODEL_NAME))
model.eval()
# Check accuracy on test set:
test_acc = my_models.check_accuracy(test_loader, model, device, dtype)
# Saving acc to file
acc_train_data = np.loadtxt(LOSS_PATH + 'data_part_4_train.csv',
delimiter=',')