Test the output of each layer of CTGAN and other deep learning models and add integration tests

When training and testing CTGAN, as well as other deep learning models, we need to ensure that the output of each layer is as expected, while adding integration tests to verify the overall performance and stability of the model.

Objectives Record the output of each layer: Capture the intermediate output of each layer during the forward process of the model and analyse it. Verify that the output makes sense: check the distribution, shape, mean, and variance of the output of each layer for anomalies. Add integration tests: Run end-to-end tests to ensure logical integrity of model training, generated data. Compare the outputs of different models and evaluate the generative effect of CTGAN with other deep learning models. Run downstream task tests using synthetic data to verify data quality.