Firstly the model is created and trained using train.py. The model parameters are also saved at model_state.pt. visualize.py is then used to "look into the cnn". The model is loaded back in using the ...
Number of filters in convolutional layers Number of units in the fully connected layer Dropout rate Learning rate Batch size Visualization: Matplotlib is used to display some results, and TensorBoard ...
Abstract: Fault diagnosis is important to stable operation of power systems, and the machine-learning-based fault-diagnosis models were widely studied because of their strong generalization ability.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results