Use DenseNet to train and inference the Sin function.

[Instructions]

1. 1_delete_log.ipynb

Delete the old logs file.

2. 2_train.ipynb

Set the parameters:

• input_data_filename: input data file path

• model_filename: the path of the output model file

• scaler_filename: output normalized file path

• epochs: the number of epochs

• learning_rate: learning rate

Set neural network parameters:

• n_feature: the number of features entered

• n_hidden_1: neurons in the first hidden layer

• n_hidden_2: neurons in the second hidden layer

• n_output: the number of outputs

After the setting is completed, it can be executed.

3. 3_kill_tensorboard.ipynb

Delete the previous tensorboard.

4. 4_tensorboard.ipynb

Start tensorboard.

5. 5_inference.ipynb

Set the parameters:

• input_data_filename: input data file path

• model_filename: input model file path

• scaler_filename: input normalized file path

Set neural network parameters:

• n_feature: the number of features entered

• n_hidden_1: neurons in the first hidden layer

• n_hidden_2: neurons in the second hidden layer

• n_output: the number of outputs

After the setting is completed, it can be executed.

After execution, you can see the results of DenseNet's inference.

Jupyter-Data-Dense-Sin-PyTorch-inference.png

This SDK is built in AppForAI - AI Dev Tools.

Purchase license separately: USD 600, permanent authorization, single APP authorization, single machine authorization, one-year activation, one-year download, one-year update, one-year email technical support.