The “weights” of a neural network is referred as “parameters” in PyTorch code and it is fine-tuned by optimizer during training. On the contrary, hyperparameters are the parameters of a neural network that is fixed by design and not tuned by training. Examples are the number of hidden layers and the choice of activation functions. […]
The post How to Grid Search Hyperparameters for PyTorch Models appeared first on MachineLearningMastery.com.