Table 2 Hyperparameters and their search space
From: Forest fire and smoke detection using deep learning-based learning without forgetting
Parameter | Search space |
|---|---|
Optimizer | Adam, RMSProp, SGD, Adagrad, Adadelta |
Number of neurons in customized layers | 64, 128, 256, 512, 1024 |
Activation function | Relu, Elu, LeakyRelu and Tanh |
Learning rate | 1e−3, 1e−4, 1e−5, 1e−6 |
Number of epochs | 100, 125, 150, 200 |
Batch size | 32, 64, 128 |