lasagne

How to calculate the number of parameters for convolutional neural network?

只愿长相守 提交于 2019-11-26 15:06:30
问题 I'm using Lasagne to create a CNN for the MNIST dataset. I'm following closely to this example: Convolutional Neural Networks and Feature Extraction with Python. The CNN architecture I have at the moment, which doesn't include any dropout layers, is: NeuralNet( layers=[('input', layers.InputLayer), # Input Layer ('conv2d1', layers.Conv2DLayer), # Convolutional Layer ('maxpool1', layers.MaxPool2DLayer), # 2D Max Pooling Layer ('conv2d2', layers.Conv2DLayer), # Convolutional Layer ('maxpool2',