Implementation of FedAvg used network in Communication Efficient Learning of Deep Networks from Decentralized Data

Viewed 20

How to implement the network used in this paper, the only description of it is: "A CNN with two 5x5 convolution layers (the first with 32 channels, the second with 64, each followed with 2x2 max pooling), a fully connected layer with 512 units and ReLu activation, and a final softmax output layer (1,663,370 total parameters)"

My implementation following this has only 580K parameters rather than 1663370.

Here is my implementation:

model = models.Sequential()

model.add(layers.Conv2D(filters=32,kernel_size=(5,5),activation="relu",input_shape=(28,28,1), strides = [1,1]))
model.add(layers.MaxPooling2D((2, 2)))

model.add(layers.Conv2D(filters=64,kernel_size=(5,5),activation="relu", strides = [1,1]))
model.add(layers.MaxPooling2D((2, 2)))

model.add(layers.Flatten())
model.add(layers.Dense(512, activation='sigmoid'))
model.add(layers.Dense(10,activation='softmax'))
model.summary()
0 Answers
Related