π΅Classic Networks
Network
First Usage
LeNet-5
Hand written digit classification
AlexNet
ImageNet Dataset
VGG-16
ImageNet Dataset
π’ LeNet-5
LeNet-5 is a very simple network - By modern standards -. It only has 7 layers;
among which there are 3 convolutional layers (C1, C3 and C5)
2 sub-sampling (pooling) layers (S2 and S4)
1 fully connected layer (F6)
Output layer
π Visualization of the network

π Summary of the network

πΈ AlexNet
Too similar to LeNet-5
It has more filters per layer
It uses ReLU instead of tanh
SGD with momentum
Uses dropout instead of regularaization
π Visualization of the network

π More Detailed

π Summary of the network

π± VGG-16
π Visualization of the network

π Summary of the network

π More Detailed

π Drawbacks
It is painfully slow to train (It has 138 million parameters π)
π©βπ§ Implementation
π§ Read More
Last updated
Was this helpful?