Build a Convolutional Network
Explore the practical steps to construct a convolutional neural network by defining layers, stacking them, and training the model on the CIFAR10 dataset. Understand the role of convolution, pooling, activation functions, loss, and optimization in building an effective CNN.
We'll cover the following...
We'll cover the following...
It is time to apply what we learned about CNNs through an assignment. We will build a fully functional CNN and train it with our familiar CIFAR10 dataset.
The CNN structure will be:
- A conv layer with 3 channels as input, 6 channels as output, and a 5x5 kernel
- A 2x2 max-pooling layer
- A conv layer with 6 channels as input, 16 channels as output, and a 5x5 kernel
- A linear layer with 1655 nodes
- A linear layer with 120 nodes
- A linear layer with 84 nodes
- A linear layer with 10 nodes