Build Lenet from Scratch

“The Conv layer is the core building block of a Convolutional Network that does most of the computational heavy lifting.”

See this blog for more details.

It is common to see that a max-pooling layer is inserted between convolutional layer in order to reduce the amount of parameters and computation in the network, including some noise. Intuitively, we downsample the volume of the output of convolutional layers because we only want the most significant features in some certain position.

“Left: In this example, the input volume of size [224x224x64] is pooled with filter size 2, stride 2 into output volume of size [112x112x64]. Notice that the volume depth is preserved. Right: The most common downsampling operation is max, giving rise to max pooling, here shown with a stride of 2. That is, each max is taken over 4 numbers (little 2x2 square).”

Neurons have full connections to all activations(flatten th eoutputs) in the previous layer, as seen in regular neural networks. Fully-Connected Layers play classifiers role in the convolutional neural network.

This is the architecture in my code.

Result:

If you like this article and consider it useful for you, please support it with 👏.

Related posts:

The idea of slow living has become popular in the media as a way to live a more meaningful life. It is about slowing down and appreciating the present moment, and making mindful choices about how you…

Samuel delivered a message from the Lord to Saul, instructing him to completely destroy the Amalekites, both the people and animals, sparing nothing. But Samuel discovers that Saul has not done all…

Microsoft Windows 10 Pro 64 is almost as cool as Nintendo 64…. Microsoft FQC-08930. Delivery Method: DVD; Operating System Windows 10 Pro (64-Bit) Specs. In the Box: (1) Microsoft FQC-08930. Delivery…