参照:
[stanford]Convolutional Neural Networks (CNNs / ConvNets)
[karpathy]ConvNetJS CIFAR-10 demo
【视频】TensorFlow and deep learning, without a PhD
Architecture Overview
- why ConvNet ?
Regular Neural Nets don’t scale well to full images. In CIFAR-10, images are only of size 32x32x3 (32 wide, 32 high, 3 color channels), so a single fully-connected neuron in a first hidden
layer of a regular Neural Network would have 32*32*3 = 3072 weights.
原文地址:https://www.cnblogs.com/gangzhuzi/p/8232786.html
时间: 2024-11-03 17:41:46