TensorFlow学习笔记（一）

光复制几个代码到自己机器上跑是没有用的。要理解！公式理解有困难，就用图片辅助理解！

MNIST中数字的表示方法

什么是one-hot？

"One-hot" encoding means that you represent the label "6" by using a vector of 10 values, all zeros but the 6th value which is 1. It is handy here because the format is very similar to how our neural network outputs ts predictions, also as a vector of 10 values.

也就是说，用二进制0，1来表示：

softmax

y = tf.nn.softmax(tf.matmul(x,W) + b)

用这两张图来理解这个公式：

参考文献

• 1 https://sites.google.com/site/nttrungmtwiki/home/it/data-science---python/tensorflow
• 2 https://www.oreilly.com/learning/not-another-mnist-tutorial-with-tensorflow