TensorFlow & Keras
Some Machine Learning terminology
特征,Feature — The input(s) to our model. In this case, a single value — the degrees in Celsius.
标签,Labels — The output our model predicts. In this case, a single value — the degrees in Fahrenheit.
样本,Example — A pair of inputs/outputs used during training. In our case a pair of values from celsius_q and fahrenheit_a at a specific index, such as (22,72).
Dense Layer,密集层
- connect everything with everything
Fashion MNIIST Dataset
激活函数 ReLU(Rectified Linear Unit)
gives an output of 0 if the input is negative or zero, and if input is positive, then the output will be equal to the input.
其他激活函数还有 Sigmoid、tanh、ELU
CNN
Convolution neural network
- convolution,
kernel 矩阵(Filter)
每个像素值取核矩阵大小的矩阵,计算与核矩阵的叉乘
- maxpooling 最大池化
pool size stride
reduce the size of input image
Overfitting
过少参数,出现偏差 过多参数,overfitting
90% work is cleaning up data
图像增强(Image Augmentation),用各种随机图像转换创建新的训练样本 Dropout,训练中随机关闭某些神经元
迁移学习(transfer learning)
用大型数据集训练过的网络(预训练网络)应用在之前未结果的数据集上。
需要更改 output layer。
hiden layer 的变量不会被训练,称为冻结网络。
MobileNet
移动设备用。