【python实现卷积神经网络】损失函数的定义(均方误差损失、交叉熵损失)
代码来源:https://github.com/eriklindernoren/ML-From-Scratch
卷积神经网络中卷积层Conv2D(带stride、padding)的具体实现:https://www.cnblogs.com/xiximayou/p/12706576.html
激活函数的实现(sigmoid、softmax、tanh、relu、leakyrelu、elu、selu、softplus):https://www.cnblogs.com/xiximayou/p/12713081.html
这节讲解两个基础的损失函数的实现:
from __future__ import division import numpy as np from mlfromscratch.utils import accuracy_score from mlfromscratch.deep_learning.activation_functions import Sigmoid class Loss(object): def loss(self, y_true, y_pred): return NotImplementedError() def gradient(self, y, y_pred): raise NotImplementedError() def acc(self, y, y_pred): return 0 class SquareLoss(Loss): def __init__(self): pass def loss(self, y, y_pred): return 0.5 * np.power((y - y_pred), 2) def gradient(self, y, y_pred): return -(y - y_pred) class CrossEntropy(Loss): def __init__(self): pass def loss(self, y, p): # Avoid division by zero p = np.clip(p, 1e-15, 1 - 1e-15) return - y * np.log(p) - (1 - y) * np.log(1 - p) def acc(self, y, p): return accuracy_score(np.argmax(y, axis=1), np.argmax(p, axis=1)) def gradient(self, y, p): # Avoid division by zero p = np.clip(p, 1e-15, 1 - 1e-15) return - (y / p) + (1 - y) / (1 - p)
其中y是真实值对应的标签,p是预测值对应的标签。
补充:
- numpy.clip():看个例子
import numpy as np
x=np.array([1,2,3,5,6,7,8,9])
np.clip(x,3,8)
array([3, 3, 3, 5, 6, 7, 8, 8])
这里使用到了mlfromscrach/utils/data_operation.py中的:
def accuracy_score(y_true, y_pred): """ Compare y_true to y_pred and return the accuracy """ accuracy = np.sum(y_true == y_pred, axis=0) / len(y_true) return accuracy
用于计算准确率。