[英]How to find accuracy of a model in CNN?
I want to find the accuracy of a customised CNN model.我想找到自定义 CNN 模型的准确性。 I have weights(w), loss value(l) and test data(x_test) with the class variable(y_test).
我有类变量(y_test)的权重(w)、损失值(l)和测试数据(x_test)。 The weights can't be adjusted, they should remain the same.
权重不能调整,它们应该保持不变。 It will be like a single layer feedforward neural network.
它就像一个单层前馈神经网络。
I want to complete this function to give the same accuracy as in Keras.我想完成此功能以提供与 Keras 相同的准确性。
Edit 1: Binary class classification problem.编辑 1:二元类分类问题。
def accuracy(x_test,y_test,w,l):
y_pred=numpy.dot(x_test,w)
acc=...
return acc
How to complete the accuracy statement as they do in Keras or any other API?.如何像在 Keras 或任何其他 API 中那样完成准确性声明?
If you want something similar to keras , you just care about y_test
and y_pred
( y_test
is y_true
):如果你想要类似于keras 的东西,你只关心
y_test
和y_pred
( y_test
是y_true
):
def acc(y_true, y_pred):
return np.equal(np.argmax(y_true, axis=-1), np.argmax(y_pred, axis=-1)).mean()
This is my POC:这是我的 POC:
import numpy as np
# y_test onehot encoded
y_test = np.array([[1, 0, 0],[0, 1, 0],[0, 0, 1], [0, 1, 0], [1, 0, 0]])
y_pred = np.random.random((5,3))
print("y_true: " + str(np.argmax(y_test, axis=-1)))
print("y_pred: " + str(np.argmax(y_pred, axis=-1)))
def acc(y_true, y_pred):
return np.equal(np.argmax(y_true, axis=-1), np.argmax(y_pred, axis=-1)).mean()
print("accuracy: " + str(acc(y_test, y_pred)))
Result:结果:
y_real: [0 1 2 1 0]
y_pred: [1 1 0 1 0]
accuracy: 0.6
Update 1: Since it is for binary classification the function will be this:更新 1:由于它用于二进制分类,因此函数将是:
def acc(y_true, y_pred):
return np.equal(y_true, np.round(y_pred)).mean()
POC:概念验证:
import numpy as np
y_test = np.array([1, 0, 0, 1, 0])
y_pred = np.random.random((5))
print("y_true: " + str(y_test))
print("y_pred: " + str(np.round(y_pred).astype(int)))
def acc(y_true, y_pred):
return np.equal(y_true, np.round(y_pred)).mean()
print("accuracy: " + str(acc(y_test, y_pred)))
If I'm not wrong you can pass your actual
and predicted
values to scoring
function available inside mlxtend
library.如果我没错,您可以将
actual
值和predicted
值传递给mlxtend
库中可用的scoring
函数。
Look Scoring - mlxtend for more explanation.查看评分 - mlxtend以获得更多解释。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.