使用精度度量进行 MNIST 数字分类时出错 [英] Error while using the Precision metric for MNIST digit classification

问题描述

我正在尝试使用 Tensorflow 和 Keras 在 MNIST 数据集上获得较高的精度分数.如果我将指标设置为准确度，我的代码可以正常工作，但是当我将其设置为精度时，它会出现以下错误:

I am trying to achieve a high Precision score on the MNIST dataset using Tensorflow and Keras. My code is working if I set the metric to accuracy but when I set it to precision, it gives the following error:

ValueError: Shapes (32, 10) and (32, 1) are incompatible

这是我的代码:

import tensorflow as tf 
import keras
from tensorflow.keras.datasets import mnist

def bulid_model(n = 1, neuron=30,lr = 3e-3,input_shape=(784,)):
    model = keras.models.Sequential()
    model.add(keras.layers.InputLayer(input_shape=input_shape))
    for layer in range(n):
        model.add(keras.layers.Dense(neuron, activation = 'relu'))
    model.add(keras.layers.Dense(10,activation='softmax'))
    optimizer = keras.optimizers.Adam(lr = lr)
    model.compile(loss = 'sparse_categorical_crossentropy',optimizer=optimizer,metrics = [keras.metrics.Precision()])
    return model

if __name__ == "__main__":
    (X_train,Y_train),(X_test,Y_test) = mnist.load_data()

    X_train = X_train.reshape(60000, 784)
    X_test = X_test.reshape(10000, 784)
    X_train = X_train.astype('float32')
    X_test = X_test.astype('float32')

    X_train /= 255
    X_test /= 255

    model = bulid_model(3,20,0.0156)

    history = model.fit(X_train,Y_train,epochs=50)

谁能帮我解决这个问题?

Can anyone help me with this?

推荐答案

精度，是二元分类的度量.它计算 true_positives 和 false_positives 然后简单地将 true_positives 除以 true_positives 和 false_positives 的总和>.

Precision, is a metric for binary classification. It computes true_positives and false_positives then simply divides true_positives by the sum of true_positives and false_positives.

但是 Accuracy 指标可用于多类分类，如 MNIST，因为它计算预测与标签相等的频率.

But Accuracy metric can be used for multi-class classification like MNIST, because it calculates how often predictions equal labels.

这篇关于使用精度度量进行 MNIST 数字分类时出错的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！