gpt4 book ai didi

python - Keras 预测()值错误 : input doesn't have the correct dimension

转载 作者:行者123 更新时间:2023-11-30 09:14:20 25 4
gpt4 key购买 nike

我对机器学习完全陌生,我想从一个相当简单的项目开始:使用 mnist 数据集进行数字识别。我正在使用 keras 和 tensorflow,并开始使用我发现的代码 here .网络已正确构建和训练,我现在想做一个简单的预测。对于初学者来说,我只是使用了用于测试的数据集部分中的一张图片,我希望我的输出就是那个数字。 (在这种情况下,输出应该是 7。)这是我的代码:

# Baseline MLP for MNIST dataset
from tensorflow.keras.datasets import mnist
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from keras.utils import np_utils

import numpy as np

# load data
(X_train, y_train), (X_test, y_test) = mnist.load_data()
# flatten 28*28 images to a 784 vector for each image
num_pixels = X_train.shape[1] * X_train.shape[2]
X_train = X_train.reshape((X_train.shape[0], num_pixels)).astype('float32')
X_test = X_test.reshape((X_test.shape[0], num_pixels)).astype('float32')

# normalize inputs from 0-255 to 0-1
X_train = X_train / 255
X_test = X_test / 255

# one hot encode outputs
y_train = np_utils.to_categorical(y_train)
y_test = np_utils.to_categorical(y_test)
num_classes = y_test.shape[1]


# define baseline model
def baseline_model():
# create model
model = Sequential()
model.add(Dense(num_pixels, input_dim=num_pixels, kernel_initializer='normal', activation='relu'))
model.add(Dense(num_classes, kernel_initializer='normal', activation='softmax'))
# Compile model
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
return model

# build the model
model = baseline_model()
print("created model")

# Fit the model
model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=10, batch_size=200, verbose=2)
print("did model.fit")


image_index=0
print("correct result : ", y_test[image_index])
print("shape of the array: ", X_test[0].shape)
print("predicted result : ", model.predict(X_test[image_index]))

现在我收到以下错误:

ValueError: Error when checking input: expected dense_input to have shape (784,) but got array with shape (1,)

尽管我的数组确实具有正确的形状!正如你所看到的,我打印了 print("shape of the array: ", X_test[0].shape) ,它确实返回了shape of the array: (784,)。 784 正是我们想要的尺寸,但我仍然收到该错误。

我花了几个小时试图解决这个问题,但无论我尝试什么(例如 reshape 数组),它似乎都不起作用。显然,对于 keras 的预测函数或数组存在一些误解。您能帮我理解并解决这个问题吗?先感谢您。

最佳答案

因此预测函数仍然期望 0 维度作为样本维度。

当您索引 X_test[0] 时,您基本上删除了这个维度,这导致预测函数现在有 784 个 1 像素的样本!

将代码更改为:

print("predicted result : ", model.predict(X_test[0].reshape(-1,num_pixels)))

现在您应该知道结果概率。

编辑:

如果您只想要最大概率预测数:

print("predicted result : ",  np.argmax(model.predict(X_test[0].reshape(-1,num_pixels)), axis = 1))

关于python - Keras 预测()值错误 : input doesn't have the correct dimension,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/59201542/

25 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com