预期 flatten_input 具有 3 个维度，但得到了具有形状的数组

Question

我正在关注tensorflow的基本分类教程。 由于代理原因，我必须离线使用数据集。 因此，我使用的是 mnist 数据集，而不是使用 fashion_mnist 数据库。

from __future__ import absolute_import, division, 

print_function, unicode_literals

# TensorFlow and tf.keras
import tensorflow as tf
from tensorflow import keras

# Helper libraries
import numpy as np
import matplotlib.pyplot as plt
from tensorflow.keras.layers import Flatten, Dense

# Noting class names
class_names = ['Zero', 'One', 'Two', 'Three', 'Four', 'Five', 'Six', 'Seven', 'Eight', 'Nine']

# Load dataset
mnist = keras.datasets.mnist
path = 'C:/projects/VirtualEnvironment/MyScripts/load/mnist.npz'
(train_x, train_y), (test_x, test_y) = mnist.load_data(path)

# Scale, so that training and testing set is preprocessed in the same way
train_x = train_x / 255.0
test_x = test_y / 255.0
train_y = tf.expand_dims(train_y, axis = -1)
test_y = tf.expand_dims(test_y, axis = -1)

#Build the model

#1. Setup the layers
model = keras.Sequential()
model.add(Flatten(input_shape = (28, 28)))
model.add(Dense(128, activation=tf.nn.relu))
model.add(Dense(10, activation=tf.nn.softmax))


#2. Compile the model
model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

# Train the model
model.fit(train_x, train_y, epochs=1)
print("Finished Training")

# Evaluate how the model performs on the test dataset
test_loss, test_acc = model.evaluate(test_x,  test_y, verbose=2)

我收到以下错误： ValueError: Error when checking input: expected flatten_input to have 3 dimensions, but got array with shape (10000, 1). 我对 tensorflow 知之甚少，所以如果有人可以指导我找到有用的网页，或者可以向我解释错误的含义，我将非常感激

Answer 1

这对我有用：

(train_x, train_y), (test_x, test_y) = tf.keras.datasets.mnist.load_data()

# Scale, so that training and testing set is preprocessed in the same way
train_x = train_x / 255.0
test_x = test_x / 255.0

model = tf.keras.Sequential()
model.add(tf.keras.layers.Flatten(input_shape = (28, 28)))
model.add(tf.keras.layers.Dense(128, activation=tf.nn.relu))
model.add(tf.keras.layers.Dense(10, activation=tf.nn.softmax))


#2. Compile the model
model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

# Train the model
model.fit(train_x, train_y, epochs=1)

# Evaluate the model
test_loss, test_acc = model.evaluate(test_x,  test_y, verbose=2)

您收到的错误意味着您在代码中的某处错误地重新调整了输入。

Answer 2

这是由您的代码中的拼写错误引起的

改变这个

test_x = test_y / 255.0

至

test_x = test_x / 255.0

Answer 3

我不确定数组形状问题，但是我可以帮助您解决代理问题，以便您可以正确下载数据集。 假设您从 IT 部门清楚了解如何使用工具，您可以通过在终端级别导出来设置 pip 代理：

假设您的登录凭据是 COMPANY\username

export http_proxy=http://COMPANY%5Cusername:password@proxy_ip:proxy_port
export https_proxy=http://COMPANY%5Cusername:password@proxy_ip:proxy_port

如果您使用的是 conda 环境，请使用 C:\Users\username 处的 .condarc 并编辑为：

channels:
- defaults

# Show channel URLs when displaying what is going to be downloaded and
# in 'conda list'. The default is False.
show_channel_urls: True
allow_other_channels: True

proxy_servers:
    http: http://COMPANY\username:password@proxy_ip:proxy_port
    https: https://COMPANY\username:password@proxy_ip:proxy_port


ssl_verify: False

希望能帮助到你。 为了调试数组形状，我建议您在扩展尺寸后使用 train_y.shape() 和 train_x.shape() 打印 train_y 和 train_x 形状。 该错误指定它得到一个 10000D object 值 1 不应该是这种情况。