numpy - 预期 conv2d_1_input 具有形状 (28, 28, 1) 但得到形状为 (1, 28, 28) 的数组

Question

所以我在 keras 上使用 mnist 示例，并且我正在尝试预测我自己的数字。我真的很挣扎如何匹配尺寸大小，因为我似乎无法找到一种方法来调整我的图像大小以在图像编号之后具有行和列。我已经尝试通过 numpy 调整大小但是我只是在错误之后得到错误...

代码

from __future__ import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K
import numpy as np
import cv2

batch_size = 20
num_classes = 10
epochs = 1
img_rows, img_cols = 28, 28

(x_train, y_train), (x_test, y_test) = mnist.load_data()

print("Processing image")   
im = cv2.imread('C:/Users/Luke/pic4.png', 0) #loading the image
print(im.shape) #28*28
im = cv2.resize(im,  (img_rows, img_cols)) 



list = [im]


batch = np.array([list for i in range(1)])   
print(batch.shape)#1*28*28
batch = batch.astype('float32')
batch /= 255

if K.image_data_format() == 'channels_first':
    x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
    x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
    input_shape = (1, img_rows, img_cols)
else:
    x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
    x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
    input_shape = (img_rows, img_cols, 1)

#print("x_train shape")     

x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255

y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

def base_model():
    model = Sequential()
    model.add(Conv2D(32, kernel_size=(3, 3),
                 activation='relu',
                 input_shape=input_shape))
    model.add(Conv2D(64, (3, 3), activation='relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.25))
    model.add(Flatten())
    model.add(Dense(128, activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(num_classes, activation='softmax'))

    model.compile(loss=keras.losses.categorical_crossentropy,
              optimizer=keras.optimizers.Adadelta(),
              metrics=['accuracy'])
return model

cnn_m = base_model()
cnn_m.summary()


print("Predicting image")
cnn_m.predict(batch)
print("Predicted image")

错误

$ python mnist_cnn_test.py
Using TensorFlow backend.

x_train shape: (60000, 28, 28, 1)
60000 train samples
10000 test samples
_________________________________________________________________
Layer (type)                 Output Shape              Param #
=================================================================
conv2d_1 (Conv2D)            (None, 26, 26, 32)        320
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 24, 24, 64)        18496
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 12, 12, 64)        0
_________________________________________________________________
dropout_1 (Dropout)          (None, 12, 12, 64)        0
_________________________________________________________________
flatten_1 (Flatten)          (None, 9216)              0
_________________________________________________________________
dense_1 (Dense)              (None, 128)               1179776
_________________________________________________________________
dropout_2 (Dropout)          (None, 128)               0
_________________________________________________________________
dense_2 (Dense)              (None, 10)                1290
=================================================================
Total params: 1,199,882
Trainable params: 1,199,882
Non-trainable params: 0
_________________________________________________________________
Predicting image
Traceback (most recent call last):
  File "mnist_cnn_test.py", line 100, in <module>
    cnn_m.predict(batch)
  File "C:\Python35\lib\site-packages\keras\models.py", line 1027, in predict
steps=steps)
  File "C:\Python35\lib\site-packages\keras\engine\training.py", line 1782, in predict
    check_batch_axis=False)
  File "C:\Python35\lib\site-packages\keras\engine\training.py", line 120, in _standardize_input_data
str(data_shape))
ValueError: Error when checking : expected conv2d_1_input to have shape (28, 28, 1) but got array with shape (1, 28, 28)

Answer 1

看起来您的数据格式有误。您的数据作为 channels_first(即每个图像为 1 x 28 x 28)传递，但 Conv2D 层期望 channels_last(28 x 28 x 1)。

一个解决方法是将 data_format=channels_first 传递给 Conv2D 和 MaxPooling 层。但是，如果您在 CPU 上运行，则可能不受支持。或者，更改此部分

if K.image_data_format() == 'channels_first':
    x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
    x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
    input_shape = (1, img_rows, img_cols)
else:
    x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
    x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
    input_shape = (img_rows, img_cols, 1)

始终执行 else block ( reshape 为 channels_last 格式)。在这种情况下，不要将 data_format 参数包含到 Conv 层(它默认为 channels_last)。