我正在使用Mac上的Anaconda中的Jupyter Notebook。与Keras和Tensorflow一起用于神经网络构建。
我调整了图像大小，并将它们移动到目录中。它们是RGB图像（3色通道）。在展平图像并分割成我的CNN的训练/测试后，它不会让我重塑我的图像。我正在尝试重塑的训练集有7151个图像，大小为256乘256.这是代码：
img_rows, img_cols = 256, 256
# number of channels
img_channels = 3
#%%
# data
path1 = 'C:\\Users\\PALASH\\Desktop\\safeunsafe\\inputdata'#path of folder of images
path2 = 'C:\\Users\\PALASH\\Desktop\\safeunsafe\\resizeddata' #path of folder to save images
listing = os.listdir(path1)
num_samples=size(listing)
#for file in listing:
# im = Image.open(path1 + '\\' + file)
# img = im.resize((img_rows,img_cols))
# gray = img.convert('L')
#need to do some more processing here
# gray.save(path2 +'\\' + file, "JPEG")
imlist = os.listdir(path2)
im1 = array(Image.open('C:\\Users\\NAME\\Desktop\\safeunsafe\\resizeddata' + '\\'+ imlist[0])) # open one image to get size
m,n = im1.shape[0:2] # get the size of the images
imnbr = len(imlist) # get the number of images
# create matrix to store all flattened images
immatrix = array([array(Image.open('C:\\Users\\NAME\\Desktop\\safeunsafe\\resizeddata'+ '\\' + im2))#.flatten()
for im2 in imlist],'f')
label=np.ones((num_samples,),dtype = int)
label[0:5723]=0
label[5723:]=1
data,Label = shuffle(immatrix,label, random_state=2)
train_data = [data,Label]
(X, y) = (train_data[0],train_data[1])
# STEP 1: split X and y into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=4)
**X_train = X_train.reshape(X_train.shape[0],3,img_rows,img_cols)
X_test = X_test.reshape(X_test.shape[0], 3, img_rows, img_cols)**
代码是返回此错误的原因：
**cannot reshape array of size 468647936 into shape (7151,3,256,256)**
如何解决此问题？我正在尝试用RGB图像训练CNN，并且我意识到它没有正确地重塑，因为7151 * 3 * 256 * 256不等于原始形状。我应该改变什么来正确地重塑图像？
这是我目前的模特：
`model = Sequential()
model.add(Conv2D(32,(26,26), input_shape=(256,256,3)))
model.add(Activation('relu'))
model.add(Conv2D(14,14))
model.add(Activation('relu'))
model.add(Conv2D(9,9))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Conv2D(3,3))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Flatten())
model.add(Dense(128))
model.add(Dense(64))
model.add(Dense(2))
以下是我的模型摘要：
Layer (type) Output Shape Param #
=================================================================
conv2d_1 (Conv2D) (None, 231, 231, 32) 64928
_________________________________________________________________
activation_1 (Activation) (None, 231, 231, 32) 0
_________________________________________________________________
conv2d_2 (Conv2D) (None, 218, 218, 14) 87822
_________________________________________________________________
activation_2 (Activation) (None, 218, 218, 14) 0
_________________________________________________________________
conv2d_3 (Conv2D) (None, 210, 210, 9) 10215
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 105, 105, 9) 0
_________________________________________________________________
conv2d_4 (Conv2D) (None, 103, 103, 3) 246
_________________________________________________________________
activation_3 (Activation) (None, 103, 103, 3) 0
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 51, 51, 3) 0
_________________________________________________________________
flatten_1 (Flatten) (None, 7803) 0
_________________________________________________________________
dense_1 (Dense) (None, 128) 998912
_________________________________________________________________
dense_2 (Dense) (None, 64) 8256
_________________________________________________________________
dense_3 (Dense) (None, 2) 130
_________________________________________________________________
activation_4 (Activation) (None, 2) 0
=================================================================
Total params: 1,170,509
Trainable params: 1,170,509
Non-trainable params: 0