[英]ValueError: Input 0 of layer sequential_1 is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: [None, 256, 256]
Everything is okay until I convert my image to grayscale.在我将图像转换为灰度之前,一切都很好。 So the rgb's shape is
(256, 256, 3)
but grayscale has (256, 256)
.所以 rgb 的形状是
(256, 256, 3)
但灰度有(256, 256)
。 When I feed it, I get that error.当我喂它时,我得到了那个错误。
network = Sequential()
network.add(Convolution2D(32, kernel_size=(3, 3),strides=1,activation='relu',input_shape=(256, 256)))
network.add(MaxPooling2D((2, 2)))
# network.add(Convolution2D(32, kernel_size=(3, 3), strides=1, activation='relu'))
# network.add(MaxPooling2D((2, 2)))
network.add(Convolution2D(64, kernel_size=(3, 3), strides=1, activation='relu'))
network.add(MaxPooling2D((2, 2)))
# network.add(Convolution2D(64, kernel_size=(3, 3), strides=1, activation='relu'))
# network.add(MaxPooling2D((2, 2)))
network.add(Convolution2D(128, kernel_size=(3, 3), strides=1, activation='relu'))
network.add(MaxPooling2D((2, 2)))
# network.add(Convolution2D(128, kernel_size=(3, 3), strides=1, activation='relu'))
# network.add(MaxPooling2D((2, 2)))
network.add(Flatten())
network.add(Dense(256, activation = 'relu'))
network.add(Dense(2, activation = 'softmax'))
checkpoint_path = os.path.join("/---------/grayscale", "weights.best.hdf5")
checkpoint = ModelCheckpoint(checkpoint_path, monitor='val_accuracy', verbose=1, save_best_only=True, mode='max')
es = EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=10)
callbacks_list = [checkpoint, es]
network.compile(optimizer = 'adam', loss = 'categorical_crossentropy', metrics = ['accuracy'])
You have to feed images of shape 256x256x1 in your network.您必须在网络中提供形状为 256x256x1 的图像。
To convert your initial x_train
into your new X_train
:要将您的初始
x_train
转换为您的新X_train
:
X_train=np.reshape(x_train,(x_train.shape[0], x_train.shape[1],x_train.shape[2],1))
and finally change your input_shape from input_shape=(256,256)
to input_shape=(256,256,1)
最后将您的 input_shape 从
input_shape=(256,256)
更改为input_shape=(256,256,1)
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.