我首先使用 3 通道图像作为 VGG16 模型的输入，没有问题：
input_images = Input(shape=(img_width, img_height, 3), name='image_input')
vgg_out = base_model(input_images) # Here base_model is a VGG16
现在我想改用 1 通道图像。 所以我是这样做的：
input_images = Input(shape=(img_width, img_height, 1), name='image_input')
repeat_2 = concatenate([input_images, input_images])
repeat_3 = concatenate([repeat_2, input_images])
vgg_out = base_model(repeat_3)
但是我收到一条错误消息：
File "test.py", line 423, in <module>
model = Model(inputs=[input_images], outputs=[vgg_out])
File "C:UserswzhouAppDataLocalContinuumAnaconda2envstensorflowlibsite-packageskeraslegacyinterfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "C:UserswzhouAppDataLocalContinuumAnaconda2envstensorflowlibsite-packageskerasenginenetwork.py", line 93, in __init__
self._init_graph_network(*args, **kwargs)
File "C:UserswzhouAppDataLocalContinuumAnaconda2envstensorflowlibsite-packageskerasenginenetwork.py", line 237, in _init_graph_network
self.inputs, self.outputs)
File "C:UserswzhouAppDataLocalContinuumAnaconda2envstensorflowlibsite-packageskerasenginenetwork.py", line 1430, in _map_graph_network
str(layers_with_complete_input))
ValueError: Graph disconnected: cannot obtain value for tensor Tensor("input_1:0", shape=(?, 64, 64, 3), dtype=float32) at layer "input_1". The following previous layers were accessed without issue: []
在 Keras 中将 1 通道图像转换为 3 通道图像的正确方法是什么？
我在Kaggle上遇到了类似的解决方案，但利用了现有的Keras层类：
from keras.applications.vgg16 import VGG16
from keras.layers import *
img_size_target = 224
img_input = Input(shape=(img_size_target, img_size_target, 1))
img_conc = Concatenate()([img_input, img_input, img_input])
model = VGG16(input_tensor=img_conc)
前几层将如下所示：
型号： "vgg16" __________________________________________________________________________________________________ 图层(类型( 输出形状参数 # 连接到 ================================================================================================== input_20 (输入层( [(无， 224， 224， 1( 0 __________________________________________________________________________________________________ concatenate_1 (连接( (无， 224， 224， 3( 0 input_20[0][0] input_20[0][0] input_20[0][0] __________________________________________________________________________________________________ block1_conv1 (Conv2D( (无， 224， 224， 64( 1792 concatenate_1[0][0]
不知道为什么你不能用自己的方式定义模型，但下面的方法有效。它还修复了您在原始定义中犯的错误，即您必须以正确的方式规范化输入灰度图像，以匹配预训练 VGG 网络中使用的原始图像预处理。否则，加载预训练的权重是没有意义的。
from keras.applications.vgg16 import VGG16
from keras.layers import *
from keras import backend as K
from keras.models import Model
import numpy as np
class Gray2VGGInput( Layer ) :
"""Custom conversion layer
"""
def build( self, x ) :
self.image_mean = K.variable(value=np.array([103.939, 116.779, 123.68]).reshape([1,1,1,3]).astype('float32'),
dtype='float32',
name='imageNet_mean' )
self.built = True
return
def call( self, x ) :
rgb_x = K.concatenate( [x,x,x], axis=-1 )
norm_x = rgb_x - self.image_mean
return norm_x
def compute_output_shape( self, input_shape ) :
return input_shape[:3] + (3,)
# 1. load pretrain
backbone = VGG16(input_shape=(224,224,3) )
# 2. define gray input
gray_image = Input( shape=(224,224,1), name='gray_input' )
# 3. convert to VGG input
vgg_input_image = Gray2VGGInput( name='gray_to_rgb_norm')( gray_image )
# 4. process by pretrained VGG
pred = backbone( vgg_input_image )
# 5. define the model end-to-end
model = Model( input=gray_image, output=pred, name='my_gray_vgg' )
print model.summary()
# 6. test model
a = np.random.randint(0,255,size=(2,224,224,1))
p = model.predict(a)
print p.shape
根据您使用的预训练模型，预处理步骤可能会有所不同(有关更多详细信息，请参阅此处(。