python - 具有不同输入的集成模型(预计会看到 2 个数组)
问题描述
我已经训练了 2 个模型。
第一个模型是 UNet:
print(model_unet.summary())
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_4 (InputLayer) (None, 128, 128, 1) 0
__________________________________________________________________________________________________
conv2d_26 (Conv2D) (None, 128, 128, 32) 320 input_4[0][0]
__________________________________________________________________________________________________
conv2d_27 (Conv2D) (None, 128, 128, 32) 9248 conv2d_26[0][0]
.....
.....
conv2d_44 (Conv2D) (None, 128, 128, 1) 33 zero_padding2d_4[0][0]
==================================================================================================
Total params: 7,846,081
Trainable params: 7,846,081
Non-trainable params: 0
其次是 ResNet:
print(model_resnet.summary())
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_3 (InputLayer) (None, 128, 128, 3) 0
__________________________________________________________________________________________________
conv1_pad (ZeroPadding2D) (None, 134, 134, 3) 0 input_3[0][0]
....
....
conv2d_25 (Conv2D) (None, 128, 128, 3) 99 zero_padding2d_3[0][0]
==================================================================================================
Total params: 24,186,915
Trainable params: 24,133,795
Non-trainable params: 53,120
UNet 有 1 个通道(灰色),ResNet 有 3 个通道。
然后,我正在尝试创建一个集成模型:
def ensemble(models, models_input):
outputs = [model(models_input[idx]) for idx, model in enumerate(models)]
x = Average()(outputs)
model_inputs = [model for model in models_input]
model = Model(model_inputs, x)
return model
models = [model_unet, model_resnet]
models_input = [Input((128,128,1)), Input((128,128, 3))]
ensemble_model = ensemble(models, models_input)
当我尝试预测验证数据时:
pred_val = ensemble_model.predict(X_val)
我收到错误:
Error when checking model input: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 2 array(s), but instead got the following list of 1 arrays: [array([[[[0.46755977],
[0.52268691],
[0.52766109],
....
X_val.shape is : (800, 128, 128, 1)
我认为问题在于渠道,但我不知道如何克服这一点。
解决方案
如果您的训练数据是灰度图像,并且考虑到您的 ResNet 模型将 RGB 图像作为输入,那么您应该问自己,您想如何从灰度到 RGB?一种答案是将灰度图像重复 3 次以获得 RBG 图像。然后,您可以轻松地定义一个具有一个输入层的模型,该输入层获取您的灰度图像并将它们相应地提供给您定义的模型:
from keras import backend as K
input_image = Input(shape=(128,128,1))
unet_out = model_unet(input_image)
rgb_image = Lambda(lambda x: K.repeat_elements(x, 3, -1))(input_image)
resnet_out = model_resnet(rgb_image)
output = Average()([unet_out, resnet_out])
ensemble_model = Model(input_image, output)
predict
然后您可以使用一个输入数组轻松调用:
pred_val = ensemble_model.predict(X_val)
此解决方案的一种替代方法是使用您在问题中使用的解决方案。但是,您首先需要将图像从灰度转换为 RGB,然后将两个数组传递给predict
方法:
X_val_rgb = np.repeat(X_val, 3, -1)
pred_val = ensemble_model.predict([X_val, X_val_rgb])
推荐阅读
- apache-spark - 从 spark 2.4.8 集群连接到 Confluent 5.5.2 代理
- reactjs - 我如何 npm 链接 React 项目中的模块?
- css - 更改下拉语义 UI 中的元素文本
- javascript - 如何将使用 javascript 的动画限制为特定的屏幕尺寸?
- html - 如何移动此下拉菜单箭头 - HTML/CSS
- php - 如何在php中将“key”和“value”添加到json/array Rest Api
- sql - 减去两个不同的时间戳并在 Oracle 中转换为分钟?
- typescript - 使用 JSX 包从基本 CLI 安装 Vue.js 以使用 TypeScript 呈现 JSX
- r - kableExtra in for - 循环
- sublimetext - Sublime Text 3 插件 HTML 弹出窗口渲染