Python 如何将1D numpy阵列从keras层输出更改为图像(3D numpy阵列)
我有keras图层的输出或特征贴图,但如何将其转换为可以显示的图像(3D numpy阵列)Python 如何将1D numpy阵列从keras层输出更改为图像(3D numpy阵列),python,numpy,neural-network,keras,conv-neural-network,Python,Numpy,Neural Network,Keras,Conv Neural Network,我有keras图层的输出或特征贴图,但如何将其转换为可以显示的图像(3D numpy阵列) model = VGG16(weights='imagenet', include_top=True) layer_outputs = [layer.output for layer in model.layers[1:]] print layer_outputs viz_model = Model(input=model.input, output=layer_out
model = VGG16(weights='imagenet', include_top=True)
layer_outputs = [layer.output for layer in model.layers[1:]]
print layer_outputs
viz_model = Model(input=model.input,
output=layer_outputs)
features = viz_model.predict(x)
output = features[0] #has shape (1,224,224,64)
如有任何意见或建议,我们将不胜感激。谢谢。您可以在迭代每个功能图时将每个功能图添加为子图:
import numpy as np
import matplotlib.pyplot as plt
from pylab import cm
m = np.random.rand(1,224,224,64)
fig = plt.figure()
fig.suptitle("Feature Maps")
for j in range(m.shape[3]):
ax = fig.add_subplot(8, 8, j+1)
ax.matshow(m[0,:,:,j], cmap=cm.gray)
plt.xticks(np.array([]))
plt.yticks(np.array([]))
plt.show()
这会给你一些类似的东西(在我的例子中只是噪音):
这是完美的解决方案!非常感谢你:)