是否可以为预训练的 Inception 模型（tensorflow 2.0/Keras）提供 2D 灰度图像？
Is it possible to feed the pretrained Inception model (tensorflow 2.0/Keras) with 2D grayscale images?
根据 Keras 2.0 文档，关于可以馈送到预训练初始模型的图像的输入形状：
input_shape: optional shape tuple, only to be specified if include_top
is False (otherwise the input shape has to be (299, 299, 3) (with
'channels_last' data format) or (3, 299, 299) (with 'channels_first'
data format). It should have exactly 3 inputs channels, and width and
height should be no smaller than 75. E.g. (150, 150, 3) would be one
valid value.
但是，我正在处理二维的灰度图像。我应该如何处理这种情况？
伪RGB图像可以复制3次灰度图
import numpy as np
# img=np.zeros((224,224))
如果您的图像的形状长度为 2，只有宽度和高度，您首先需要添加一个额外的尺寸：
img = np.expand_dims(img,-1)
您将最后一个维度重复 3 次：
img = np.repeat(img,3,2)
print(img.shape)
# (224,224,3)
根据 Keras 2.0 文档，关于可以馈送到预训练初始模型的图像的输入形状：
input_shape: optional shape tuple, only to be specified if include_top is False (otherwise the input shape has to be (299, 299, 3) (with 'channels_last' data format) or (3, 299, 299) (with 'channels_first' data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 75. E.g. (150, 150, 3) would be one valid value.
但是，我正在处理二维的灰度图像。我应该如何处理这种情况？
伪RGB图像可以复制3次灰度图
import numpy as np
# img=np.zeros((224,224))
如果您的图像的形状长度为 2，只有宽度和高度，您首先需要添加一个额外的尺寸：
img = np.expand_dims(img,-1)
您将最后一个维度重复 3 次：
img = np.repeat(img,3,2)
print(img.shape)
# (224,224,3)