python 记一下用过的一些方法

1 单通道转3通道

import numpy as np

with tf.Session():
	image, label = sess.run(next_batch)	# batch_size=1
	print(image.shape)	# [224, 224, 1]
	image = np.concatenate((image, image, image), axis=-1)
	print(image.shape)	# [224, 224, 3]
	# image有三个通道，每个通道都是原始的单通道的复制

2增加矩阵维度 numpy.expand_dims(a, axis)

>>> x = np.array([1,2])
>>> x.shape
(2,)
>>> y = np.expand_dims(x, axis=0)
>>> y
array([[1, 2]])
>>> y.shape
(1, 2)
>>> y = np.expand_dims(x, axis=1)  # Equivalent to x[:,newaxis]
>>> y
array([[1],
       [2]])
>>> y.shape
(2, 1)

 

不断更新中......