keras中的img_to_array()函数并不等于nd.array().
主要区别在于,img_to_array()不管是2D shape还是3D shape image,返回都是3D Numpy array. 而nd.array()本身不改变shape。
def img_to_array(img, data_format='channels_last', dtype='float32'):
"""Converts a PIL Image instance to a Numpy array.
# Arguments
img: PIL Image instance.
data_format: Image data format,
either "channels_first" or "channels_last".
dtype: Dtype to use for the returned array.
# Returns
A 3D Numpy array.
# Raises
ValueError: if invalid `img` or `data_format` is passed.
"""
if data_format not in {'channels_first', 'channels_last'}:
raise ValueError('Unknown data_format: %s' % data_format)
# Numpy array x has format (height, width, channel)
# or (channel, height, width)
# but original PIL image has format