Machine learning 理解pycaffe中的load_image()方法
源描述Machine learning 理解pycaffe中的load_image()方法,machine-learning,computer-vision,neural-network,deep-learning,caffe,Machine Learning,Computer Vision,Neural Network,Deep Learning,Caffe,源描述 Load an image converting from grayscale or alpha as needed. Parameters ---------- filename : string color : boolean flag for color format. True (default) loads as RGB while False loads as intensity (if image is already grayscale). Retur
Load an image converting from grayscale or alpha as needed.
Parameters
----------
filename : string
color : boolean
flag for color format. True (default) loads as RGB while False
loads as intensity (if image is already grayscale).
Returns
-------
image : an image with type np.float32 in range [0, 1]
of size (H x W x 3) in RGB or
of size (H x W x 1) in grayscale.
这是一个如何使用它的例子
input_image = 255 * caffe.io.load_image(IMAGE_FILE)
我的问题是,如果图像文件是RGB颜色,每个通道的值为0-255,并且返回值caffe.io.load\u IMAGE(图像文件)
在范围[0,1]内,乘以255,每个通道的范围仍然是0-255
那么,执行此步骤的目的是什么?将图像读取到[0..1]范围内的浮点类型的原因是:
uint
转换为浮点时,将像素值缩放为[0..1]是很常见的(例如,请参见Matlab)李>
谢谢,现在对我来说更有意义了。