keras 里的load img用的是PIL,与cv2中的resize算法不同, 两个库的nearest算法结果不同
cv2:
https://www.cnblogs.com/jyxbk/p/7651241.html
cv2.resize(src, dsize[, dst[, fx[, fy[, interpolation]]]]) -> dst
参数说明:
src - 原图
dst - 目标图像。当参数dsize不为0时,dst的大小为size;否则,它的大小需要根据src的大小,参数fx和fy决定。dst的类型(type)和src图像相同
dsize - 目标图像大小。当dsize为0时,它可以通过以下公式计算得出:
所以,参数dsize和参数(fx, fy)不能够同时为0
fx - 水平轴上的比例因子。当它为0时,计算公式如下:
fy - 垂直轴上的比例因子。当它为0时,计算公式如下:
interpolation - 插值方法。共有5种:
1)INTER_NEAREST - 最近邻插值法
2)INTER_LINEAR - 双线性插值法(默认)
3)INTER_AREA - 基于局部像素的重采样(resampling using pixel area relation)。对于图像抽取(image decimation)来说,这可能是一个更好的方法。但如果是放大图像时,它和最近邻法的效果类似。
4)INTER_CUBIC - 基于4x4像素邻域的3次插值法
5)INTER_LANCZOS4 - 基于8x8像素邻域的Lanczos插值
keras load_img
https://github.com/keras-team/keras-preprocessing/blob/master/keras_preprocessing/image/utils.py
def load_img(path, grayscale=False, color_mode='rgb', target_size=None,
interpolation='nearest'):
"""Loads an image into PIL format.
# Arguments
path: Path to image file.
grayscale: DEPRECATED use `color_mode="grayscale"`.
color_mode: The desired image format. One of "grayscale", "rgb", "rgba".
"grayscale" supports 8-bit images and 32-bit signed integer images.
Default: "rgb".
target_size: Either `None` (default to original size)
or tuple of ints `(img_height, img_width)`.
interpolation: Interpolation method used to resample the image if the
target size is different from that of the loaded image.
Supported methods are "nearest", "bilinear", and "bicubic".
If PIL version 1.1.3 or newer is installed, "lanczos" is also
supported. If PIL version 3.4.0 or newer is installed, "box" and
"hamming" are also supported.
Default: "nearest".
# Returns
A PIL Image instance.
# Raises
ImportError: if PIL is not available.
ValueError: if interpolation method is not supported.
"""
if grayscale is True:
warnings.warn('grayscale is deprecated. Please use '
'color_mode = "grayscale"')
color_mode = 'grayscale'
if pil_image is None:
raise ImportError('Could not import PIL.Image. '
'The use of `load_img` requires PIL.')
with open(path, 'rb') as f:
img = pil_image.open(io.BytesIO(f.read()))
if color_mode == 'grayscale':
# if image is not already an 8-bit, 16-bit or 32-bit grayscale image
# convert it to an 8-bit grayscale image.
if img.mode not in ('L', 'I;16', 'I'):
img = img.convert('L')
elif color_mode == 'rgba':
if img.mode != 'RGBA':
img = img.convert('RGBA')
elif color_mode == 'rgb':
if img.mode != 'RGB':
img = img.convert('RGB')
else:
raise ValueError('color_mode must be "grayscale", "rgb", or "rgba"')
if target_size is not None:
width_height_tuple = (target_size[1], target_size[0])
if img.size != width_height_tuple:
if interpolation not in _PIL_INTERPOLATION_METHODS:
raise ValueError(
'Invalid interpolation method {} specified. Supported '
'methods are {}'.format(
interpolation,
", ".join(_PIL_INTERPOLATION_METHODS.keys())))
resample = _PIL_INTERPOLATION_METHODS[interpolation]
img = img.resize(width_height_tuple, resample)
return img