Faster-RCNN_TF代码解读20：blob.py

# --------------------------------------------------------
# Fast R-CNN
# Copyright (c) 2015 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick
# --------------------------------------------------------

"""Blob helper functions."""

import numpy as np
import cv2
#ims为缩放后的图像列表
#函数作用：返回blob，该blob存的是缩放后的im信息，该blob可能右边与下边值为0
def im_list_to_blob(ims):
    """Convert a list of images into a network input.

    Assumes images are already prepared (means subtracted, BGR order, ...).
    """
    #取出该batch里所有缩放后图片长和宽的最大值
    max_shape = np.array([im.shape for im in ims]).max(axis=0)
    #图片数
    num_images = len(ims)
    #做全零array
    blob = np.zeros((num_images, max_shape[0], max_shape[1], 3),
                    dtype=np.float32)
    #im信息存入blob中，该blob可能右边与下边值为0
    for i in xrange(num_images):
        im = ims[i]
        blob[i, 0:im.shape[0], 0:im.shape[1], :] = im

    return blob
#cfg.PIXEL_MEANS 为 np.array([[[102.9801, 115.9465, 122.7717]]])
#target_size为5个缩放比例的随机一个
#cfg.TRAIN.MAX_SIZE为1000
#函数作用：对图像进行缩放，返回缩放后的image以及缩放比例
def prep_im_for_blob(im, pixel_means, target_size, max_size):
    """Mean subtract and scale an image for use in a blob."""
    im = im.astype(np.float32, copy=False)
    #减去3通道的平均值
    im -= pixel_means
    im_shape = im.shape
    #取得长宽的大小值
    im_size_min = np.min(im_shape[0:2])
    im_size_max = np.max(im_shape[0:2])
    im_scale = float(target_size) / float(im_size_min)
    # Prevent the biggest axis from being more than MAX_SIZE
    #防止最长边超过MAX_SIZE
    if np.round(im_scale * im_size_max) > max_size:
        im_scale = float(max_size) / float(im_size_max)
    #对im进行缩放，缩放比例为im_scale
    im = cv2.resize(im, None, None, fx=im_scale, fy=im_scale,
                    interpolation=cv2.INTER_LINEAR)
    #返回缩放后的im与缩放比例
    return im, im_scale