技術標籤：faster-RCNNpython深度學習機器學習資料結構演算法

code
paper

一、原理解析：

① 面積保持不變，長、寬比分別為[0.5, 1, 2]是產生的Anchors box

② 如果經過scales變化，即長、寬分別均為 (168=128)、(1616=256)、(16*32=512)，對應anchor box如圖

③ 綜合以上兩種變換，最後生成9個Anchor box

二、程式碼實現：

# --------------------------------------------------------
# Faster R-CNN
# Copyright (c) 2015 Microsoft
 

# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick and Sean Bell
# --------------------------------------------------------
import numpy as np
def generate_anchors(base_size=16, ratios=[0.5, 1, 2],
                     scales=2**np.arange(3, 6)):
    """通過列舉縱橫比X縮放參考（0、0、15、15）視窗來生成錨定（參考）視窗。"""
 

    base_anchor = np.array([1, 1, base_size, base_size]) - 1 
    ratio_anchors = _ratio_enum(base_anchor, ratios)
    anchors = np.vstack([_scale_enum(ratio_anchors[i, :], scales)
                         for i in xrange(ratio_anchors.shape[0])])
    return anchors

def _whctrs(anchor):
    """
    返回錨點（視窗）的寬度，高度，x中心和y中心。
    """
 

    w = anchor[2] - anchor[0] + 1
    h = anchor[3] - anchor[1] + 1
    x_ctr = anchor[0] + 0.5 * (w - 1)
    y_ctr = anchor[1] + 0.5 * (h - 1)
    return w, h, x_ctr, y_ctr

def _mkanchors(ws, hs, x_ctr, y_ctr):
    """
    給定一個圍繞中心（x_ctr，y_ctr）的寬度（ws）和高度（hs）的向量，輸出一組錨點（windows）。
    """
    ws = ws[:, np.newaxis]
    hs = hs[:, np.newaxis]
    anchors = np.hstack((x_ctr - 0.5 * (ws - 1),
                         y_ctr - 0.5 * (hs - 1),
                         x_ctr + 0.5 * (ws - 1),
                         y_ctr + 0.5 * (hs - 1)))
    return anchors

def _ratio_enum(anchor, ratios):
    """
    為錨的每個縱橫比列舉一組錨。
    """
    w, h, x_ctr, y_ctr = _whctrs(anchor)
    size = w * h
    size_ratios = size / ratios
    ws = np.round(np.sqrt(size_ratios))
    hs = np.round(ws * ratios)
    anchors = _mkanchors(ws, hs, x_ctr, y_ctr)
    return anchors

def _scale_enum(anchor, scales):
    """
    為錨定的每個刻度列舉一組錨定。
    """
    w, h, x_ctr, y_ctr = _whctrs(anchor)
    ws = w * scales
    hs = h * scales
    anchors = _mkanchors(ws, hs, x_ctr, y_ctr)
    return anchors

if __name__ == '__main__':
    import time
    t = time.time()
    a = generate_anchors()
    print time.time() - t
    print a
    from IPython import embed; embed()

參考文獻：
Faster RCNN 學習筆記