算法思路总结

最新推荐文章于 2021-11-07 14:31:41 发布

来路与归途

最新推荐文章于 2021-11-07 14:31:41 发布

阅读量278

点赞数

CC 4.0 BY-SA版权

分类专栏：算法思想

本文链接：https://blog.youkuaiyun.com/qq_42233538/article/details/90344392

算法思想专栏收录该内容

13 篇文章

订阅专栏

1.将一个列表截取为batch_size的整数倍，常用于深度神经网络训练

a=[1,2,3,4,5,6]
batch_size=4
b=len(a)%batch_size
print(a[:-b])

输出结果

[1, 2, 3, 4]

2.Faster RCNN锚点的生成

步骤2.1将特征图上的每个点生成一个列表【x,y,x,y】

def generate_anchors_pre(height, width, feat_stride, anchor_scales=(8, 16, 32), anchor_ratios=(0.5, 1, 2)):
    """ A wrapper function to generate anchors given different scales
      Also return the number of anchors in variable 'length'
    """
    #生成9个目标框
    anchors = generate_anchors(ratios=np.array(anchor_ratios),
              scales=np.array(anchor_scales))
    A = anchors.shape[0]
    #步骤1，生成图像网格图
    shift_x = np.arange(0, width) * feat_stride
    shift_y = np.arange(0, height) * feat_stride
    shift_x, shift_y = np.meshgrid(shift_x, shift_y)
    #步骤2，生成[x.T,y.T,x.T,y.T]
    shifts = np.vstack((shift_x.ravel(), shift_y.ravel(), shift_x.ravel(), shift_y.ravel())).transpose()
    K = shifts.shape[0]
    # width changes faster, so here it is H, W, C
    #步骤3，装置为（k,1,4）与瞄点框相加，生成每个特征点的9个目标框
    anchors = anchors.reshape((1, A, 4)) + shifts.reshape((1, K, 4)).transpose((1, 0, 2))
    anchors = anchors.reshape((K * A, 4)).astype(np.float32, copy=False)
    length = np.int32(anchors.shape[0])

    return anchors, length

2.2根据给定的一个目标框大小，生成9个目标框

def generate_anchors(base_size=16, ratios=[0.5, 1, 2],
                     scales=2 ** np.arange(3, 6)):
    """
    Generate anchor (reference) windows by enumerating aspect ratios X
    scales wrt a reference (0, 0, 15, 15) window.
    """
    #生成等面积且长宽比例为ratios=[0.5, 1, 2]的三个框
    base_anchor = np.array([1, 1, base_size, base_size]) - 1
    ratio_anchors = _ratio_enum(base_anchor, ratios)
    # 根据每一个框再生成放大倍数为8,16,32的三个框
    anchors = np.vstack([_scale_enum(ratio_anchors[i, :], scales)
                         for i in range(ratio_anchors.shape[0])])
    return anchors


def _whctrs(anchor):
    """
    Return width, height, x center, and y center for an anchor (window).
    """

    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):
    """
    Given a vector of widths (ws) and heights (hs) around a center
    (x_ctr, y_ctr), output a set of anchors (windows).
    【框左上角点X，框左上角点Y,框右下角点X，框右下角点Y】
    """

    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):
    """
    Enumerate a set of anchors for each aspect ratio wrt an anchor.
    #生成三个等面积，长宽比不同的的框
    """

    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):
    """
    Enumerate a set of anchors for each scale wrt an anchor.
    #将3个等面积，长宽比不同的的框，每个在放大得到3个框
    """

    w, h, x_ctr, y_ctr = _whctrs(anchor)
    ws = w * scales
    hs = h * scales
    anchors = _mkanchors(ws, hs, x_ctr, y_ctr)
    return anchors

2.3将2.1和2.2加在一起，为每个特征图上的像素点生成9个目标框

3，tensorflow模型保存于加载，实现中断训练后，下次训练接着之前的模型进行训练

#1.创建会话对象
sess = tf.Session()
#2.创建模型保存对象
saver = tf.train.Saver()
3.初始化变量
sess.run(tf.global_variables_initializer())
4.判断FLAGS.logs_dir路径下是否有模型存在，如果有，加载最新的训练模型
ckpt = tf.train.get_checkpoint_state(FLAGS.logs_dir)
if ckpt and ckpt.model_checkpoint_path:
    saver.restore(sess, ckpt.model_checkpoint_path)
    print("Model restored...")
5.判断训练，还是验证
5.1若为训练
    保存模型
5.2若为验证
    直接执行代码