EAST-eval.py

前言

今天来学习测试模块，前面大多数的函数都讲解完了，今天主要看看代码实现的功能。话不多时先附上整篇代码：

import cv2
import time
import math
import os
import numpy as np
import tensorflow as tf

import locality_aware_nms as nms_locality


tf.app.flags.DEFINE_string('test_data_path', '/tmp/ch4_test_images/images/', '')
tf.app.flags.DEFINE_string('gpu_list', '0', '')
tf.app.flags.DEFINE_string('checkpoint_path', '/tmp/east_icdar2015_resnet_v1_50_rbox/', '')
tf.app.flags.DEFINE_string('output_dir', '/tmp/ch4_test_images/images/', '')
tf.app.flags.DEFINE_bool('no_write_images', False, 'do not write images')

import model
from icdar import restore_rectangle

FLAGS = tf.app.flags.FLAGS

def get_images():
    '''
    find image files in test data path
    :return: list of files found
    '''
    files = []
    exts = ['jpg', 'png', 'jpeg', 'JPG']
    for parent, dirnames, filenames in os.walk(FLAGS.test_data_path):
        for filename in filenames:
            for ext in exts:
                if filename.endswith(ext):
                    files.append(os.path.join(parent, filename))
                    break
    print('Find {} images'.format(len(files)))
    return files


def resize_image(im, max_side_len=2400):
    '''
    resize image to a size multiple of 32 which is required by the network
    :param im: the resized image
    :param max_side_len: limit of max image size to avoid out of memory in gpu
    :return: the resized image and the resize ratio
    '''
    h, w, _ = im.shape

    resize_w = w
    resize_h = h

    # limit the max side
    if max(resize_h, resize_w) > max_side_len:
        ratio = float(max_side_len) / resize_h if resize_h > resize_w else float(max_side_len) / resize_w
    else:
        ratio = 1.
    resize_h = int(resize_h * ratio)
    resize_w = int(resize_w * ratio)

    resize_h = resize_h if resize_h % 32 == 0 else (resize_h // 32 - 1) * 32
    resize_w = resize_w if resize_w % 32 == 0 else (resize_w // 32 - 1) * 32
    resize_h = max(32, resize_h)
    resize_w = max(32, resize_w)
    im = cv2.resize(im, (int(resize_w), int(resize_h)))

    ratio_h = resize_h / float(h)
    ratio_w = resize_w / float(w)

    return im, (ratio_h, ratio_w)


def detect(score_map, geo_map, timer, score_map_thresh=0.8, box_thresh=0.1, nms_thres=0.2):
    '''
    restore text boxes from score map and geo map
    :param score_map:
    :param geo_map:
    :param timer:
    :param score_map_thresh: threshhold for score map
    :param box_thresh: threshhold for boxes
    :param nms_thres: threshold for nms
    :return:
    '''
    if len(score_map.shape) == 4:
        score_map = score_map[0, :, :, 0]
        geo_map = geo_map[0, :, :, ]
    # filter the score map
    xy_text = np.argwhere(score_map > score_map_thresh)
    # sort the text boxes via the y axis
    xy_text = xy_text[np.argsort(xy_text[:, 0])]
    # restore
    start = time.time()
    text_box_restored = restore_rectangle(xy_text[:, ::-1]*4, geo_map[xy_text[:, 0], xy_text[:, 1], :]) # N*4*2
    print('{} text boxes before nms'.format(text_box_restored.shape[0]))
    boxes = np.zeros((text_box_restored.shape[0], 9), dtype=np.float32)
    boxes[:, :8] = text_box_restored.reshape((-1, 8))
    boxes[:, 8] = score_map[xy_text[:, 0], xy_text[:, 1]]
    timer['restore'] = time.time() - start
    # nms part
    start = time.time()
    boxes = nms_locality.nms_locality(boxes.astype(np.float64), nms_thres)
    #boxes = lanms.merge_quadrangle_n9(boxes.astype('float32'), nms_thres)
    timer['nms'] = time.time() - start

    if boxes.shape[0] == 0:
        return None, timer

    # here we filter some low score boxes by the average score map, this is different from the orginal paper
    for i, box in enumerate(boxes):
        mask = np.zeros_like(score_map, dtype=np.uint8)
        cv2.fillPoly(mask, box[:8].reshape((-1, 4, 2)).astype(np.int32) // 4, 1)
        boxes[i, 8] = cv2.mean(score_map, mask)[0]
    boxes = boxes[boxes[:, 8] > box_thresh]

    return boxes, timer


def sort_poly(p):
    min_axis = np.argmin(np.sum(p, axis=1))
    p = p[[min_axis, (min_axis+1)%4, (min_axis+2)%4, (min_axis+3)%4]]
    if abs(p[0, 0] - p[1, 0]) > abs(p[0, 1] - p[1, 1]):
        return p
    else:
        return p[[0, 3, 2, 1]]


def main(argv=None):
    import os
    os.environ['CUDA_VISIBLE_DEVICES'] = FLAGS.gpu_list


    try:
        os.makedirs(FLAGS.output_dir)
    except OSError as e:
        if e.errno != 17:
            raise

    with tf.get_default_graph().as_default():
        input_images = tf.placeholder(tf.float32, shape=[None, None, None, 3], name='input_images')
        global_step = tf.get_variable('global_step', [], initializer=tf.constant_initializer(0), trainable=False)

        f_score, f_geometry = model.model(input_images, is_training=False)

        variable_averages = tf.train.ExponentialMovingAverage(0.997, global_step)
        saver = tf.train.Saver(variable_averages.variables_to_restore())

        with tf.Session(config=tf.ConfigProto(allow_soft_placement=True)) as sess:
            ckpt_state = tf.train.get_checkpoint_state(FLAGS.checkpoint_path)
            model_path = os.path.join(FLAGS.checkpoint_path, os.path.basename(ckpt_state.model_checkpoint_path))
            print('Restore from {}'.format(model_path))
            saver.restore(sess, model_path)

            im_fn_list = get_images()
            for im_fn in im_fn_list:
                im = cv2.imread(im_fn)[:, :, ::-1]
                start_time = time.time()
                im_resized, (ratio_h, ratio_w) = resize_image(im)

                timer = {'net': 0, 'restore': 0, 'nms': 0}
                start = time.time()
                score, geometry = sess.run([f_score, f_geometry], feed_dict={input_images: [im_resized]})
                timer['net'] = time.time() - start

                boxes, timer = detect(score_map=score, geo_map=geometry, timer=timer)
                print('{} : net {:.0f}ms, restore {:.0f}ms, nms {:.0f}ms'.format(
                    im_fn, timer['net']*1000, timer['restore']*1000, timer['nms']*1000))

                if boxes is not None:
                    boxes = boxes[:, :8].reshape((-1, 4, 2))
                    boxes[:, :, 0] /= ratio_w
                    boxes[:, :, 1] /= ratio_h

                duration = time.time() - start_time
                print('[timing] {}'.format(duration))

                # save to file
                if boxes is not None:
                    res_file = os.path.join(
                        FLAGS.output_dir,
                        '{}.txt'.format(
                            os.path.basename(im_fn).split('.')[0]))

                    with open(res_file, 'w') as f:
                        for box in boxes:
                            # to avoid submitting errors
                            box = sort_poly(box.astype(np.int32))
                            if np.linalg.norm(box[0] - box[1]) < 5 or np.linalg.norm(box[3]-box[0]) < 5:
                                continue
                            f.write('{},{},{},{},{},{},{},{}\r\n'.format(
                                box[0, 0], box[0, 1], box[1, 0], box[1, 1], box[2, 0], box[2, 1], box[3, 0], box[3, 1],
                            ))
                            cv2.polylines(im[:, :, ::-1], [box.astype(np.int32).reshape((-1, 1, 2))], True, color=(255, 255, 0), thickness=1)
                if not FLAGS.no_write_images:
                    img_path = os.path.join(FLAGS.output_dir, os.path.basename(im_fn))
                    cv2.imwrite(img_path, im[:, :, ::-1])

if __name__ == '__main__':
    tf.app.run()

get_images()

def get_images():
    '''
    find image files in test data path
    :return: list of files found
    '''
    files = []
    exts = ['jpg', 'png', 'jpeg', 'JPG']
    for parent, dirnames, filenames in os.walk(FLAGS.test_data_path):
        for filename in filenames:
            for ext in exts:
                if filename.endswith(ext):
                    files.append(os.path.join(parent, filename))
                    break
    print('Find {} images'.format(len(files)))
    return files

1）Python endswith()
Python endswith() 方法用于判断字符串是否以指定后缀结尾，如果以指定后缀结尾返回True，否则返回False。可选参数"start"与"end"为检索字符串的开始与结束位置。
2）Python os.walk()
os.walk() 方法用于通过在目录树中游走输出在目录中的文件名，向上或者向下。
os.walk() 方法是一个简单易用的文件、目录遍历器，可以帮助我们高效的处理文件、目录方面的事情。
在Unix，Windows中有效。
总结：可以看出这段代码实现了图片的获取和判断，遍历测试文件，然后将文件中符合条件的图片路径保存。

resize_image(im, max_side_len=2400)

def resize_image(im, max_side_len=2400):
    '''
    resize image to a size multiple of 32 which is required by the network
    :param im: the resized image
    :param max_side_len: limit of max image size to avoid out of memory in gpu
    :return: the resized image and the resize ratio
    '''
    h, w, _ = im.shape

    resize_w = w
    resize_h = h

    # limit the max side
    if max(resize_h, resize_w) > max_side_len:
        ratio = float(max_side_len) / resize_h if resize_h > resize_w else float(max_side_len) / resize_w
    else:
        ratio = 1.
    resize_h = int(resize_h * ratio)
    resize_w = int(resize_w * ratio)

    resize_h = resize_h if resize_h % 32 == 0 else (resize_h // 32 - 1) * 32
    resize_w = resize_w if resize_w % 32 == 0 else (resize_w // 32 - 1) * 32
    resize_h = max(32, resize_h)
    resize_w = max(32, resize_w)
    im = cv2.resize(im, (int(resize_w), int(resize_h)))

    ratio_h = resize_h / float(h)
    ratio_w = resize_w / float(w)

    return im, (ratio_h, ratio_w)

这段代码可以看出主要功能是：判断一下图片的尺寸如果在范围内大于32且是32的整数倍，返回原尺寸，并且返回比例1，如果大于尺寸，重置成最大尺寸，并且返回比例
。

detect()

def detect(score_map, geo_map, timer, score_map_thresh=0.8, box_thresh=0.1, nms_thres=0.2):
    '''
    restore text boxes from score map and geo map
    :param score_map:
    :param geo_map:
    :param timer:
    :param score_map_thresh: threshhold for score map
    :param box_thresh: threshhold for boxes
    :param nms_thres: threshold for nms
    :return:
    '''
    if len(score_map.shape) == 4:
        score_map = score_map[0, :, :, 0]
        geo_map = geo_map[0, :, :, ]
    # filter the score map
    xy_text = np.argwhere(score_map > score_map_thresh)
    # sort the text boxes via the y axis
    xy_text = xy_text[np.argsort(xy_text[:, 0])]
    # restore
    start = time.time()
    text_box_restored = restore_rectangle(xy_text[:, ::-1]*4, geo_map[xy_text[:, 0], xy_text[:, 1], :]) # N*4*2
    print('{} text boxes before nms'.format(text_box_restored.shape[0]))
    boxes = np.zeros((text_box_restored.shape[0], 9), dtype=np.float32)
    boxes[:, :8] = text_box_restored.reshape((-1, 8))
    boxes[:, 8] = score_map[xy_text[:, 0], xy_text[:, 1]]
    timer['restore'] = time.time() - start
    # nms part
    start = time.time()
    boxes = nms_locality.nms_locality(boxes.astype(np.float64), nms_thres)
    #boxes = lanms.merge_quadrangle_n9(boxes.astype('float32'), nms_thres)
    timer['nms'] = time.time() - start

    if boxes.shape[0] == 0:
        return None, timer

    # here we filter some low score boxes by the average score map, this is different from the orginal paper
    for i, box in enumerate(boxes):
        mask = np.zeros_like(score_map, dtype=np.uint8)
        cv2.fillPoly(mask, box[:8].reshape((-1, 4, 2)).astype(np.int32) // 4, 1)
        boxes[i, 8] = cv2.mean(score_map, mask)[0]
    boxes = boxes[boxes[:, 8] > box_thresh]

    return boxes, timer

1）np.argsort（）
argsort()函数是将x中的元素从小到大排列，提取其对应的index(索引)，然后输出到y
可以看出这块主要是两个函数：time和nms_locality.nms_locality。这段函数主要是对结果的nms处理后最终文本框和返还处理的时间。

main(argv=None)

def main(argv=None):
    import os
    os.environ['CUDA_VISIBLE_DEVICES'] = FLAGS.gpu_list


    try:
        os.makedirs(FLAGS.output_dir)
    except OSError as e:
        if e.errno != 17:
            raise

    with tf.get_default_graph().as_default():
        input_images = tf.placeholder(tf.float32, shape=[None, None, None, 3], name='input_images')
        global_step = tf.get_variable('global_step', [], initializer=tf.constant_initializer(0), trainable=False)

        f_score, f_geometry = model.model(input_images, is_training=False)

        variable_averages = tf.train.ExponentialMovingAverage(0.997, global_step)
        saver = tf.train.Saver(variable_averages.variables_to_restore())

        with tf.Session(config=tf.ConfigProto(allow_soft_placement=True)) as sess:
            ckpt_state = tf.train.get_checkpoint_state(FLAGS.checkpoint_path)
            model_path = os.path.join(FLAGS.checkpoint_path, os.path.basename(ckpt_state.model_checkpoint_path))
            print('Restore from {}'.format(model_path))
            saver.restore(sess, model_path)

            im_fn_list = get_images()
            for im_fn in im_fn_list:
                im = cv2.imread(im_fn)[:, :, ::-1]
                start_time = time.time()
                im_resized, (ratio_h, ratio_w) = resize_image(im)

                timer = {'net': 0, 'restore': 0, 'nms': 0}
                start = time.time()
                score, geometry = sess.run([f_score, f_geometry], feed_dict={input_images: [im_resized]})
                timer['net'] = time.time() - start

                boxes, timer = detect(score_map=score, geo_map=geometry, timer=timer)
                print('{} : net {:.0f}ms, restore {:.0f}ms, nms {:.0f}ms'.format(
                    im_fn, timer['net']*1000, timer['restore']*1000, timer['nms']*1000))

                if boxes is not None:
                    boxes = boxes[:, :8].reshape((-1, 4, 2))
                    boxes[:, :, 0] /= ratio_w
                    boxes[:, :, 1] /= ratio_h

                duration = time.time() - start_time
                print('[timing] {}'.format(duration))

                # save to file
                if boxes is not None:
                    res_file = os.path.join(
                        FLAGS.output_dir,
                        '{}.txt'.format(
                            os.path.basename(im_fn).split('.')[0]))

                    with open(res_file, 'w') as f:
                        for box in boxes:
                            # to avoid submitting errors
                            box = sort_poly(box.astype(np.int32))
                            if np.linalg.norm(box[0] - box[1]) < 5 or np.linalg.norm(box[3]-box[0]) < 5:
                                continue
                            f.write('{},{},{},{},{},{},{},{}\r\n'.format(
                                box[0, 0], box[0, 1], box[1, 0], box[1, 1], box[2, 0], box[2, 1], box[3, 0], box[3, 1],
                            ))
                            cv2.polylines(im[:, :, ::-1], [box.astype(np.int32).reshape((-1, 1, 2))], True, color=(255, 255, 0), thickness=1)
                if not FLAGS.no_write_images:
                    img_path = os.path.join(FLAGS.output_dir, os.path.basename(im_fn))
                    cv2.imwrite(img_path, im[:, :, ::-1])

1)cv2.polylines
polylines()函数 ,多边形的绘制。
这一段运用到前面的自定义函数，可以看出主要功能就是将测试图片输入模型中，然后将结果经过nms操作输出最终文本框，然后将文本框在图片中画出来，最后保存在相应的路径中。

最后

eval.py的代码解释大就是如此，由于前面大多数函数的讲解，大多数函数已经讲过，所以不再赘述，大家如果跟着前面的文章学习，应该可以理解各段代码的意义，所以这里只给出未出现过的函数解释，和每段功能，如有错误望请指出，再次对各位前辈致以诚挚谢意。