def main(args):
# 加载图片
image, image_meta, _, _ = image_utils.load_image_gt(
np.random.randint(10), args.image_path, config.IMAGE_SHAPE[0], None)
# 加载模型
config.IMAGES_PER_GPU = 1
m = models.ctpn_net(config, 'test')
if args.weight_path is not None:
m.load_weights(args.weight_path)
else:
m.load_weights(config.WEIGHT_PATH)
# m.summary()
# 模型预测
text_boxes, text_scores, _ = m.predict(np.array([image]))
text_boxes = np_utils.remove_pad(text_boxes[0])
text_scores = np_utils.remove_pad(text_scores[0])[:, 0]
# 文本行检测器
image_meta = image_utils.parse_image_meta(image_meta)
detector = TextDetector(config)
text_lines = detector.detect(text_boxes, text_scores, config.IMAGE_SHAPE,
image_meta['window'])
# print("text_lines:{}".format(text_lines))
boxes_num = 15
fig = plt.figure(figsize=(16, 16))
ax = fig.add_subplot(1, 1, 1)
visualize.display_polygons(image,
text_lines[:boxes_num, :8],
text_lines[:boxes_num, 8],
ax=ax)
fig.savefig('examples.{}.png'.format(np.random.randint(10)))
def __init__(self):
config.USE_SIDE_REFINE = True
config.IMAGES_PER_GPU = 1
config.IMAGE_SHAPE = (1024, 1024, 3)
self.m = models.ctpn_net(config, 'test')
self.m.load_weights(config.WEIGHT_PATH, by_name=True)
self.m.summary()
def main(args):
# 覆盖参数 rewrite the parameters
config.USE_SIDE_REFINE = bool(args.use_side_refine)
if args.weight_path is not None:
config.WEIGHT_PATH = args.weight_path
config.IMAGES_PER_GPU = 1
config.IMAGE_SHAPE = (1024, 1024, 3)
# 加载图片 load images
image, image_meta, _, _ = image_utils.load_image_gt(np.random.randint(10),
args.image_path,
config.IMAGE_SHAPE[0],
None)
# 加载模型 load the model
m = models.ctpn_net(config, 'test')
m.load_weights(config.WEIGHT_PATH, by_name=True)
# m.summary()
# 模型预测 prediction
text_boxes, text_scores, _ = m.predict([np.array([image]), np.array([image_meta])])
text_boxes = np_utils.remove_pad(text_boxes[0])
text_scores = np_utils.remove_pad(text_scores[0])[:, 0]
# 文本行检测器 text detector
image_meta = image_utils.parse_image_meta(image_meta)
detector = TextDetector(config)
text_lines = detector.detect(text_boxes, text_scores, config.IMAGE_SHAPE, image_meta['window'])
# 可视化保存图像 saving the images
boxes_num = 30
fig = plt.figure(figsize=(16, 16))
ax = fig.add_subplot(1, 1, 1)
visualize.display_polygons(image, text_lines[:boxes_num, :8], text_lines[:boxes_num, 8],
ax=ax)
image_name = os.path.basename(args.image_path)
fig.savefig('{}.{}.jpg'.format(os.path.splitext(image_name)[0], int(config.USE_SIDE_REFINE)))
def main(args):
# 覆盖参数
config.USE_SIDE_REFINE = bool(args.use_side_refine)
if args.weight_path is None:
args.weight_path = config.WEIGHT_PATH
config.IMAGES_PER_GPU = 1
config.IMAGE_SHAPE = (720, 720, 3)
config.set_root(args.root)
try:
os.makedirs(args.output_dir)
except:
pass
# 图像路径
image_path_list = file_utils.get_sub_files(args.root)
# 加载模型
m = models.ctpn_net(config, 'test')
m.load_weights(args.weight_path, by_name=True)
# 预测
start_time = datetime.datetime.now()
gen = generator(image_path_list, config.IMAGE_SHAPE)
text_boxes, text_scores, image_metas = m.predict_generator(
generator=gen, steps=len(image_path_list), use_multiprocessing=True)
end_time = datetime.datetime.now()
print("======完成{}张图像评估，耗时:{} 秒".format(len(image_path_list),
end_time - start_time))
# 去除padding
text_boxes = [np_utils.remove_pad(text_box) for text_box in text_boxes]
text_scores = [
np_utils.remove_pad(text_score)[:, 0] for text_score in text_scores
]
image_metas = image_utils.batch_parse_image_meta(image_metas)
# 文本行检测
detector = TextDetector(config)
text_lines = [
detector.detect(boxes, scores, config.IMAGE_SHAPE,
window) for boxes, scores, window in zip(
text_boxes, text_scores, image_metas["window"])
]
# 还原检测文本行边框到原始图像坐标
text_lines = [
image_utils.recover_detect_quad(boxes, window, scale)
for boxes, window, scale in zip(text_lines, image_metas["window"],
image_metas["scale"])
]
# 写入文档中
for image_path, boxes in zip(image_path_list, text_lines):
output_filename = os.path.splitext(
'res_' + os.path.basename(image_path))[0] + '.txt'
with open(os.path.join(args.output_dir, output_filename),
mode='w') as f:
for box in boxes.astype(np.int32):
f.write("{},{},{},{},{},{},{},{}\r\n".format(
box[0], box[1], box[2], box[3], box[4], box[5], box[6],
box[7]))
def main(args):
# 覆盖参数 rewrite the parameters
config.USE_SIDE_REFINE = bool(args.use_side_refine)
if args.weight_path is not None:
config.WEIGHT_PATH = args.weight_path
config.IMAGES_PER_GPU = 1
config.IMAGE_SHAPE = (1024, 1024, 3)
# 图像路径 path of the images
image_path_list = file_utils.get_sub_files(args.image_dir)
# 加载模型 load the model
m = models.ctpn_net(config, 'test')
m.load_weights(config.WEIGHT_PATH, by_name=True)
# 预测 predicting
start_time = datetime.datetime.now()
gen = generator(image_path_list, config.IMAGE_SHAPE)
text_boxes, text_scores, image_metas = m.predict_generator(
generator=gen, steps=len(image_path_list), use_multiprocessing=True)
end_time = datetime.datetime.now()
print("====== Image No.{}:Evaluation completed，time:{} second".format(
len(image_path_list), end_time - start_time))
# 去除padding removing the padding
text_boxes = [np_utils.remove_pad(text_box) for text_box in text_boxes]
text_scores = [
np_utils.remove_pad(text_score)[:, 0] for text_score in text_scores
]
image_metas = image_utils.batch_parse_image_meta(image_metas)
# 文本行检测 text Dector
detector = TextDetector(config)
text_lines = [
detector.detect(boxes, scores, config.IMAGE_SHAPE,
window) for boxes, scores, window in zip(
text_boxes, text_scores, image_metas["window"])
]
# 还原检测文本行边框到原始图像坐标 restore the text boundary to the original image
text_lines = [
image_utils.recover_detect_quad(boxes, window, scale)
for boxes, window, scale in zip(text_lines, image_metas["window"],
image_metas["scale"])
]
# 写入文档中 writing into a txt file
for image_path, boxes in zip(image_path_list, text_lines):
output_filename = os.path.splitext(
'res_' + os.path.basename(image_path))[0] + '.txt'
with open(os.path.join(args.output_dir, output_filename),
mode='w') as f:
for box in boxes.astype(np.int32):
f.write("{},{},{},{},{},{},{},{}\r\n".format(
box[0], box[1], box[2], box[3], box[4], box[5], box[6],
box[7]))
def main(args):
set_gpu_growth()
# 加载标注
annotation_files = file_utils.get_sub_files(config.IMAGE_GT_DIR)
image_annotations = [
reader.load_annotation(file, config.IMAGE_DIR)
for file in annotation_files
]
# 过滤不存在的图像，ICDAR2017中部分图像找不到
image_annotations = [
ann for ann in image_annotations if os.path.exists(ann['image_path'])
]
# 加载模型
m = models.ctpn_net(config, 'train')
models.compile(m,
config,
loss_names=['ctpn_regress_loss', 'ctpn_class_loss'])
if args.init_epochs > 0:
m.load_weights(args.weight_path, by_name=True)
else:
m.load_weights(config.PRE_TRAINED_WEIGHT, by_name=True)
m.summary()
# 生成器
gen = generator(image_annotations, config.IMAGES_PER_GPU,
config.IMAGE_SHAPE, config.ANCHORS_WIDTH,
config.MAX_GT_INSTANCES)
# 训练
m.fit_generator(gen,
steps_per_epoch=len(image_annotations) //
config.IMAGES_PER_GPU,
epochs=args.epochs,
initial_epoch=args.init_epochs,
verbose=True,
callbacks=get_call_back(),
use_multiprocessing=True)
# 保存模型
m.save(config.WEIGHT_PATH)
if __name__ == '__main__':
parse = argparse.ArgumentParser()
parse.add_argument("--epochs", type=int, default=50, help="epochs")
parse.add_argument("--init_epochs", type=int, default=0, help="epochs")
parse.add_argument("--weight_path",
type=str,
default=None,
help="weight path")
argments = parse.parse_args(sys.argv[1:])
main(argments)
def main(args):
set_gpu_growth()
# 加载标注 load the annotations
annotation_files = file_utils.get_sub_files(config.IMAGE_GT_DIR)
image_annotations = [
reader.load_annotation(file, config.IMAGE_DIR)
for file in annotation_files
]
# 过滤不存在的图像，ICDAR2017中部分图像找不到 remove the missing images
image_annotations = [
ann for ann in image_annotations if os.path.exists(ann['image_path'])
]
# 加载模型 load the model
m = models.ctpn_net(config, 'train')
models.compile(m,
config,
loss_names=[
'ctpn_regress_loss', 'ctpn_class_loss',
'side_regress_loss'
])
# 增加度量 increasing the metrics
output = models.get_layer(m, 'ctpn_target').output
models.add_metrics(
m, ['gt_num', 'pos_num', 'neg_num', 'gt_min_iou', 'gt_avg_iou'],
output[-5:])
if args.init_epochs > 0:
m.load_weights(args.weight_path, by_name=True)
else:
m.load_weights(config.PRE_TRAINED_WEIGHT, by_name=True)
m.summary()
# 生成器 generator
gen = generator(image_annotations, config.IMAGES_PER_GPU,
config.IMAGE_SHAPE, config.ANCHORS_WIDTH,
config.MAX_GT_INSTANCES)
# 训练 training
m.fit_generator(gen,
steps_per_epoch=len(image_annotations) //
config.IMAGES_PER_GPU * 2,
epochs=args.epochs,
initial_epoch=args.init_epochs,
verbose=True,
callbacks=get_call_back(),
workers=2,
use_multiprocessing=True)
# 保存模型 model saving
m.save(config.WEIGHT_PATH)
import random as rng
import matplotlib.pyplot as plt
from rect_op import merge_bounding_boxes
from tilt_align import get_lines, get_rotation_angle, ctpn_coordinate_pair, rotate_image
matplotlib.use('Agg')
from matplotlib import pyplot as plt
from ctpn.utils import image_utils, np_utils, visualize
from ctpn.utils.detector import TextDetector
from ctpn.config import cur_config as config
from ctpn.layers import models
config.USE_SIDE_REFINE = True
config.IMAGES_PER_GPU = 1
config.IMAGE_SHAPE = (1024, 1024, 3)
m = models.ctpn_net(config, 'test')
m.load_weights(config.WEIGHT_PATH, by_name=True)
m.summary()
def get_text_lines(name: str, dir=r'D:\citizenIdData\Train_DataSet'):
# 加载图片
image, image_meta, _, _ = image_utils.load_image_gt(
np.random.randint(10), dir + '\\' + name, config.IMAGE_SHAPE[0], None)
# 加载模型
# 模型预测
text_boxes, text_scores, _ = m.predict(
[np.array([image]), np.array([image_meta])])
text_boxes = np_utils.remove_pad(text_boxes[0])
def main(args):
set_gpu_growth()
# 加载标注
annotation_files = file_utils.get_sub_files(config.IMAGE_GT_DIR)
# annotation_files_1 = [file for file in annotation_files if 'rctw' in file]
annotation_files = [file for file in annotation_files if 'rects' in file]
# annotation_files = annotation_files_1 + annotation_files_2
image_annotations = [
reader.load_annotation(file, config.IMAGE_DIR)
for file in annotation_files
]
# 过滤不存在的图像，ICDAR2017中部分图像找不到
image_annotations = [
ann for ann in image_annotations if os.path.exists(ann['image_path'])
]
# 加载模型
m = models.ctpn_net(config, 'train')
models.compile(m,
config,
loss_names=[
'ctpn_regress_loss', 'ctpn_class_loss',
'side_regress_loss'
])
# 增加度量
output = models.get_layer(m, 'ctpn_target').output
models.add_metrics(
m, ['gt_num', 'pos_num', 'neg_num', 'gt_min_iou', 'gt_avg_iou'],
output[-5:])
if args.init_epochs > 0:
m.load_weights(args.weight_path, by_name=True)
else:
m.load_weights(config.PRE_TRAINED_WEIGHT, by_name=True)
m.summary()
# 生成器
gen = generator(image_annotations[:-100],
config.IMAGES_PER_GPU,
config.IMAGE_SHAPE,
config.ANCHORS_WIDTH,
config.MAX_GT_INSTANCES,
horizontal_flip=False,
random_crop=False)
val_gen = generator(image_annotations[-100:], config.IMAGES_PER_GPU,
config.IMAGE_SHAPE, config.ANCHORS_WIDTH,
config.MAX_GT_INSTANCES)
# 训练
m.fit_generator(gen,
steps_per_epoch=len(image_annotations) //
config.IMAGES_PER_GPU * 2,
epochs=args.epochs,
initial_epoch=args.init_epochs,
validation_data=val_gen,
validation_steps=100 // config.IMAGES_PER_GPU,
verbose=True,
callbacks=get_call_back(),
workers=2,
use_multiprocessing=True)
# 保存模型
m.save(config.WEIGHT_PATH)
def main(args):
set_gpu_growth()
config.set_root(args.root)
image_annotations = load_folder_annotation(args.root)
if len(image_annotations) < 5:
print("Too small dataset...")
return
# gen = generator(image_annotations[:-100],
# config.IMAGES_PER_GPU,
# config.IMAGE_SHAPE,
# config.ANCHORS_WIDTH,
# config.MAX_GT_INSTANCES,
# horizontal_flip=False,
# random_crop=False)
# val_gen = generator(image_annotations[-100:],
# config.IMAGES_PER_GPU,
# config.IMAGE_SHAPE,
# config.ANCHORS_WIDTH,
# config.MAX_GT_INSTANCES)
# for bat in range(100):
# print(bat)
# val, _ = next(gen)
# for key in val.keys():
# print( val[key].shape, end="," )
# print()
# val, _ = next(val_gen)
# for key in val.keys():
# print( val[key].shape, end="," )
# print()
# print()
# exit(1)
# 加载模型
m = models.ctpn_net(config, 'train')
models.compile(m,
config,
loss_names=[
'ctpn_regress_loss', 'ctpn_class_loss',
'side_regress_loss'
])
# 增加度量
output = models.get_layer(m, 'ctpn_target').output
models.add_metrics(
m, ['gt_num', 'pos_num', 'neg_num', 'gt_min_iou', 'gt_avg_iou'],
output[-5:])
# 从0开始的话，用resnet50
if args.weight_path is None:
args.weight_path = config.WEIGHT_PATH
# get current epoch from file name.
if args.init_epochs == 0:
res = re.match(r".*ctpn\.(\d+)\.h5", args.weight_path)
if res is not None:
args.init_epochs = int(res.group(1))
m.load_weights(args.weight_path, by_name=True)
m.summary()
# print( len( image_annotations[:-100]), len(image_annotations[-100:]) )
# 生成器
# 前面100条作为训练集，后面100条做成测试集。
gen = generator(image_annotations[:-10],
config.IMAGES_PER_GPU,
config.IMAGE_SHAPE,
config.ANCHORS_WIDTH,
config.MAX_GT_INSTANCES,
horizontal_flip=False,
random_crop=False)
val_gen = generator(image_annotations[-10:], config.IMAGES_PER_GPU,
config.IMAGE_SHAPE, config.ANCHORS_WIDTH,
config.MAX_GT_INSTANCES)
# 训练
m.fit_generator(gen,
steps_per_epoch=len(image_annotations) //
config.IMAGES_PER_GPU * 2,
epochs=args.epochs,
initial_epoch=args.init_epochs,
validation_data=val_gen,
validation_steps=100 // config.IMAGES_PER_GPU,
verbose=True,
callbacks=get_call_back(),
workers=args.jobs,
use_multiprocessing=True)
#
# # 保存模型
path = os.path.split(config.WEIGHT_PATH)
m.save(os.sep.join([path[0], "ctpn.%03d.h5" % (args.epochs)]))
