def model(img, adjust=False):
"""
@img: 图片
@adjust: 是否调整文字识别结果
"""
cfg_from_file('./ctpn/ctpn/text.yml')
text_recs, img_framed, img = text_detect(img)
text_recs = sort_box(text_recs)
result = charRec(img, text_recs, adjust)
return result, img_framed
def init_session():
global sess, input_img, output_cls_prob, output_box_pred, text_detector
cfg_from_file('ctpn/text.yml')
# init session
config = tf.ConfigProto(allow_soft_placement=True)
sess = tf.Session(config=config)
with gfile.FastGFile('data/ctpn.pb', 'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
sess.graph.as_default()
tf.import_graph_def(graph_def, name='')
sess.run(tf.global_variables_initializer())
input_img = sess.graph.get_tensor_by_name('Placeholder:0')
output_cls_prob = sess.graph.get_tensor_by_name('Reshape_2:0')
output_box_pred = sess.graph.get_tensor_by_name('rpn_bbox_pred/Reshape_1:0')
text_detector = TextDetector()
textdetector = TextDetector()
boxes = textdetector.detect(boxes, scores[:, np.newaxis], img.shape[:2])
draw_boxes(img, image_name, boxes, scale)
timer.toc()
print(('Detection took {:.3f}s for '
'{:d} object proposals').format(timer.total_time, boxes.shape[0]))
if __name__ == '__main__':
if os.path.exists("data/results/"):
shutil.rmtree("data/results/")
os.makedirs("data/results/")
cfg_from_file('ctpn/text.yml')
# init session
config = tf.ConfigProto(allow_soft_placement=True)
sess = tf.Session(config=config)
# load network
net = get_network("VGGnet_test")
# load model
print(('Loading network {:s}... '.format("VGGnet_test")), end=' ')
saver = tf.train.Saver()
try:
ckpt = tf.train.get_checkpoint_state(cfg.TEST.checkpoints_path)
print('Restoring from {}...'.format(ckpt.model_checkpoint_path), end=' ')
saver.restore(sess, ckpt.model_checkpoint_path)
print('done')
output1 =''.join(output1)
output1 =' '.join([output1[i:i+4] for i in range(0, len(output1), 4)])
output2 =''.join(output2)
output2 =' '.join([output2[i:i+4] for i in range(0, len(output2), 4)])
print ("METHOD 1")
print ("############")
print("card number 1:",output1)
print("card number 2:",output2)
# Method 2 : Other info
cfg_from_file('ctpn/text.yml')
print ("METHOD 2")
print ("############")
# init session
config = tf.ConfigProto(allow_soft_placement=True)
sess = tf.Session(config=config)
# load network
net = get_network("VGGnet_test")
# load model
print(('Loading network {:s}... '.format("VGGnet_test")), end=' ')
saver = tf.train.Saver()
detect_graph = tf.get_default_graph()
if len(sys.argv) == 1:
parser.print_help()
# sys.exit(1)
args = parser.parse_args()
return args
if __name__ == '__main__':
args = parse_args()
print('Called with args:')
print(args)
if args.cfg_file is not None:
cfg_from_file(args.cfg_file)
if args.set_cfgs is not None:
cfg_from_list(args.set_cfgs)
print('Using config:')
pprint.pprint(cfg)
if not args.randomize:
# fix the random seeds (numpy and caffe) for reproducibility
np.random.seed(cfg.RNG_SEED)
imdb = get_imdb(
args.imdb_name) #-----------------------------------------------------
print 'Loaded dataset `{:s}` for training'.format(imdb.name)
roidb = get_training_roidb(imdb)
output_dir = get_output_dir(imdb, None)
import os
# sys.path.append(os.getcwd())
# this_dir = os.path.dirname(__file__)
parentdir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
sys.path.append(parentdir)
from lib.fast_rcnn.train import get_training_roidb, train_net
from lib.fast_rcnn.config import cfg_from_file, get_output_dir, get_log_dir
from lib.datasets.factory import get_imdb
from lib.networks.factory import get_network
from lib.fast_rcnn.config import cfg
if __name__ == '__main__':
# 将text.yml的配置与默认config中的默认配置进行合并
cfg_from_file('text.yml')
print('Using config:~~~~~~~~~~~~~~~~')
# 根据给定的名字，得到要加载的数据集
imdb = get_imdb('voc_2007_trainval')
print('Loaded dataset `{:s}` for training'.format(imdb.name))
# 准备训练数据
roidb = get_training_roidb(imdb)
# 模型输出的路径
output_dir = get_output_dir(imdb, None)
# summary的输出路径
log_dir = get_log_dir(imdb)
print('Output will be saved to `{:s}`'.format(output_dir))
print('Logs will be saved to `{:s}`'.format(log_dir))
device_name = '/gpu:0'
print(device_name)
def train(rpn_data,
roi_data,
rpn_cls_score_reshape,
rpn_bbox_pred,
feature_map,
cls_score,
bbox_pred,
input_image_tensor,
input_gt_box_tensor,
input_im_info_tensor,
pretrain_model=None):
output_dir = '/home/give/PycharmProjects/MyFasterRCNN/parameters'
saver = tf.train.Saver(max_to_keep=5)
# RPN
# classification loss(fg bg)
rpn_cls_score = tf.reshape(rpn_cls_score_reshape, [-1, 2])
rpn_label = tf.reshape(rpn_data[0], [-1])
rpn_cls_score = tf.reshape(
tf.gather(rpn_cls_score, tf.where(tf.not_equal(rpn_label, -1))),
[-1, 2])
rpn_label = tf.reshape(
tf.gather(rpn_label, tf.where(tf.not_equal(rpn_label, -1))), [-1])
rpn_cross_entropy = tf.reduce_mean(
tf.nn.sparse_softmax_cross_entropy_with_logits(logits=rpn_cls_score,
labels=rpn_label))
# bounding box regression L1 loss
rpn_bbox_pred = rpn_bbox_pred
rpn_bbox_targets = tf.transpose(rpn_data[1], [0, 2, 3, 1])
rpn_bbox_inside_weights = tf.transpose(rpn_data[2], [0, 2, 3, 1])
rpn_bbox_outside_weights = tf.transpose(rpn_data[3], [0, 2, 3, 1])
rpn_smooth_l1 = _modified_smooth_l1(3.0, rpn_bbox_pred, rpn_bbox_targets,
rpn_bbox_inside_weights,
rpn_bbox_outside_weights)
rpn_loss_box = tf.reduce_mean(
tf.reduce_sum(rpn_smooth_l1, reduction_indices=[1, 2, 3]))
# classification loss
label = tf.reshape(roi_data[1], [-1])
cross_entropy = tf.reduce_mean(
tf.nn.sparse_softmax_cross_entropy_with_logits(logits=cls_score,
labels=label))
smooth_l1 = _modified_smooth_l1(1.0, bbox_pred, roi_data[2], roi_data[3],
roi_data[4])
loss_box = tf.reduce_mean(tf.reduce_sum(smooth_l1, reduction_indices=[1]))
loss = cross_entropy + loss_box + rpn_cross_entropy + rpn_loss_box
global_step = tf.Variable(0, trainable=False)
lr = tf.train.exponential_decay(cfg.TRAIN.LEARNING_RATE,
global_step,
cfg.TRAIN.STEPSIZE,
0.001,
staircase=True)
momentum = cfg.TRAIN.MOMENTUM
train_op = tf.train.MomentumOptimizer(lr, momentum).minimize(
loss, global_step=global_step)
with tf.Session() as sess:
args = parse_args()
from lib.datasets.factory import get_imdb
from lib.fast_rcnn.train import get_training_roidb, filter_roidb
from lib.fast_rcnn.train import get_data_layer
import lib.roi_data_layer.roidb as rdl_roidb
import numpy as np
from lib.fast_rcnn.config import cfg_from_file, cfg_from_list
if args.cfg_file is not None:
cfg_from_file(args.cfg_file)
if args.set_cfgs is not None:
cfg_from_list(args.set_cfgs)
imdb = get_imdb('voc_2007_trainval')
roidb = get_training_roidb(imdb)
roidb = filter_roidb(roidb)
bbox_means, bbox_stds = rdl_roidb.add_bbox_regression_targets(roidb)
data_layer = get_data_layer(roidb, imdb.num_classes)
init_op = tf.global_variables_initializer()
sess.run(init_op)
if pretrain_model is not None:
print('Loading pretrained model '
'weights from {:s}').format(pretrain_model)
load(pretrain_model, sess, saver, True)
for iter_index in range(args.max_iters):
blobs = data_layer.forward()
# blobs keys include: data, gt_boxesm im_info
_, rpn_bbox_targets_value, rpn_bbox_inside_weights_value, rpn_bbox_outside_weights_value = sess.run(
[
train_op, rpn_bbox_targets, rpn_bbox_inside_weights,
rpn_bbox_outside_weights
],
feed_dict={
input_image_tensor: blobs['data'],
input_gt_box_tensor: blobs['gt_boxes'],
input_im_info_tensor: blobs['im_info']
})
rpn_label_value, loss_value, loss_box_value, cross_entropy_value, rpn_cross_entropy_value, rpn_loss_box_value = sess.run(
[
rpn_label, loss, loss_box, cross_entropy,
rpn_cross_entropy, rpn_loss_box
],
feed_dict={
input_image_tensor: blobs['data'],
input_gt_box_tensor: blobs['gt_boxes'],
input_im_info_tensor: blobs['im_info']
})
if iter_index % 100 == 0:
print 'iter: %d / %d' % (iter_index, args.max_iters)
print 'total loss: %.4f, rpn cross entropy: %.4f, rpn_loss_box: %.4f, cross entroopy: %.4f, loss box: %.4f' % (
loss_value, rpn_cross_entropy_value, rpn_loss_box_value,
cross_entropy_value, loss_box_value)
# print np.shape(rpn_label_value), rpn_label_value
if iter_index == 0:
continue
infix = ('_' + cfg.TRAIN.SNAPSHOT_INFIX
if cfg.TRAIN.SNAPSHOT_INFIX != '' else '')
filename = (cfg.TRAIN.SNAPSHOT_PREFIX + infix +
'_iter_{:d}'.format(iter_index + 1) + '.ckpt')
filename = os.path.join(output_dir, filename)
saver.save(sess, filename)
plt.switch_backend('agg')
from matplotlib.backends.backend_agg import FigureCanvasAgg as FigureCanvas
from matplotlib.figure import Figure
from CTPN.demo import ctpn
from lib.fast_rcnn.config import cfg,cfg_from_file
from lib.networks.factory import get_network
import glob
import shutil
from flask import Flask, redirect, request, url_for, send_file
from redis import Redis
redis = Redis(host="redis", db=0, socket_connect_timeout=2, socket_timeout=2)
app = Flask(__name__)
cfg_from_file('CTPN/ctpn/text.yml')
# init session
sess_CTPN = tf.Session(config=tf.ConfigProto(allow_soft_placement=True))
# load network
net = get_network("VGGnet_test")
# load model
print(('Loading network {:s}... '.format("VGGnet_test")), end=' ')
saver = tf.train.Saver()
try:
ckpt = tf.train.get_checkpoint_state(cfg.TEST.checkpoints_path)
print('Restoring from {}...'.format(ckpt.model_checkpoint_path), end=' ')
saver.restore(sess_CTPN, ckpt.model_checkpoint_path)
print('done')
except:
max_scale=TextLineCfg.MAX_SCALE)
scores, boxes = test_ctpn(sess, net, img)
textdetector = TextDetector()
boxes = textdetector.detect(boxes, scores[:, np.newaxis], img.shape[:2])
sort_index = np.argsort(boxes[:, -1])[::-1]
boxes = boxes[sort_index]
# print(boxes)
texts = draw_boxes(img, image_name, boxes, scale)
timer.toc()
print(('Detection took {:.3f}s for '
'{:d} object proposals').format(timer.total_time, boxes.shape[0]))
return texts
if __name__ == '__main__':
cfg_from_file('./text.yml')
config = tf.ConfigProto(allow_soft_placement=True)
sess = tf.Session(config=config)
net = get_network("VGGnet_test")
# load model
print(('Loading network {:s}... '.format("VGGnet_test")), end=' ')
saver = tf.train.Saver()
try:
ckpt = tf.train.get_checkpoint_state(cfg.TEST.checkpoints_path)
print('Restoring from {}...'.format(ckpt.model_checkpoint_path),
end=' ')
saver.restore(sess, ckpt.model_checkpoint_path)
print('done')
except:
raise 'Check your pretrained {:s}'.format(ckpt.model_checkpoint_path)
if len(sys.argv) == 1:
parser.print_help()
# sys.exit(1)
args = parser.parse_args()
return args
if __name__ == '__main__':
args = parse_args()
print('Called with args:')
print(args)
if args.cfg_file is not None:
cfg_from_file(args.cfg_file)
if args.set_cfgs is not None:
cfg_from_list(args.set_cfgs)
print('Using config:')
pprint.pprint(cfg)
if not args.randomize:
# fix the random seeds (numpy and caffe) for reproducibility
np.random.seed(cfg.RNG_SEED)
imdb = get_imdb(args.imdb_name)
print 'Loaded dataset `{:s}` for training'.format(imdb.name)
roidb = get_training_roidb(imdb)
output_dir = get_output_dir(imdb, None)
log_dir = get_log_dir(imdb)
def __init__(self):
# fast-rcnn 配置加载
cfg_from_file('./ctpn/ctpn/text.yml')
def export():
cfg_from_file(os.path.join(dir_path, 'text.yml'))
config = tf.ConfigProto(allow_soft_placement=True)
sess = tf.Session(config=config)
# with gfile.FastGFile('../data/ctpn.pb', 'rb') as f:
# graph_def = tf.GraphDef()
# graph_def.ParseFromString(f.read())
# sess.graph.as_default()
# tf.import_graph_def(graph_def, name='')
# sess.run(tf.global_variables_initializer())
net = get_network("VGGnet_test")
print(('Loading network {:s}... '.format("VGGnet_test")), end=' ')
saver = tf.train.Saver()
print(saver)
try:
ckpt_path = os.path.abspath(
os.path.join(dir_path, cfg.TEST.checkpoints_path))
print('check_path, ', ckpt_path)
ckpt = tf.train.get_checkpoint_state(ckpt_path)
print('Restoring from {}...'.format(ckpt.model_checkpoint_path),
end=' ')
saver.restore(sess, ckpt.model_checkpoint_path)
print('done')
except:
raise 'Check your pretrained {:s}'.format(ckpt.model_checkpoint_path)
print(' done.')
'''
input_img = sess.graph.get_tensor_by_name('Placeholder:0')
output_cls_prob = sess.graph.get_tensor_by_name('Reshape_2:0')
output_box_pred = sess.graph.get_tensor_by_name('rpn_bbox_pred/Reshape_1:0')
'''
raw_image = tf.placeholder(tf.float32,
shape=[None, None, None, 3
]) #\u8f93\u5165\u539f\u59cb\u56fe\u50cf
print('raw_image, ')
jpeg = preprocess_image(raw_image) #\u9884\u5904\u7406,\u7f29\u653e
#jpeg,im_info = preprocess_image(raw_image) #\u9884\u5904\u7406,\u7f29\u653e
# Preprocessing our input image
#cls_prob_info,box_pred_info = tf.import_graph_def\
output_tensor_cls_prob,output_tensor_box_pred = tf.import_graph_def\
(tf.get_default_graph().as_graph_def(),
input_map={'Placeholder:0': jpeg},
return_elements=['Reshape_2:0','rpn_bbox_pred/Reshape_1:0'])
builder = tf.saved_model.builder.SavedModelBuilder('./exportn/1')
imageplaceholder_info = tf.saved_model.utils.build_tensor_info(jpeg)
#imageplaceholder_info = tf.saved_model.utils.build_tensor_info(input_img)
#cls_prob_info = tf.saved_model.utils.build_tensor_info(output_cls_prob)
#box_pred_info = tf.saved_model.utils.build_tensor_info(output_box_pred)
print('predict_method_name,',
tf.saved_model.signature_constants.PREDICT_METHOD_NAME)
prediction_signature = (
tf.saved_model.signature_def_utils.build_signature_def(
inputs={'image': imageplaceholder_info},
outputs={
'output_cls_prob': output_tensor_cls_prob,
'output_box_pred': output_tensor_box_pred
#'output_cls_prob': cls_prob_info,
#'output_box_pred': box_pred_info
},
method_name=tf.saved_model.signature_constants.PREDICT_METHOD_NAME)
)
init_op = tf.group(tf.tables_initializer(), name='legacy_init_op')
builder.add_meta_graph_and_variables(
sess, [tf.saved_model.tag_constants.SERVING],
signature_def_map={'ctpn_recs_predict': prediction_signature},
legacy_init_op=init_op)
builder.save()
timer.toc()
print(('Detection took {:.3f}s for '
'{:d} object proposals').format(timer.total_time, boxes.shape[0]))
if __name__ == '__main__':
if os.path.exists("/content/drive/My Drive/GR2/ctpn/results/"):
shutil.rmtree("/content/drive/My Drive/GR2/ctpn/results/")
print("====== remove result folder =======")
os.makedirs("/content/drive/My Drive/GR2/ctpn/results/")
if os.path.exists("/content/drive/My Drive/GR2/ctpn/results_visualize/"):
shutil.rmtree("/content/drive/My Drive/GR2/ctpn/results_visualize/")
print("====== remove result folder results_visualize=======")
os.makedirs("/content/drive/My Drive/GR2/ctpn/results_visualize/")
cfg_from_file('/content/text-detection-ctpn/ctpn/text.yml')
# init session
config = tf.ConfigProto(allow_soft_placement=True)
sess = tf.Session(config=config)
# load network
net = get_network("VGGnet_test")
# load model
print(('Loading network {:s}... '.format("VGGnet_test")), end=' ')
saver = tf.train.Saver()
try:
print('==============')
print(cfg.TEST.checkpoints_path)
ckpt = tf.train.get_checkpoint_state(cfg.TEST.checkpoints_path)
print(ckpt)
scores, boxes = test_ctpn(sess, net, img)
textdetector = TextDetector()
boxes = textdetector.detect(boxes, scores[:, np.newaxis], img.shape[:2])
draw_boxes(img, image_name, boxes, scale)
timer.toc()
print(('Detection took {:.3f}s for '
'{:d} object proposals').format(timer.total_time, boxes.shape[0]))
if __name__ == '__main__':
if os.path.exists("data/results/"):
shutil.rmtree("data/results/")
os.makedirs("data/results/")
cfg_from_file('ctpn/text_demo.yml')
# init session
config = tf.ConfigProto(allow_soft_placement=True)
sess = tf.Session(config=config)
# load network
net = get_network("VGGnet_test")
# load model
print(('Loading network {:s}... '.format("VGGnet_test")), end=' ')
saver = tf.train.Saver()
try:
ckpt = tf.train.get_checkpoint_state(cfg.TEST.checkpoints_path)
print('Restoring from {}...'.format(ckpt.model_checkpoint_path),
end=' ')
saver.restore(sess, ckpt.model_checkpoint_path)
scores, boxes = test_ctpn(sess, net, img)
textdetector = TextDetector()
boxes = textdetector.detect(boxes, scores[:, np.newaxis], img.shape[:2])
draw_boxes(img, image_name, boxes, scale)
timer.toc()
print(('Detection took {:.3f}s for '
'{:d} object proposals').format(timer.total_time, boxes.shape[0]))
if __name__ == '__main__':
if os.path.exists("data/results/"):
shutil.rmtree("data/results/")
os.makedirs("data/results/")
cfg_from_file(os.path.join(cfg.ROOT_DIR, 'ctpn', 'text.yml'))
# init session
config = tf.ConfigProto(allow_soft_placement=True)
sess = tf.Session(config=config)
# load network
net = get_network("VGGnet_test")
# load model
print(('Loading network {:s}... '.format("VGGnet_test")), end=' ')
saver = tf.train.Saver()
c_path = os.path.join(cfg.ROOT_DIR, cfg.TEST.checkpoints_path)
try:
ckpt = tf.train.get_checkpoint_state(cfg.TEST.checkpoints_path)
print('Restoring from {}...'.format(ckpt.model_checkpoint_path),
end=' ')
import pprint
import os
import tensorflow as tf
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
from lib.fast_rcnn.train import SolverWrapper
from lib.fast_rcnn.config import cfg_from_file
from lib.networks.factory import get_network
from lib.fast_rcnn.config import cfg
import seetaas_helper as helper
if __name__ == '__main__':
yaml_cfg = helper.get_parameter(yaml_file="adl.yml")
cfg_from_file(yaml_cfg)
print('Using config:')
pprint.pprint(cfg)
device_name = '/gpu:0'
print(device_name)
train_graph = tf.Graph()
with train_graph.as_default():
network = get_network('VGGnet_train')
solver = SolverWrapper(train_graph,
network,
output_dir='/tmp/model',
dataset_path='/tmp/dataset',
dataset_name='root')
config = tf.ConfigProto(allow_soft_placement=True,
log_device_placement=False)
with tf.Session(config=config, graph=train_graph) as sess:
solver.train_model(sess)
