def infer(img_path, mode='infer'):
# imgList = load_img_path('/home/yang/Downloads/FILE/ml/imgs/image_contest_level_1_validate/')
imgList = helper.load_img_path(img_path)
print(imgList[:5])
model = cnn_lstm_otc_ocr.LSTMOCR(mode)
model.build_graph()
total_steps = len(imgList) / FLAGS.batch_size
os.environ["CUDA_VISIBLE_DEVICES"] = '2'
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver(tf.global_variables(), max_to_keep=100)
ckpt = tf.train.latest_checkpoint(FLAGS.checkpoint_dir)
if ckpt:
saver.restore(sess, ckpt)
print('restore from ckpt{}'.format(ckpt))
else:
print('cannot restore')
decoded_expression = []
for curr_step in range(int(total_steps)):
imgs_input = []
seq_len_input = []
for img in imgList[curr_step * FLAGS.batch_size:(curr_step + 1) *
FLAGS.batch_size]:
im = cv2.imread(img, cv2.IMREAD_COLOR).astype(
np.float32) / 255.
im = np.reshape(im, [
FLAGS.image_height, FLAGS.image_width, FLAGS.image_channel
])
def get_input_lens(seqs):
length = np.array([FLAGS.max_stepsize for _ in seqs],
dtype=np.int64)
return seqs, length
inp, seq_len = get_input_lens(np.array([im]))
imgs_input.append(im)
seq_len_input.append(seq_len)
imgs_input = np.asarray(imgs_input)
seq_len_input = np.asarray(seq_len_input)
seq_len_input = np.reshape(seq_len_input, [-1])
feed = {model.inputs: imgs_input}
dense_decoded_code = sess.run(model.dense_decoded, feed)
for item in dense_decoded_code:
expression = ''
for i in item:
if i == -1:
expression += ''
else:
expression += utils.decode_maps[i]
decoded_expression.append(expression)
with open('./result.txt', 'a') as f:
for code in decoded_expression:
print(code)
f.write(code + '\n')
def infer(img_path, mode='infer'):
# imgList = load_img_path('/home/yang/Downloads/FILE/ml/imgs/image_contest_level_1_validate/')
imgList = helper.load_img_path(img_path)
# actual = []
# for name in imgList:
# # code = name.split('/')[-1].split('_')[1].split('.')[0]
# code = '-'.join(name.split('/')[-1].split('-')[:-1])
# actual.append(code)
# actual = np.asarray(actual)
# MAX = 120
# imgList = imgList[:MAX]
print(imgList[:5])
with open('./actual.txt', 'w') as f:
for name in imgList:
code = name.split('/')[-1].split('_')[1].split('.')[0]
# code = '-'.join(name.split('/')[-1].split('-')[:-1])
f.write(code + '\n')
# exit(1)
# im = cv2.imread(imgList[0], cv2.IMREAD_GRAYSCALE).astype(np.float32) / 255.
# cv2.imshow('image',im)
model = cnn_lstm_otc_ocr.LSTMOCR(mode)
model.build_graph()
total_steps = len(imgList) // FLAGS.batch_size
config = tf.ConfigProto(allow_soft_placement=True)
with tf.Session(config=config) as sess:
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver(tf.global_variables(), max_to_keep=100)
ckpt = tf.train.latest_checkpoint(FLAGS.checkpoint_dir)
if ckpt:
saver.restore(sess, ckpt)
print('restore from ckpt{}'.format(ckpt))
else:
print('cannot restore')
decoded_expression = []
for curr_step in range(total_steps):
imgs_input = []
seq_len_input = []
for img in imgList[curr_step * FLAGS.batch_size:(curr_step + 1) *
FLAGS.batch_size]:
# im = cv2.imread(img, 0).astype(np.float32) / 255.
im = cv2.imread(img, cv2.IMREAD_GRAYSCALE).astype(
np.float32) / 255.
im = cv2.resize(im, (FLAGS.image_width, FLAGS.image_height))
im = np.reshape(im, [
FLAGS.image_height, FLAGS.image_width, FLAGS.image_channel
])
def get_input_lens(seqs):
length = np.array([FLAGS.max_stepsize for _ in seqs],
dtype=np.int64)
return seqs, length
inp, seq_len = get_input_lens(np.array([im]))
imgs_input.append(im)
seq_len_input.append(seq_len)
imgs_input = np.asarray(imgs_input)
seq_len_input = np.asarray(seq_len_input)
seq_len_input = np.reshape(seq_len_input, [-1])
feed = {model.inputs: imgs_input}
dense_decoded_code = sess.run(model.dense_decoded, feed)
for item in dense_decoded_code:
expression = ''
for i in item:
if i == -1:
expression += ''
else:
expression += utils.decode_maps[i]
decoded_expression.append(expression)
with open('./result.txt', 'w') as f:
for code in decoded_expression:
f.write(code + '\n')
def infer(img_path, mode='infer'):
imgList = helper.load_img_path(img_path)
print(imgList[:5])
model = orcmodel.LSTMOCR(mode) # 生成模型类
model.build_graph() # 建立模型
total_steps = math.ceil(len(imgList) / FLAGS.batch_size) #获得最小批总批次
config = tf.ConfigProto(allow_soft_placement=True)
with tf.Session(config=config) as sess:
sess.run(tf.global_variables_initializer()) # 初始化
saver = tf.train.Saver(tf.global_variables(),
max_to_keep=100) # saver 获取变量
ckpt = tf.train.latest_checkpoint(FLAGS.checkpoint_dir)
if ckpt:
saver.restore(sess, ckpt) # 恢复变量
print('restore from ckpt{}'.format(ckpt))
else:
print('cannot restore')
decoded_expression = []
true_expression = []
for curr_step in range(total_steps):
imgs_input = []
seq_len_input = []
for img in imgList[curr_step * FLAGS.batch_size:(curr_step + 1) *
FLAGS.batch_size]:
# 准备预测数据
true_expression.append(
img.split('/')[-1].split('_')[-1].split('.')[0])
im = np.array(Image.open(img).convert("L")).astype(
np.float32) / 255.
im = np.reshape(im, [
FLAGS.image_height, FLAGS.image_width, FLAGS.image_channel
])
def get_input_lens(seqs):
length = np.array([FLAGS.max_stepsize for _ in seqs],
dtype=np.int64)
return seqs, length
inp, seq_len = get_input_lens(np.array([im]))
imgs_input.append(im)
seq_len_input.append(seq_len)
imgs_input = np.asarray(imgs_input)
seq_len_input = np.asarray(seq_len_input)
seq_len_input = np.reshape(seq_len_input, [-1])
feed = {model.inputs: imgs_input, model.seq_len: seq_len_input}
# 运行预测，获得解码结果
dense_decoded = sess.run(model.dense_decoded, feed)
# 解析对应的验证码
for item in dense_decoded:
expression = ''
for i in item:
if i == -1:
expression += ''
else:
expression += utils.decode_maps[i]
decoded_expression.append(expression)
# 记录预测结果
with open('./result.txt', 'w') as f:
f.write("%-6s %-6s %-6s" % ("pred", "true", "is_right") + '\n')
for code, true_code in zip(decoded_expression, true_expression):
f.write("%-6s %-6s %-d" %
(code, true_code, code == true_code) + '\n')
def infer(img_path, mode='infer'):
# imgList = load_img_path('/home/yang/Downloads/FILE/ml/imgs/image_contest_level_1_validate/')
imgList = helper.load_img_path(img_path)
print(imgList[:5])
model = cnn_lstm_otc_ocr.LSTMOCR(mode)
model.build_graph()
total_steps = len(imgList) / FLAGS.batch_size
config = tf.ConfigProto(allow_soft_placement=True)
with tf.Session(config=config) as sess:
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver(tf.global_variables(), max_to_keep=100)
ckpt = tf.train.latest_checkpoint(FLAGS.checkpoint_dir)
if ckpt:
saver.restore(sess, ckpt)
print('restore from ckpt{}'.format(ckpt))
else:
print('cannot restore')
decoded_expression = []
for curr_step in range(total_steps):
imgs_input = []
seq_len_input = []
for img in imgList[curr_step * FLAGS.batch_size: (curr_step + 1) * FLAGS.batch_size]:
im = cv2.imread(img, 0).astype(np.float32) / 255.
im = np.reshape(im, [FLAGS.image_height, FLAGS.image_width, FLAGS.image_channel])
def get_input_lens(seqs):
length = np.array([FLAGS.max_stepsize for _ in seqs], dtype=np.int64)
return seqs, length
inp, seq_len = get_input_lens(np.array([im]))
imgs_input.append(im)
seq_len_input.append(seq_len)
imgs_input = np.asarray(imgs_input)
seq_len_input = np.asarray(seq_len_input)
seq_len_input = np.reshape(seq_len_input, [-1])
feed = {model.inputs: imgs_input}
dense_decoded_code = sess.run(model.dense_decoded, feed)
for item in dense_decoded_code:
expression = ''
for i in item:
if i == -1:
expression += ''
else:
expression += utils.decode_maps[i]
decoded_expression.append(expression)
with open('./result.txt', 'a') as f:
for code in decoded_expression:
f.write(code + '\n')
import cv2
import numpy as np
import tensorflow as tf
import cnn_lstm_otc_ocr
import utils
import helper
os.environ["CUDA_VISIBLE_DEVICES"] = '2'
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
FLAGS = utils.FLAGS
imgs_input = []
# 图片所在路径
imgList = helper.load_img_path('./infer/')
FLAGS.batch_size = len(imgList)
print(imgList[:5])
for img in imgList:
im = cv2.imread(img, cv2.IMREAD_COLOR).astype(np.float32) / 255.
im = np.reshape(
im, [FLAGS.image_height, FLAGS.image_width, FLAGS.image_channel])
imgs_input.append(im)
imgs_input = np.asarray(imgs_input)
model = cnn_lstm_otc_ocr.LSTMOCR('infer')
model.build_graph()
# 定义节点
logit = model.get_logist()
def infer(img_path, mode='infer'):
# imgList = load_img_path('/home/yang/Downloads/FILE/ml/imgs/image_contest_level_1_validate/')
imgList = helper.load_img_path(img_path)
actual = []
# for name in imgList:
# # code = name.split('/')[-1].split('_')[1].split('.')[0]
# code = '-'.join(name.split('/')[-1].split('-')[:-1])
# actual.append(code)
# actual = np.asarray(actual)
# MAX = 120
# imgList = imgList[:MAX]
print(imgList[:5])
with open('./actual.txt', 'w') as f:
for name in imgList:
code = name.split('/')[-1].split('-')[:-1]
# code = name.split('/')[-1].split('_')[-1].split('.')[0]
## convert year field from 2019 -> 19
# code = code.split('-')
# code[2] = code[2][2:]
code = '-'.join(code)
actual.append(code)
f.write(code + '\n')
actual = np.asarray(actual)
# exit(1)
# im = cv2.imread(imgList[0], cv2.IMREAD_GRAYSCALE).astype(np.float32) / 255.
# cv2.imshow('image',im)
model = cnn_lstm_otc_ocr.LSTMOCR(mode)
model.build_graph()
total_steps = len(imgList) // FLAGS.batch_size
config = tf.ConfigProto(allow_soft_placement=True)
with tf.Session(config=config) as sess:
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver(tf.global_variables(), max_to_keep=100)
ckpt = tf.train.latest_checkpoint(FLAGS.checkpoint_dir)
# print(ckpt)
if ckpt:
saver.restore(sess, ckpt)
print('restore from ckpt{}'.format(ckpt))
else:
print('cannot restore')
decoded_expression = []
for curr_step in range(total_steps):
imgs_input = []
seq_len_input = []
for img in imgList[curr_step * FLAGS.batch_size: (curr_step + 1) * FLAGS.batch_size]:
# im = cv2.imread(img, 0).astype(np.float32) / 255.
im = cv2.imread(img, cv2.IMREAD_GRAYSCALE).astype(np.float32) / 255.
im = cv2.resize(im, (FLAGS.image_width, FLAGS.image_height))
# im = im[10:45,8:160]
# im = cv2.resize(im, (FLAGS.image_width, FLAGS.image_height))
im = np.reshape(im, [FLAGS.image_height, FLAGS.image_width, FLAGS.image_channel])
# cv2.imshow('image',im)
# cv2.waitKey(0)
def get_input_lens(seqs):
length = np.array([FLAGS.max_stepsize for _ in seqs], dtype=np.int64)
return seqs, length
inp, seq_len = get_input_lens(np.array([im]))
imgs_input.append(im)
seq_len_input.append(seq_len)
imgs_input = np.asarray(imgs_input)
seq_len_input = np.asarray(seq_len_input)
seq_len_input = np.reshape(seq_len_input, [-1])
feed = {model.inputs: imgs_input}
dense_decoded_code = sess.run(model.dense_decoded, feed)
for item in dense_decoded_code:
expression = ''
for i in item:
if i == -1:
expression += ''
else:
expression += utils.decode_maps[i]
decoded_expression.append(expression)
# visualize the layers
# conv_out = sess.run(model.conv_out,feed)
# img_name = imgList[curr_step].split('/')[-1].split('.')[0]
# # layer0 = conv_out[0]
# for i in range(len(conv_out)):
# layer = conv_out[i]
# print(layer.shape)
# plotNNFilter(layer)
# plt.show()
# plt.savefig("./imgs/filters/conv-{}_{}".format(i+1,img_name))
# print(decoded_expression)
# layer0 = model.conv_out[0]
# print(layer0.shape)
# print(layer0)
# print(type(layer0.eval()))
# plotNNFilter(layer0)
## visualize the layers
# test image
# SIZE = 167,55
# imageToUse = imgList[0]
# im = cv2.imread(imageToUse, cv2.IMREAD_GRAYSCALE).astype(np.float32) / 255.
# im = cv2.resize(im, SIZE)
# im = im[8:48,5:155]
# im = cv2.resize(im, SIZE)
# im = np.reshape(im, [SIZE[1],SIZE[0],1])
# cv2.imshow('image',im)
# cv2.waitKey(0)
# op = sess.graph.get_operations()
# for i in op:
# print(i.name)
# exit(1)
# print layers
# plt.imshow(np.reshape(imageToUse,[28,28]), interpolation="nearest", cmap="gray")
with open('./result.txt', 'w') as f:
for code in decoded_expression:
f.write(code + '\n')
# print(code)
# exit()
decoded_expression = np.asarray(decoded_expression)
imgList = np.asarray(imgList)
# print 6 corect and 6 incorrect predictions
c = decoded_expression == actual
w = decoded_expression != actual
correct = imgList[c]
wrong = imgList[w]
print("correct predictions:")
print(correct[:6])
print("********")
print("wrong predictions:")
print(wrong[:6])
print("********")
for i in range(6):
print("prediction = {}".format(decoded_expression[w][i]))
print("actual = {}".format(actual[w][i]))
print("********")
acc = float(c.sum()) / (c.sum()+w.sum())
print("accuracy = {}".format(acc))
def infer(img_path, mode='infer'):
# imgList = load_img_path('/home/yang/Downloads/FILE/ml/imgs/image_contest_level_1_validate/')
imgList = helper.load_img_path(img_path)
print(imgList[:5])
model = cnn_lstm_otc_ocr.LSTMOCR(mode)
model.build_graph()
total_steps = len(imgList) / FLAGS.batch_size
config = tf.ConfigProto(allow_soft_placement=True)
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver(tf.global_variables(), max_to_keep=100)
ckpt = tf.train.latest_checkpoint(FLAGS.checkpoint_dir)
if ckpt:
saver.restore(sess, ckpt)
print('restore from ckpt{}'.format(ckpt))
else:
print('cannot restore')
decoded_expression = []
for curr_step in range(int(total_steps)):
imgs_input = []
seq_len_input = []
for img in imgList[curr_step * FLAGS.batch_size:(curr_step + 1) *
FLAGS.batch_size]:
im = cv2.imread(img, 0).astype(np.float32) / 255.
im = np.reshape(im, [
FLAGS.image_height, FLAGS.image_width, FLAGS.image_channel
])
def get_input_lens(seqs):
length = np.array([FLAGS.out_channels for _ in seqs],
dtype=np.int64)
return seqs, length
inp, seq_len = get_input_lens(np.array([im]))
imgs_input.append(im)
seq_len_input.append(seq_len)
imgs_input = np.asarray(imgs_input)
seq_len_input = np.asarray(seq_len_input)
seq_len_input = np.reshape(seq_len_input, [-1])
feed = {model.inputs: imgs_input}
dense_decoded_code = sess.run(model.dense_decoded, feed)
for item in dense_decoded_code:
expression = ''
for i in item:
if i == -1:
expression += ''
else:
expression += utils.decode_maps[i]
decoded_expression.append(expression)
print(decoded_expression)
with open('./result.txt', 'w') as f:
true_count = 0
for ind, code in enumerate(decoded_expression[0:len(imgList)]):
img_name = imgList[ind]
img_label = img_name.split('_')[-1].replace('.jpg', '')
if code == img_label:
true_count = true_count + 1
f.write('{} {} {}\n'.format(img_name, img_label, code))
print('{}/{} = {}'.format(true_count, len(imgList),
float(true_count) / len(imgList)))
def infer(root, mode='infer'):
model = cnn_lstm_otc_ocr.LSTMOCR(mode)
model.build_graph()
config = tf.ConfigProto(allow_soft_placement=True)
with tf.Session(config=config) as sess:
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver(tf.global_variables(), max_to_keep=100)
ckpt = tf.train.latest_checkpoint(FLAGS.checkpoint_dir)
if ckpt:
saver.restore(sess, ckpt)
print('restore from ckpt{}'.format(ckpt))
else:
print('cannot restore')
for img_file in os.listdir(root):
start_time = time.time()
img_path = os.path.join(root, img_file)
print(img_path)
# imgList = load_img_path('/home/yang/Downloads/FILE/ml/imgs/image_contest_level_1_validate/')
file_name = img_path.split('/')[-1].split('_')[0]
imgList = helper.load_img_path(img_path)
#print(imgList[:5])
total_steps = len(imgList) / FLAGS.batch_size
sample_num = len(imgList) * 3
total_acc = 0
for curr_step in xrange(total_steps):
decoded_expression = []
imgs_input = []
seq_len_input = []
imgs_label = []
for img in imgList[curr_step *
FLAGS.batch_size:(curr_step + 1) *
FLAGS.batch_size]:
label = img.split('_')[-1].split('.')[0]
imgs_label.append(label.upper())
#print (img)
im = cv2.imread(img, cv2.IMREAD_GRAYSCALE).astype(
np.float32) / 255.
im = cv2.resize(im,
(FLAGS.image_width, FLAGS.image_height))
im = np.reshape(im, [
FLAGS.image_height, FLAGS.image_width,
FLAGS.image_channel
])
def get_input_lens(seqs):
length = np.array([FLAGS.max_stepsize for _ in seqs],
dtype=np.int64)
return seqs, length
inp, seq_len = get_input_lens(np.array([im]))
imgs_input.append(im)
seq_len_input.append(seq_len)
imgs_input = np.asarray(imgs_input)
seq_len_input = np.asarray(seq_len_input)
seq_len_input = np.reshape(seq_len_input, [-1])
feed = {model.inputs: imgs_input, model.seq_len: seq_len_input}
dense_decoded_code = sess.run(model.dense_decoded, feed)
for item in dense_decoded_code:
expression = ''
for i in item:
if i == -1:
expression += ''
else:
expression += utils.decode_maps[i]
decoded_expression.append(expression)
acc = utils.test_accuracy_calculation(imgs_label,
decoded_expression, True)
total_acc += acc
print(total_acc / total_steps)
print(file_name)
print(sample_num)
with open('./result.txt', 'a') as f:
f.write(file_name + ',' +
str(round(total_acc / total_steps, 2)) + ',' +
str(sample_num) + ',' +
str(round((time.time() - start_time) /
sample_num, 2)) + '\n')