def validate(config):
if hasattr(config.eval, 'random_seed'):
np.random.seed(config.eval.random_seed)
tf.set_random_seed(config.eval.random_seed)
random.seed(config.eval.random_seed)
if hasattr(config.eval.execution, 'CUDA_VISIBLE_DEVICES'):
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ[
"CUDA_VISIBLE_DEVICES"] = config.train.execution.CUDA_VISIBLE_DEVICES
height, width, channels_num = config.input_shape
rnn_cells_num = config.rnn_cells_num
graph = tf.Graph()
with graph.as_default():
with slim.arg_scope([slim.batch_norm, slim.dropout],
is_training=False):
inp_data, label_val, file_names = data_input(
height,
width,
channels_num,
config.eval.file_list_path,
batch_size=config.eval.batch_size)
prob = inference(rnn_cells_num, inp_data, config.num_classes)
prob = tf.transpose(prob, (1, 0, 2)) # prepare for CTC
data_length = tf.fill(
[tf.shape(prob)[1]],
tf.shape(prob)[0]) # input seq length, batch size
result = tf.nn.ctc_greedy_decoder(prob,
data_length,
merge_repeated=True)
predictions = tf.to_int32(result[0][0])
d_predictions = tf.sparse_to_dense(predictions.indices, [
tf.shape(inp_data, out_type=tf.int64)[0], config.max_lp_length
],
predictions.values,
default_value=-1,
name='d_predictions')
init = tf.initialize_all_variables()
saver = tf.train.Saver(write_version=tf.train.SaverDef.V2)
# session
conf = tf.ConfigProto()
if hasattr(config.eval.execution, 'per_process_gpu_memory_fraction'):
conf.gpu_options.per_process_gpu_memory_fraction = config.train.execution.per_process_gpu_memory_fraction
if hasattr(config.eval.execution, 'allow_growth'):
conf.gpu_options.allow_growth = config.train.execution.allow_growth
sess = tf.Session(graph=graph, config=conf)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
sess.run(init)
checkpoints_dir = config.model_dir
latest_checkpoint = None
wait_iters = 0
if not os.path.exists(os.path.join(checkpoints_dir, 'eval')):
os.mkdir(os.path.join(checkpoints_dir, 'eval'))
writer = tf.summary.FileWriter(os.path.join(checkpoints_dir, 'eval'),
sess.graph)
while True:
if config.eval.checkpoint != '':
new_checkpoint = config.eval.checkpoint
else:
new_checkpoint = tf.train.latest_checkpoint(checkpoints_dir)
if latest_checkpoint != new_checkpoint:
latest_checkpoint = new_checkpoint
saver.restore(sess, latest_checkpoint)
current_step = tf.train.load_variable(latest_checkpoint,
'global_step')
test_size = dataset_size(config.eval.file_list_path)
time_start = time.time()
mean_accuracy, mean_accuracy_minus_1 = 0.0, 0.0
steps = int(test_size / config.eval.batch_size) if int(
test_size / config.eval.batch_size) else 1
num = 0
for _ in range(steps):
val, slabel, _ = sess.run(
[d_predictions, label_val, file_names])
acc, acc1, num_ = accuracy(slabel, val, config.vocab,
config.r_vocab)
mean_accuracy += acc
mean_accuracy_minus_1 += acc1
num += num_
writer.add_summary(
tf.Summary(value=[
tf.Summary.Value(tag='evaluation/acc',
simple_value=float(mean_accuracy / num)),
tf.Summary.Value(tag='evaluation/acc-1',
simple_value=float(mean_accuracy_minus_1 /
num))
]), current_step)
print('Test acc: {}'.format(mean_accuracy / num))
print('Test acc-1: {}'.format(mean_accuracy_minus_1 / num))
print('Time per step: {} for test size {}'.format(
time.time() - time_start / steps, test_size))
else:
if wait_iters % 12 == 0:
sys.stdout.write('\r')
for _ in range(11 + wait_iters // 12):
sys.stdout.write(' ')
sys.stdout.write('\r')
for _ in range(1 + wait_iters // 12):
sys.stdout.write('|')
else:
sys.stdout.write('.')
sys.stdout.flush()
time.sleep(5)
wait_iters += 1
if config.eval.checkpoint != '':
break
coord.request_stop()
coord.join(threads)
sess.close()
def infer(config):
if hasattr(config.infer, 'random_seed'):
np.random.seed(config.infer.random_seed)
tf.set_random_seed(config.infer.random_seed)
random.seed(config.infer.random_seed)
if hasattr(config.infer.execution, 'CUDA_VISIBLE_DEVICES'):
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ[
"CUDA_VISIBLE_DEVICES"] = config.train.execution.CUDA_VISIBLE_DEVICES
height, width, channels_num = config.input_shape
rnn_cells_num = config.rnn_cells_num
graph = tf.Graph()
with graph.as_default():
with slim.arg_scope([slim.batch_norm, slim.dropout],
is_training=False):
inp_data, filenames = data_input(
height,
width,
channels_num,
config.infer.file_list_path,
batch_size=config.infer.batch_size)
prob = inference(rnn_cells_num, inp_data, config.num_classes)
prob = tf.transpose(prob, (1, 0, 2)) # prepare for CTC
data_length = tf.fill(
[tf.shape(prob)[1]],
tf.shape(prob)[0]) # input seq length, batch size
result = tf.nn.ctc_greedy_decoder(prob,
data_length,
merge_repeated=True)
predictions = tf.to_int32(result[0][0])
d_predictions = tf.sparse_to_dense(predictions.indices, [
tf.shape(inp_data, out_type=tf.int64)[0], config.max_lp_length
],
predictions.values,
default_value=-1,
name='d_predictions')
init = tf.initialize_all_variables()
saver = tf.train.Saver(write_version=tf.train.SaverDef.V2)
# session
conf = tf.ConfigProto()
if hasattr(config.eval.execution, 'per_process_gpu_memory_fraction'):
conf.gpu_options.per_process_gpu_memory_fraction = config.train.execution.per_process_gpu_memory_fraction
if hasattr(config.eval.execution, 'allow_growth'):
conf.gpu_options.allow_growth = config.train.execution.allow_growth
sess = tf.Session(graph=graph, config=conf)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
sess.run(init)
latest_checkpoint = config.infer.checkpoint
if config.infer.checkpoint == '':
latest_checkpoint = tf.train.latest_checkpoint(config.model_dir)
saver.restore(sess, latest_checkpoint)
infer_size = dataset_size(config.infer.file_list_path)
steps = int(infer_size /
config.infer.batch_size) if int(infer_size /
config.infer.batch_size) else 1
ii = 0
for _ in range(steps):
vals, batch_filenames = sess.run([d_predictions, filenames])
#print(batch_filenames)
pred = decode_beams(vals, config.r_vocab)
for i, filename in enumerate(batch_filenames):
filename = filename.decode('utf-8')
img = cv2.imread(filename)
size = cv2.getTextSize(pred[i], cv2.FONT_HERSHEY_SIMPLEX, 0.55, 2)
text_width = size[0][0]
text_height = size[0][1]
img_he, img_wi, _ = img.shape
img = cv2.copyMakeBorder(img,
0,
text_height + 10,
0,
0 if text_width < img_wi else text_width -
img_wi,
cv2.BORDER_CONSTANT,
value=(255, 255, 255))
cv2.putText(img, pred[i], (0, img_he + text_height + 5),
cv2.FONT_HERSHEY_SIMPLEX, 0.55, (0, 0, 0), 2)
#cv2.imshow('License Plate', img)
ii = ii + 1
nameImg = 'result_' + str(ii) + '.png'
savePath = "results"
pathImg = savePath + "/" + nameImg
print("Result saved at: {}".format(pathImg))
cv2.imwrite(os.path.join(savePath, nameImg), img)
key = cv2.waitKey(1)
if key == 27:
break
coord.request_stop()
coord.join(threads)
sess.close()