from utils.model import load_weights
from utils.training import Logger
os.environ["CUDA_VISIBLE_DEVICES"] = '2'
# In[3]
# TextBoxes++ + DenseNet
model = TBPP512_dense(softmax=False)
weights_path = None
freeze = []
batch_size = 6
experiment = 'dsodtbpp512fl_synthtext'
# In[4]
prior_util = PriorUtil(model)
if weights_path is not None:
load_weights(model, weights_path)
for layer in model.layers:
layer.trainable = not layer.name in freeze
#optim = keras.optimizers.SGD(lr=1e-3, momentum=0.9, decay=0, nesterov=True)
optim = keras.optimizers.Adam(lr=1e-3,
beta_1=0.9,
beta_2=0.999,
epsilon=0.001,
decay=0.0)
# weight decay
"threshold": 0.01
}
tfnet = TFNet(yolo9000)
# Starting the model here.1
Model = TBPP512_dense
input_shape = (512, 512, 3)
weights_path = 'weights.022.h5'
confidence_threshold = 0.35
confidence_threshold = 0.25
sl_graph = tf.Graph()
with sl_graph.as_default():
sl_session = tf.Session()
with sl_session.as_default():
sl_model = Model(input_shape)
prior_util = PriorUtil(sl_model)
sl_model.load_weights(weights_path, by_name=True)
input_width = 256
input_height = 32
weights_path = 'weights.022.h5'
def get_iou(bb1, bb2):
"""
Calculate the Intersection over Union (IoU) of two bounding boxes.
Parameters
----------
bb1 : dict
Keys: {'x1', 'x2', 'y1', 'y2'}
The (x1, y1) position is at the top left corner,
data_path = './data/ky_test'
dataset_name = 'AGM_GOOD'
confidence_threshold = 0.25
image_names = np.sort(
glob.glob(os.path.join(data_path, dataset_name, '*', '*.bmp')))
print(len(image_names))
annotation_path = os.path.join(data_path, dataset_name, 'Annotations')
if not os.path.exists(annotation_path):
os.makedirs(annotation_path)
# TextBoxes++ + DenseNet
tbpp = TBPP512_dense(softmax=False)
# model = TBPP512(softmax=False)
prior_util = PriorUtil(tbpp)
checkdir = os.path.dirname(weights_path)
input_width = 256
input_height = 32
crnn = CRNN((input_width, input_height, 1),
len(alphabet),
prediction_only=True,
gru=False)
print("started loading model weights")
tic = time.time()
tbpp.load_weights(weights_path)
crnn.load_weights(weights_path_crnn)
print(time.time() - tic)
print("finished loading model weights")
from crnn_utils import decode
if __name__ == '__main__':
Model = TBPP512_dense
input_shape = (512, 512, 3)
weights_path = 'weights.022.h5'
confidence_threshold = 0.35
confidence_threshold = 0.25
sl_graph = tf.Graph()
with sl_graph.as_default():
sl_session = tf.Session()
with sl_session.as_default():
sl_model = Model(input_shape)
prior_util = PriorUtil(sl_model)
sl_model.load_weights(weights_path, by_name=True)
input_width = 256
input_height = 32
weights_path = 'weights.022.h5'
crnn_graph = tf.Graph()
with crnn_graph.as_default():
crnn_session = tf.Session()
with crnn_session.as_default():
crnn_model = CRNN((input_width, input_height, 1),
len(alphabet),
prediction_only=True,
gru=True)
crnn_model.load_weights(weights_path, by_name=True)
weights_path = options.weights_file
output_dir = options.output_dir
map_images_dir = options.images_dir
do_preprocess = bool(options.preprocess)
test_only = bool(options.test_only)
test_split_file = options.test_split
confidence_threshold = options.confidence
do_rotate_image = bool(options.rotate)
# TextBoxes++ + DenseNet
model = TBPP512_dense(softmax=False)
load_weights(model, weights_path)
prior_util = PriorUtil(model)
test_filenames = []
if test_only:
with open(test_split_file) as f:
test_filenames = [line.replace("\n", "") for line in f.readlines()]
crop_h = 512
crop_w = 512
step = 400
angles = range(-90, 95, 5) if do_rotate_image else [0]
for filepath in glob.glob(os.path.join(map_images_dir, 'D*')):
filename = filepath.split('/')[-1]