def local_eval(func, model, image_size, test_path, name_path, verbose):
tmp_path = os.path.join('tmp' +
time.strftime("%Y%m%d%H%M", time.localtime()))
if os.path.exists(tmp_path):
os.remove(tmp_path)
with open(test_path) as f:
lines = f.readlines()
paths = [line.split()[0] for line in lines]
infer_time = []
with open(tmp_path, 'a+') as f:
for i, path in enumerate(paths, 1):
if i == 1:
sys.stdout.write('\n')
sys.stdout.write('\r' + keras_bar(i, len(paths)))
image = read_image(path)
h, w = image.shape[:2]
image = preprocess_image(image, (image_size, image_size)).astype(
np.float32)
images = np.expand_dims(image, axis=0)
tic = time.time()
bboxes, scores, classes, valid_detections = model.predict(images)
toc = time.time()
infer_time.append(toc - tic)
bboxes = bboxes[0][:valid_detections[0]]
scores = scores[0][:valid_detections[0]]
classes = classes[0][:valid_detections[0]]
bboxes *= image_size
_, bboxes = preprocess_image_inv(image, (w, h), bboxes)
line = path
for bbox, score, cls in zip(bboxes, scores, classes):
x1, y1, x2, y2 = bbox
line += " {:.2f},{:.2f},{:.2f},{:.2f},{},{:.4f}".format(
x1, y1, x2, y2, int(cls), score)
f.write(line + '\n')
ans = func(test_path, tmp_path, name_path, verbose)
# remove tmp
os.remove(tmp_path)
if verbose:
if len(infer_time) > 5:
s = np.mean(infer_time[5:])
else:
s = np.mean(infer_time)
print('Inference time', s * 1000, 'ms')
return ans
def _getitem(self, sub_idx):
path, bboxes, labels = self.annotation[sub_idx]
image = read_image(path)
if len(bboxes) != 0:
bboxes, labels = np.array(bboxes), np.array(labels)
else:
bboxes, labels = np.zeros((0, 4)), np.zeros((0,))
image, bboxes = preprocess_image(image, (self._image_size, self._image_size), bboxes)
labels = augment.onehot(labels, self.num_classes, self.label_smoothing)
return image, bboxes, labels
def _getitem(self, sub_idx):
path, bboxes, labels = self.annotation[sub_idx]
image = read_image(path)
bboxes, labels = np.array(bboxes), np.array(labels)
image = augment.random_distort(image)
image = augment.random_grayscale(image)
image, bboxes = augment.random_flip_lr(image, bboxes)
image, bboxes = augment.random_rotate(image, bboxes)
image, bboxes, labels = augment.random_crop_and_zoom(
image, bboxes, labels, (self._image_size, self._image_size))
#image, bboxes = preprocess_image(image, (self._image_size, self._image_size), bboxes)
labels = augment.onehot(labels, self.num_classes, self.label_smoothing)
return image, bboxes, labels
def main(_argv):
# read config
print('Config File From:', FLAGS.config)
print('Media From:', FLAGS.media)
print('Use GPU:', FLAGS.gpu)
if not FLAGS.gpu:
import os
os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
cfg = decode_cfg(FLAGS.config)
model_type = cfg['yolo']['type']
if model_type == 'yolov3':
from core.model.one_stage.yolov3 import YOLOv3 as Model
elif model_type == 'yolov3_tiny':
from core.model.one_stage.yolov3 import YOLOv3_Tiny as Model
elif model_type == 'yolov4':
from core.model.one_stage.yolov4 import YOLOv4 as Model
elif model_type == 'yolov4_tiny':
from core.model.one_stage.yolov4 import YOLOv4_Tiny as Model
elif model_type == 'yolox':
from core.model.one_stage.custom import YOLOX as Model
else:
raise NotImplementedError()
_, model = Model(cfg)
model.summary()
init_weight_path = cfg['test']['init_weight_path']
if init_weight_path:
print('Load Weights File From:', init_weight_path)
load_weights(model, init_weight_path)
else:
raise SystemExit('init_weight_path is Empty !')
# assign colors for difference labels
shader = Shader(cfg['yolo']['num_classes'])
names = cfg['yolo']['names']
image_size = cfg['test']['image_size'][0]
#model.save('E:/dm/repo/yolox/ckpts/tmp/voc_yolov4_tiny_SM_DM_CIoU_FL/yolov4_tiny_best/yolov4_tiny.h5')
# full_model = tf.function(lambda Input: model(Input))
# full_model = full_model.get_concrete_function(tf.TensorSpec(model.inputs[0].shape, model.inputs[0].dtype))
#
# # Get frozen ConcreteFunction
# frozen_func = convert_variables_to_constants_v2(full_model)
# frozen_func.graph.as_graph_def()
#
# layers = [op.name for op in frozen_func.graph.get_operations()]
# print("-" * 50)
# print("Frozen model layers: ")
# for layer in layers:
# print(layer)
#
# print("-" * 50)
# print("Frozen model inputs: ")
# print(frozen_func.inputs)
# print("Frozen model outputs: ")
# print(frozen_func.outputs)
#
# # Save frozen graph from frozen ConcreteFunction to hard drive
# tf.io.write_graph(graph_or_graph_def=frozen_func.graph,
# logdir="./frozen_models",
# name="yolov4_tiny_tf.pb",
# as_text=False)
def inference(image):
h, w = image.shape[:2]
image = preprocess_image(image,
(image_size, image_size)).astype(np.float32)
images = np.expand_dims(image, axis=0)
tic = time.time()
bboxes, scores, classes, valid_detections = model.predict(images)
toc = time.time()
bboxes = bboxes[0][:valid_detections[0]]
scores = scores[0][:valid_detections[0]]
classes = classes[0][:valid_detections[0]]
# bboxes *= image_size
_, bboxes = postprocess_image(image, (w, h), bboxes)
return (toc - tic) * 1000, bboxes, scores, classes
if FLAGS.media.startswith('rtsp') or FLAGS.media.isdigit(
) or FLAGS.media.endswith('.mp4') or FLAGS.media.endswith('.avi'):
from collections import deque
d = deque(maxlen=10)
media = read_video(FLAGS.media)
while True:
ret, image = media.read()
if not ret: break
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
ms, bboxes, scores, classes = inference(image)
image = draw_bboxes(image, bboxes, scores, classes, names, shader)
d.append(ms)
mms = np.mean(d)
print('Inference Time:', mms, 'ms')
image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
image = cv2.putText(image, "{:.2f} ms".format(mms), (0, 30),
cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 255, 0),
2)
cv2.imshow('Image', image)
if cv2.waitKey(33) == ord('q'):
break
media.release()
elif FLAGS.media.endswith('.jpg') or FLAGS.media.endswith('.png'):
image = read_image(FLAGS.media)
ms, bboxes, scores, classes = inference(image)
image = draw_bboxes(image, bboxes, scores, classes, names, shader)
print('Inference Time:', ms, 'ms')
image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
cv2.imshow('Image', image)
cv2.waitKey()
def main(_argv):
# read config
print('Config File From:', FLAGS.config)
print('Media From:', FLAGS.media)
print('Use GPU:', FLAGS.gpu)
if not FLAGS.gpu:
import os
os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
cfg = decode_cfg(FLAGS.config)
model_type = cfg['yolo']['type']
if model_type == 'yolov3':
from core.model.one_stage.yolov3 import YOLOv3 as Model
elif model_type == 'yolov3_tiny':
from core.model.one_stage.yolov3 import YOLOv3_Tiny as Model
elif model_type == 'yolov4':
from core.model.one_stage.yolov4 import YOLOv4 as Model
elif model_type == 'yolov4_tiny':
from core.model.one_stage.yolov4 import YOLOv4_Tiny as Model
else:
raise NotImplementedError()
_, model = Model(cfg)
model.summary()
init_weight_path = cfg['test']['init_weight_path']
if init_weight_path:
print('Load Weights File From:', init_weight_path)
load_weights(model, init_weight_path)
else:
raise SystemExit('init_weight_path is Empty !')
# assign colors for difference labels
shader = Shader(cfg['yolo']['num_classes'])
names = cfg['yolo']['names']
image_size = cfg['test']['image_size'][0]
def inference(image):
h, w = image.shape[:2]
image = preprocess_image(image,
(image_size, image_size)).astype(np.float32)
images = np.expand_dims(image, axis=0)
tic = time.time()
bboxes, scores, classes, valid_detections = model.predict(images)
toc = time.time()
bboxes = bboxes[0][:valid_detections[0]]
scores = scores[0][:valid_detections[0]]
classes = classes[0][:valid_detections[0]]
# bboxes *= image_size
_, bboxes = postprocess_image(image, (w, h), bboxes)
return (toc - tic) * 1000, bboxes, scores, classes
if FLAGS.media.startswith('rtsp') or FLAGS.media.isdigit(
) or FLAGS.media.endswith('.mp4') or FLAGS.media.endswith('.avi'):
from collections import deque
d = deque(maxlen=10)
media = read_video(FLAGS.media)
while True:
ret, image = media.read()
if not ret: break
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
ms, bboxes, scores, classes = inference(image)
image = draw_bboxes(image, bboxes, scores, classes, names, shader)
d.append(ms)
mms = np.mean(d)
print('Inference Time:', mms, 'ms')
image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
image = cv2.putText(image, "{:.2f} ms".format(mms), (0, 30),
cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 255, 0),
2)
cv2.imshow('Image', image)
if cv2.waitKey(33) == ord('q'):
break
media.release()
elif FLAGS.media.endswith('.jpg') or FLAGS.media.endswith('.png'):
image = read_image(FLAGS.media)
ms, bboxes, scores, classes = inference(image)
image = draw_bboxes(image, bboxes, scores, classes, names, shader)
print('Inference Time:', ms, 'ms')
image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
cv2.imshow('Image', image)
cv2.waitKey()