def main():
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
phi = 1
weighted_bifpn = False
model_path = 'checkpoints/2019-12-03/pascal_05_0.6283_1.1975_0.8029.h5'
image_sizes = (512, 640, 768, 896, 1024, 1280, 1408)
image_size = image_sizes[phi]
classes = [
'aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair',
'cow', 'diningtable', 'dog', 'horse', 'motorbike', 'person', 'pottedplant', 'sheep', 'sofa', 'train',
'tvmonitor',
]
num_classes = len(classes)
score_threshold = 0.5
colors = [np.random.randint(0, 256, 3).tolist() for i in range(num_classes)]
model, prediction_model = efficientdet(phi=phi,
weighted_bifpn=weighted_bifpn,
num_classes=num_classes,
score_threshold=score_threshold)
prediction_model.load_weights(model_path, by_name=True)
video_path = 'datasets/video.mp4'
cap = cv2.VideoCapture(video_path)
while True:
ret, frame = cap.read()
if not ret:
break
h, w = frame.shape[:2]
image, scale, offset_h, offset_w = preprocess_image(frame, image_size=image_size)
anchors = anchors_for_shape((image_size, image_size))
boxes_batch, scores_batch, labels_batch = prediction_model.predict_on_batch([np.expand_dims(image, axis=0),
np.expand_dims(anchors, axis=0)])
for i, (boxes, scores, labels) in enumerate(zip(boxes_batch, scores_batch, labels_batch)):
boxes = post_process_boxes(boxes=boxes,
scale=scale,
offset_h=offset_h,
offset_w=offset_w,
height=h,
width=w)
indices = np.where(scores[:] > score_threshold)[0]
boxes = boxes[indices]
labels = labels[indices]
draw_boxes(frame, boxes, scores, labels, colors, classes)
cv2.imshow('image', frame)
cv2.waitKey(1)
def main():
os.environ['CUDA_VISIBLE_DEVICES'] = '1'
phi = 0
model_path = 'checkpoints/2020-03-13/pascal_64_0.2799_0.4923_0.7896_w.h5'
image_sizes = (512, 640, 768, 896, 1024, 1280, 1408)
image_size = image_sizes[phi]
classes = [
'aeroplane',
'bicycle',
'bird',
'boat',
'bottle',
'bus',
'car',
'cat',
'chair',
'cow',
'diningtable',
'dog',
'horse',
'motorbike',
'person',
'pottedplant',
'sheep',
'sofa',
'train',
'tvmonitor',
]
num_classes = len(classes)
score_threshold = 0.3
colors = [
np.random.randint(0, 256, 3).tolist() for i in range(num_classes)
]
model, prediction_model = sapd(
phi=phi,
num_classes=num_classes,
score_threshold=score_threshold,
)
prediction_model.load_weights(model_path, by_name=True)
for image_path in glob.glob('datasets/VOC2007/JPEGImages/*.jpg'):
image = cv2.imread(image_path)
src_image = image.copy()
image = image[:, :, ::-1]
h, w = image.shape[:2]
image, scale, offset_h, offset_w = preprocess_image(
image, image_size=image_size)
# run network
start = time.time()
boxes, scores, labels = prediction_model.predict_on_batch(
[np.expand_dims(image, axis=0)])
boxes, scores, labels = np.squeeze(boxes), np.squeeze(
scores), np.squeeze(labels)
print(time.time() - start)
boxes = post_process_boxes(boxes=boxes,
scale=scale,
offset_h=offset_h,
offset_w=offset_w,
height=h,
width=w)
# select indices which have a score above the threshold
indices = np.where(scores[:] > score_threshold)[0]
# select those detections
boxes = boxes[indices]
labels = labels[indices]
draw_boxes(src_image, boxes, scores, labels, colors, classes)
cv2.namedWindow('image', cv2.WINDOW_NORMAL)
cv2.imshow('image', src_image)
key = cv2.waitKey(0)
def main():
phi = 1
model_path = 'checkpoints/2019-12-03/pascal_05.pb'
image_sizes = (512, 640, 768, 896, 1024, 1280, 1408)
image_size = image_sizes[phi]
classes = [
'aeroplane',
'bicycle',
'bird',
'boat',
'bottle',
'bus',
'car',
'cat',
'chair',
'cow',
'diningtable',
'dog',
'horse',
'motorbike',
'person',
'pottedplant',
'sheep',
'sofa',
'train',
'tvmonitor',
]
num_classes = len(classes)
score_threshold = 0.5
colors = [
np.random.randint(0, 256, 3).tolist() for i in range(num_classes)
]
output_names = {
'output_boxes':
'filtered_detections/map/TensorArrayStack/TensorArrayGatherV3:0',
'output_scores':
'filtered_detections/map/TensorArrayStack_1/TensorArrayGatherV3:0',
'output_labels':
'filtered_detections/map/TensorArrayStack_2/TensorArrayGatherV3:0'
}
graph = tf.Graph()
graph.as_default()
sess = tf.Session()
graph = get_frozen_graph(model_path)
tf.import_graph_def(graph, name='')
output_boxes = sess.graph.get_tensor_by_name(output_names["output_boxes"])
output_scores = sess.graph.get_tensor_by_name(
output_names['output_scores'])
output_labels = sess.graph.get_tensor_by_name(
output_names['output_labels'])
image_path = 'datasets/VOC2007/JPEGImages/000002.jpg'
image = cv2.imread(image_path)
src_image = image.copy()
image = image[:, :, ::-1]
h, w = image.shape[:2]
image, scale = preprocess_image(image, image_size=image_size)
anchors = anchors_for_shape((image_size, image_size))
# run network
start = time.time()
image_batch = np.expand_dims(image, axis=0)
anchors_batch = np.expand_dims(anchors, axis=0)
feed_dict = {"input_1:0": image_batch, "input_4:0": anchors_batch}
boxes, scores, labels = sess.run(
[output_boxes, output_scores, output_labels], feed_dict)
boxes, scores, labels = np.squeeze(boxes), np.squeeze(scores), np.squeeze(
labels)
print(time.time() - start)
boxes = post_process_boxes(boxes=boxes,
scale=scale,
offset_h=offset_h,
offset_w=offset_w,
height=h,
width=w)
# select indices which have a score above the threshold
indices = np.where(scores[:] > score_threshold)[0]
# select those detections
boxes = boxes[indices]
labels = labels[indices]
draw_boxes(src_image, boxes, scores, labels, colors, classes)
cv2.namedWindow('image', cv2.WINDOW_NORMAL)
cv2.imshow('image', src_image)
cv2.waitKey(0)