def serve():
server = grpc.server(futures.ThreadPoolExecutor(max_workers=10))
all_in_one_pb2_grpc.add_AllInOneServicer_to_server(Greeter(), server)
server.add_insecure_port('[::]:50051')
server.start()
model = load_model(
"/home/samuel/projects/All-In-One/allinonemodels/allinone.json",
"/home/samuel/projects/All-In-One/allinonemodels/freeze2.h5",
["age_estimation", "smile", "gender_probablity"])
model.summary()
detector = dlib.get_frontal_face_detector()
#image demo
images_demo(model,
"/home/samuel/projects/All-In-One/grpc/test/test_images/",
detector)
#video demo
#webcam_demo(model,detector)
video_demo(
model,
"/home/samuel/projects/All-In-One/grpc/test/test_videos/video_demo3.mp4",
detector)
try:
while True:
time.sleep(_ONE_DAY_IN_SECONDS)
except KeyboardInterrupt:
server.stop(0)
def main():
print("loading model")
model = load_model(
"/home/samuel/projects/All-In-One/allinonemodels/allinone.json",
"/home/samuel/projects/All-In-One/allinonemodels/freeze2.h5",
["age_estimation", "smile", "gender_probablity"])
model.summary()
print("loaded model")
detector = dlib.get_frontal_face_detector()
images_demo(model, "/home/samuel/projects/All-In-One/Images/", detector)
def main():
global args
args = parser.parse_args()
if not os.path.isdir(args.out):
os.mkdir(args.out)
topics = []
velo_topics = []
odom_topics = []
if args.odom_topics != None:
for t in args.odom_topics.split(","):
odom_topics.append(t)
topics.append(t)
cam_topics = []
if args.cam_topics != None:
for t in args.cam_topics.split(","):
cam_topics.append(t)
topics.append(t)
if args.velo_topics != None:
for t in args.velo_topics.split(","):
velo_topics.append(t)
topics.append(t)
import json
print(json.dumps(cfg, sort_keys=True, indent=2))
model = load_model()
offset = 0
for b in args.bags.split(","):
print("start bag", b)
bag_name = b.split('/')[-1]
car_name = bag_name.split('_')[1]
date = int(bag_name.split('_')[0].split('T')[0])
sys.stdout.flush()
bag = rosbag.Bag(b)
msg_it = iter(
buffered_message_generator(bag, args.tolerance, topics,
odom_topics))
offset = msg_loop(args.out, args.rate, args.frame_limit, topics,
velo_topics, cam_topics, odom_topics, msg_it, offset,
model, car_name, date)
from flask import Flask, flash, render_template, redirect, url_for, request
import demo
model = demo.load_model()
app = Flask(__name__)
@app.route('/')
def hello_world():
return redirect('/classify')
@app.route('/classify', methods=['GET', 'POST'])
def classify_system():
error = None
if request.method == 'POST':
comment = request.form['comment']
if comment == '':
error = 'Bạn chưa nhập dữ liệu. Hãy nhập lại'
return render_template('UI_demo.html', error=error)
else:
predict = demo.classify_one_comment(model, comment)[-1]
print(predict)
if predict == 0:
emotional = "Tích cực"
else:
emotional = "Tiêu cực"
return render_template('UI_demo.html',
error=error,
comment=comment,
from demo import load_model, detect
import glob
import time
MODEL = 'faster_rcnn_inception_resnet_v2_atrous_coco_11_06_2017'
sess = load_model(MODEL)
THRESHOLD = 0.7
TEST_IMAGE_PATHS = glob.glob("/root/data/demo/van_big/*.jpg")
for img_path in TEST_IMAGE_PATHS:
tic = time.time()
outputs = detect(sess, img_path, thresh=THRESHOLD)
print("Detection Time {0:.2f} sec".format(time.time() - tic))
for output in outputs:
score = output['score']
class_name = output['class']
x = output['x']
y = output['y']
width = output['width']
height = output['height']
print("'{}' detected with confidence {} in [{}, {}, {}, {}]\n".format(class_name.upper(),\
score, x, y, width,\
height))
#video demo
#webcam_demo(model,detector)
video_demo(
model,
"/home/samuel/projects/All-In-One/grpc/test/test_videos/video_demo3.mp4",
detector)
try:
while True:
time.sleep(_ONE_DAY_IN_SECONDS)
except KeyboardInterrupt:
server.stop(0)
if __name__ == '__main__':
model = load_model(
"/home/samuel/projects/All-In-One/allinonemodels/allinone.json",
"/home/samuel/projects/All-In-One/allinonemodels/freeze2.h5",
["age_estimation", "smile", "gender_probablity"])
model.summary()
detector = dlib.get_frontal_face_detector()
#image demo
images_demo(model,
"/home/samuel/projects/All-In-One/grpc/test/test_images/",
detector)
#video demo
#webcam_demo(model,detector)
video_demo(
model,
"/home/samuel/projects/All-In-One/grpc/test/test_videos/video_demo3.mp4",
detector)
serve()
def main():
parser = get_parser()
args = parser.parse_args()
device = torch.device(args.device)
smpl = SMPL_Layer().to(device)
train_parser = TrainingOptionParser()
model_args = train_parser.load(pjoin(args.model_path, 'args.txt'))
test_pose, test_loc = load_test_anim(args.pose_file, device)
test_shape = torch.tensor(np.load('./eval_constant/test_shape.npy'),
device=device)
topo_loader = TopologyLoader(device=device, debug=False)
smpl_topo_begin, len_topo_smpl = topo_loader.load_smpl_group(
'./dataset/Meshes/SMPL/topology/', is_train=False)
env_model, res_model = load_model(device,
model_args,
topo_loader,
args.model_path,
envelope_only=False)
res_weight = []
res_skeleton = []
res_verts = []
res_verts_lbs = []
gt_skeleton = smpl.get_offset(test_shape)
gt_verts = []
print('Evaluating model...')
for i in tqdm(range(test_shape.shape[0])):
pose_ph = torch.zeros((1, 72), device=device)
t_pose = smpl.forward(pose_ph, test_shape[[i]])[0][0]
# t_pose = t_pose[topo_loader.v_masks[i]]
gt_vs = smpl.forward(test_pose,
test_shape[[i]].expand(test_pose.shape[0], -1))[0]
gt_vs = gt_vs[:, topo_loader.v_masks[i]]
gt_verts.append(gt_vs)
weight, skeleton, vs, vs_lbs, _, _ = run_single_mesh(t_pose,
smpl_topo_begin +
i,
test_pose,
env_model,
res_model,
requires_lbs=True)
res_weight.append(weight)
res_skeleton.append(skeleton)
res_verts.append(vs)
res_verts_lbs.append(vs_lbs)
err_weight = []
err_avg_verts = []
err_max_verts = []
err_lbs_verts = []
err_j2j = []
err_j2b = []
err_b2b = []
print('Aggregating error...')
for i in tqdm(range(test_shape.shape[0])):
mask = topo_loader.v_masks[i]
weight_gt = smpl.weights[mask]
err_weight.append(chamfer_weight(res_weight[i], weight_gt))
err_vert = vert_distance(res_verts[i], gt_verts[i])
err_lbs = vert_distance(res_verts_lbs[i], gt_verts[i])
err_avg_verts.append(err_vert[0])
err_max_verts.append(err_vert[1])
err_lbs_verts.append(err_lbs[0])
err_j2j.append(
chamfer_j2j(res_skeleton[i], gt_skeleton[i], parent_smpl))
err_j2b.append(
chamfer_j2b(res_skeleton[i], gt_skeleton[i], parent_smpl))
err_b2b.append(
chamfer_b2b(res_skeleton[i], gt_skeleton[i], parent_smpl))
err_weight = np.array(err_weight).mean()
err_avg_verts = np.array(err_avg_verts).mean()
err_max_verts = np.array(err_max_verts).mean()
err_lbs_verts = np.array(err_lbs_verts).mean()
err_j2j = np.array(err_j2j).mean()
err_j2b = np.array(err_j2b).mean()
err_b2b = np.array(err_b2b).mean()
print('Skinning Weight L1 = %.7f' % err_weight)
print('Vertex Mean Loss L2 = %.7f' % err_avg_verts)
print('Vertex Max Loss L2 = %.7f' % err_max_verts)
print('Envelope Mean Loss L2 = %.7f' % err_lbs_verts)
print('CD-J2J = %.7f' % err_j2j)
print('CD-J2B = %.7f' % err_j2b)
print('CD-B2B = %.7f' % err_b2b)