def main():
# load heatmaps .etc
rpsm_db = generate_data_for_rpsm()
# load pairwise constraints
pairwise_file = os.path.join(config.DATASET.ROOT, 'testdata',
'pairwise_b16.pkl')
with open(pairwise_file, 'rb') as f:
pairwise = pickle.load(f)
pairwise = pairwise['pairwise_constrain']
all_cameras, all_hms, all_boxes, all_grid_centers, all_limb_lengths, all_gts = load_rpsm_testdata_all(
rpsm_db)
res = []
for idx, (cameras, hms, boxes, grid_center, limb_length, gt) in enumerate(
zip(all_cameras, all_hms, all_boxes, all_grid_centers,
all_limb_lengths, all_gts)):
pose = rpsm(cameras, hms, boxes, grid_center, limb_length, pairwise,
config)
# print('GroundTruth Pose: ', gt)
# print('Recovered Pose by RPSM: ', pose)
mpjpe = np.mean(np.sqrt(np.sum((pose - gt)**2, axis=1)))
# print('MPJPE: ', mpjpe)
res.append(mpjpe)
if idx % 500 == 0:
print('%d:%.2f' % (idx, mpjpe))
print('MPJPE: ', np.mean(res))
def main():
args = parse_args()
logger, final_output_dir, tb_log_dir = create_logger(
config, args.cfg, 'test3d')
prediction_path = os.path.join(final_output_dir,
config.TEST.HEATMAP_LOCATION_FILE)
test_dataset = eval('dataset.' + config.DATASET.TEST_DATASET)(
config, config.DATASET.TEST_SUBSET, False)
all_heatmaps = h5py.File(prediction_path)['heatmaps']
pairwise_file = config.PICT_STRUCT.PAIRWISE_FILE
with open(pairwise_file, 'rb') as f:
pairwise = pickle.load(f)['pairwise_constrain']
cnt = 0
grouping = test_dataset.grouping
mpjpes = []
for items in grouping:
heatmaps = []
boxes = []
poses = []
cameras = []
for idx in items:
datum = test_dataset.db[idx]
camera = datum['camera']
cameras.append(camera)
poses.append(
camera_to_world_frame(datum['joints_3d'], camera['R'],
camera['T']))
box = {}
box['scale'] = np.array(datum['scale'])
box['center'] = np.array(datum['center'])
boxes.append(box)
heatmaps.append(all_heatmaps[cnt])
cnt += 1
heatmaps = np.array(heatmaps)
# This demo uses GT root locations and limb length; but can be replaced by statistics
grid_center = poses[0][0]
body = HumanBody()
limb_length = compute_limb_length(body, poses[0])
prediction = rpsm(cameras, heatmaps, boxes, grid_center, limb_length,
pairwise, config)
mpjpe = np.mean(np.sqrt(np.sum((prediction - poses[0])**2, axis=1)))
mpjpes.append(mpjpe)
print(np.mean(mpjpes))
def main():
parse_args()
test_data_file = 'data/testdata/rpsm_testdata_b16.pkl'
pairwise_file = 'data/testdata/pairwise_b16.pkl'
with open(pairwise_file, 'rb') as f:
pairwise = pickle.load(f)
pairwise = pairwise['pairwise_constrain']
all_cameras, all_hms, all_boxes, all_grid_centers, all_limb_lengths, all_gts = load_rpsm_testdata_all(
test_data_file)
res = []
for idx, (cameras, hms, boxes, grid_center, limb_length, gt) in enumerate(zip(all_cameras,
all_hms, all_boxes, all_grid_centers,all_limb_lengths, all_gts)):
pose = rpsm(cameras, hms, boxes, grid_center, limb_length, pairwise, config)
# print('GroundTruth Pose: ', gt)
# print('Recovered Pose by RPSM: ', pose)
mpjpe = np.mean(np.sqrt(np.sum((pose - gt)**2, axis=1)))
# print('MPJPE: ', mpjpe)
res.append(mpjpe)
if idx % 500 == 0:
print('%d:%.2f' % (idx, mpjpe))
print('MPJPE: ', np.mean(res))