def __init__(self, args):
self.results = []
self.resultsPath = get_xivo_output_filename(args.dump,
args.dataset,
args.seq,
cam_id=args.cam_id,
sen=args.sen)
self.seq = seq
self.est = EstimatorData(estimator_results)
def plot_cov(self, ind):
plt.figure()
plt.title("{} covariance for timestep {}".format(self.seq, ind))
ax = plt.gca()
im = ax.imshow(self.est.P[:, :, ind], cmap='RdBu')
ax.figure.colorbar(im, ax=ax)
def user_select_plot(self):
while True:
print("Index range: {} to {}".format(self.est.start_ind,
self.est.end_ind))
index = int(input("Select a timestep: "))
self.plot_cov(index)
plt.show()
if __name__ == "__main__":
args = parser.parse_args()
estimator_data = get_xivo_output_filename(args.dump,
args.dataset,
args.seq,
cam_id=args.cam_id,
sen=args.sen)
CP = CovariancePlot(estimator_data, args.seq)
CP.user_select_plot()
)
parser.add_argument("-use_weights", default=False, action="store_true")
parser.add_argument("-cov_type", default="WTV")
args = parser.parse_args()
estimator_datafiles = []
estimators = []
test_estimators = []
test_datafiles = []
# Load data
for cam_id in [0, 1]:
for seq in ["room1", "room2", "room3", "room4", "room5", "room6"]:
estimator_datafile = get_xivo_output_filename(args.dump,
args.dataset,
seq,
cam_id=cam_id)
seq_est = EstimatorData(estimator_datafile,
adjust_startend_to_samplecov=True)
if seq == "room6":
test_datafiles.append(estimator_datafile)
test_estimators.append(seq_est)
else:
estimator_datafiles.append(estimator_datafile)
estimators.append(seq_est)
weights = {}
if args.use_weights:
weights["weightW"] = 10.
weights["weightT"] = 10.
sigmas = [np.zeros((0, 1)) for cov_type in cov_list]
df = [state_size(cov_type) for cov_type in cov_list]
num_timesteps = 0
num_1sigma = {cov_type: np.zeros(df[k]) for k, cov_type in enumerate(cov_list)}
num_2sigma = {cov_type: np.zeros(df[k]) for k, cov_type in enumerate(cov_list)}
num_3sigma = {cov_type: np.zeros(df[k]) for k, cov_type in enumerate(cov_list)}
for cam_id in [0, 1]:
for seq in ["room6"]:
print("Cam {}, {}".format(cam_id, seq))
estimator_data = get_xivo_output_filename(args.dump,
"tumvi",
seq,
cam_id=cam_id)
gt_data = get_xivo_gt_filename(args.dump, "tumvi", seq)
if args.cov_source == "original":
adjust = False
else:
adjust = True
calib = CovarianceCalibration(seq,
gt_data,
estimator_data,
three_sigma=False,
start_ind=0,
end_ind=None,
cov_type=args.cov_type,
point_cloud_registration="horn",
sigmas = np.zeros(0)
# Get neural network name, input mode, and covariance prediction type
with open(neural_net + ".pkl", "rb") as fid:
net_params = pickle.load(fid)
network_input_mode = net_params["input_mode"]
network_cov_type = net_params["cov_type"]
assert (network_cov_type == args.cov_type)
neural_net_name = neural_net.split('/')[-1]
# Collect tumvi data
for i, cam_id in enumerate(cam_ids):
for j, seq in enumerate(sequences):
idx_1 = i * len(sequences) + j
estimator_data = get_xivo_output_filename(
covdumpdir, "tumvi", seq, cam_id)
gt_data = get_xivo_gt_filename(covdumpdir, "tumvi", seq)
calib = CovarianceCalibration(
seq,
gt_data,
estimator_data,
three_sigma=False,
start_ind=0,
end_ind=None,
point_cloud_registration='horn',
plot_timesteps=False,
cov_type=network_cov_type,
adjust_startend_to_samplecov=True)
calib.align_gt_to_est()
calib.compute_errors()