@files(params)
def score_frame_queue(
(dataset_dir, dataset_config_filename, frame_hist_filename),
(outfile_wait, outfile_npz), dataset_name, frame, likelihood_i):
np.random.seed(0)
dataset_dir = os.path.join(FL_DATA, dataset_name)
cf = pickle.load(open(dataset_config_filename))
led_params = pickle.load(
open(os.path.join(dataset_dir, "led.params.pickle")))
EO = measure.led_params_to_EO(cf, led_params)
x_range = np.linspace(0, cf['field_dim_m'][1], X_GRID_NUM)
y_range = np.linspace(0, cf['field_dim_m'][0], Y_GRID_NUM)
phi_range = np.linspace(0, 2 * np.pi, PHI_GRID_NUM)
degrees_from_vertical = 30
radian_range = degrees_from_vertical / 180. * np.pi
theta_range = np.linspace(np.pi / 2. - radian_range,
np.pi / 2. + radian_range, THETA_GRID_NUM)
sv = create_state_vect(y_range, x_range, phi_range, theta_range)
# now the input args
chunk_size = 80000
chunks = int(np.ceil(len(sv) / float(chunk_size)))
@files(params)
def det_run((epoch_dir, epoch_config_filename,
region_filename, led_params_filename), outfile,
epoch,
frame_start, frame_end):
np.random.seed(0)
cf = pickle.load(open(epoch_config_filename, 'r'))
region = pickle.load(open(region_filename, 'r'))
env = util.Environmentz(cf['field_dim_m'],
cf['frame_dim_pix'])
led_params = pickle.load(open(led_params_filename, 'r'))
eo_params = measure.led_params_to_EO(cf, led_params)
if frame_end > cf['end_f']:
frame_end = cf['end_f']
truth = np.load(os.path.join(epoch_dir, 'positions.npy'))
truth_interp, missing = measure.interpolate(truth)
derived_truth = measure.compute_derived(truth_interp,
T_DELTA)
frame_pos = np.arange(frame_start, frame_end)
# load frames
frames = organizedata.get_frames(epoch_dir, frame_pos)
FRAMEN = len(frames)
def pf_run((epoch_dir, epoch_config_filename,
region_filename, led_params_filename), outfile,
epoch, (config_name, config_params),
posnoise,
velnoise, pix_threshold, PARTICLEN,
frame_start, frame_end, diode_scale):
np.random.seed(0)
cf = pickle.load(open(epoch_config_filename, 'r'))
region = pickle.load(open(region_filename, 'r'))
env = util.Environmentz(cf['field_dim_m'],
cf['frame_dim_pix'])
led_params = pickle.load(open(led_params_filename, 'r'))
eoparams = enlarge_sep(measure.led_params_to_EO(cf, led_params),
amount = diode_scale,
front_amount = diode_scale, back_amount = diode_scale)
#print "EO PARAMS ARE", eoparams
tr = TemplateObj(0.8, 0.4)
tr.set_params(*eoparams)
le1 = likelihood.LikelihoodEvaluator2(env, tr, similarity='dist',
likeli_params = config_params)
model_inst = model.CustomModel(env, le1,
POS_NOISE_STD=posnoise,
VELOCITY_NOISE_STD=velnoise)
frame_pos = np.arange(frame_start, frame_end)
@files(params)
def pf_run((epoch_dir, epoch_config_filename, region_filename,
led_params_filename), outfile, epoch, (config_name, config_params),
posnoise, velnoise, pix_threshold, PARTICLEN, frame_start,
frame_end, diode_scale):
np.random.seed(0)
cf = pickle.load(open(epoch_config_filename, 'r'))
region = pickle.load(open(region_filename, 'r'))
env = util.Environmentz(cf['field_dim_m'], cf['frame_dim_pix'])
led_params = pickle.load(open(led_params_filename, 'r'))
eoparams = enlarge_sep(measure.led_params_to_EO(cf, led_params),
amount=diode_scale,
front_amount=diode_scale,
back_amount=diode_scale)
#print "EO PARAMS ARE", eoparams
tr = TemplateObj(0.8, 0.4)
tr.set_params(*eoparams)
le1 = likelihood.LikelihoodEvaluator2(env,
tr,
similarity='dist',
likeli_params=config_params)
model_inst = model.CustomModel(env,
le1,
yield (infiles, outfiles, epoch, frame, likelihood_i)
@files(params)
def score_frame_queue((dataset_dir, dataset_config_filename,
frame_hist_filename), (outfile_wait,
outfile_npz), dataset_name, frame, likelihood_i):
np.random.seed(0)
dataset_dir = os.path.join(FL_DATA, dataset_name)
cf = pickle.load(open(dataset_config_filename))
led_params = pickle.load(open(os.path.join(dataset_dir, "led.params.pickle")))
EO = measure.led_params_to_EO(cf, led_params)
x_range = np.linspace(0, cf['field_dim_m'][1], X_GRID_NUM)
y_range = np.linspace(0, cf['field_dim_m'][0], Y_GRID_NUM)
phi_range = np.linspace(0, 2*np.pi, PHI_GRID_NUM)
degrees_from_vertical = 30
radian_range = degrees_from_vertical/180. * np.pi
theta_range = np.linspace(np.pi/2.-radian_range,
np.pi/2. + radian_range, THETA_GRID_NUM)
sv = create_state_vect(y_range, x_range, phi_range, theta_range)
# now the input args
chunk_size = 80000
chunks = int(np.ceil(len(sv) / float(chunk_size)))
if pos > MAX:
return
@files(params)
def det_run((epoch_dir, epoch_config_filename, region_filename,
led_params_filename), outfile, epoch, frame_start, frame_end):
np.random.seed(0)
cf = pickle.load(open(epoch_config_filename, 'r'))
region = pickle.load(open(region_filename, 'r'))
env = util.Environmentz(cf['field_dim_m'], cf['frame_dim_pix'])
led_params = pickle.load(open(led_params_filename, 'r'))
eo_params = measure.led_params_to_EO(cf, led_params)
if frame_end > cf['end_f']:
frame_end = cf['end_f']
truth = np.load(os.path.join(epoch_dir, 'positions.npy'))
truth_interp, missing = measure.interpolate(truth)
derived_truth = measure.compute_derived(truth_interp, T_DELTA)
frame_pos = np.arange(frame_start, frame_end)
# load frames
frames = organizedata.get_frames(epoch_dir, frame_pos)
FRAMEN = len(frames)
coordinates = []
