def h5_shorten(input_filename, output_filename, options):
with open_file_safe(input_filename, mode="r") as h5:
with open_file_safe(output_filename, mode="w",
delete_on_error=True) as output_h5:
if not options.data2d_only:
do_data_association_tables(h5, output_h5, options)
for node in h5.root._f_iter_nodes():
if hasattr(node, "name") and node.name in [
"data2d_distorted",
"kalman_estimates",
]:
if options.data2d_only:
if node.name != "data2d_distorted":
continue
print("selectively copying", node)
copy_selective(h5, node, output_h5.root, options)
elif hasattr(node, "name") and node.name in [
"ML_estimates",
"ML_estimates_2d_idxs",
]:
continue
else:
# copy everything from source to dest
print("copying entire", node)
node._f_copy(output_h5.root, recursive=True)
def h5_shorten(input_filename, output_filename, options):
with open_file_safe(input_filename, mode='r') as h5:
with open_file_safe(output_filename, mode='w',
delete_on_error=True) as output_h5:
if not options.data2d_only:
do_data_association_tables(h5, output_h5, options)
for node in h5.root._f_iter_nodes():
if (hasattr(node, 'name') and node.name
in ['data2d_distorted', 'kalman_estimates']):
if options.data2d_only:
if node.name != 'data2d_distorted':
continue
print 'selectively copying', node
copy_selective(h5, node, output_h5.root, options)
elif (hasattr(node, 'name') and node.name
in ['ML_estimates', 'ML_estimates_2d_idxs']):
continue
else:
# copy everything from source to dest
print 'copying entire', node
node._f_copy(output_h5.root, recursive=True)
def kalmanize(
src_filename,
do_full_kalmanization=True,
dest_filename=None,
reconstructor=None,
reconstructor_filename=None,
start_frame=None,
stop_frame=None,
exclude_cam_ids=None,
exclude_camns=None,
dynamic_model_name=None,
debug=False,
frames_per_second=None,
area_threshold=0,
min_observations_to_save=0,
options=None,
):
if options is None:
# get default options
parser = get_parser()
(options, args) = parser.parse_args([])
if debug:
numpy.set_printoptions(precision=3, linewidth=120, suppress=False)
if exclude_cam_ids is None:
exclude_cam_ids = []
if exclude_camns is None:
exclude_camns = []
use_existing_filename = True
if reconstructor is not None:
assert isinstance(reconstructor, flydra_core.reconstruct.Reconstructor)
assert reconstructor_filename is None
with open_file_safe(src_filename, mode='r') as results:
camn2cam_id, cam_id2camns = get_caminfo_dicts(results)
if do_full_kalmanization:
if dynamic_model_name is None:
if hasattr(results.root, 'kalman_estimates'):
if hasattr(results.root.kalman_estimates.attrs,
'dynamic_model_name'):
dynamic_model_name = (results.root.kalman_estimates.
attrs.dynamic_model_name)
warnings.warn('dynamic model not specified. '
'using "%s"' % dynamic_model_name)
if dynamic_model_name is None:
dynamic_model_name = 'EKF mamarama, units: mm'
warnings.warn('dynamic model not specified. '
'using "%s"' % dynamic_model_name)
else:
print 'using dynamic model "%s"' % dynamic_model_name
if reconstructor_filename is not None:
if reconstructor_filename.endswith('h5'):
with PT.open_file(reconstructor_filename, mode='r') as fd:
reconstructor = flydra_core.reconstruct.Reconstructor(
fd,
minimum_eccentricity=options.
force_minimum_eccentricity)
else:
reconstructor = flydra_core.reconstruct.Reconstructor(
reconstructor_filename,
minimum_eccentricity=options.force_minimum_eccentricity
)
else:
# reconstructor_filename is None
if reconstructor is None:
reconstructor = flydra_core.reconstruct.Reconstructor(
results,
minimum_eccentricity=options.force_minimum_eccentricity
)
if options.force_minimum_eccentricity is not None:
if (reconstructor.minimum_eccentricity !=
options.force_minimum_eccentricity):
raise ValueError('could not force minimum_eccentricity')
if dest_filename is None:
dest_filename = os.path.splitext(
results.filename)[0] + '.kalmanized.h5'
else:
use_existing_filename = False
dest_filename = tempfile.mktemp(suffix='.h5')
if reconstructor is not None and reconstructor.cal_source_type == 'pytables':
save_reconstructor_filename = reconstructor.cal_source.filename
else:
warnings.warn('unable to determine reconstructor source '
'filename for %r' % reconstructor.cal_source_type)
save_reconstructor_filename = None
if frames_per_second is None:
frames_per_second = get_fps(results)
if do_full_kalmanization:
print 'read frames_per_second from file', frames_per_second
dt = 1.0 / frames_per_second
if options.sync_error_threshold_msec is None:
# default is IFI/2
sync_error_threshold = (0.5 * dt)
else:
sync_error_threshold = options.sync_error_threshold_msec / 1000.0
if os.path.exists(dest_filename):
if use_existing_filename:
raise ValueError('%s already exists. Will not '
'overwrite.' % dest_filename)
else:
os.unlink(dest_filename)
with open_file_safe(dest_filename,
mode="w",
title="tracked Flydra data file",
delete_on_error=True) as h5file:
if 'experiment_info' in results.root:
results.root.experiment_info._f_copy(h5file.root,
recursive=True)
if do_full_kalmanization:
parsed = read_textlog_header(results)
if 'trigger_CS3' not in parsed:
parsed['trigger_CS3'] = 'unknown'
textlog_save_lines = [
'kalmanize running at %s fps, (top %s, trigger_CS3 %s, flydra_version %s)'
% (str(frames_per_second), str(parsed.get(
'top', 'unknown')), str(parsed['trigger_CS3']),
flydra_core.version.__version__),
'original file: %s' % (src_filename, ),
'dynamic model: %s' % (dynamic_model_name, ),
'reconstructor file: %s' % (save_reconstructor_filename, ),
]
kalman_model = dynamic_models.get_kalman_model(
name=dynamic_model_name, dt=dt)
h5saver = KalmanSaver(
h5file,
reconstructor,
cam_id2camns=cam_id2camns,
min_observations_to_save=min_observations_to_save,
textlog_save_lines=textlog_save_lines,
dynamic_model_name=dynamic_model_name,
dynamic_model=kalman_model,
debug=debug,
fake_timestamp=options.fake_timestamp,
)
tracker = Tracker(
reconstructor,
kalman_model=kalman_model,
save_all_data=True,
area_threshold=area_threshold,
area_threshold_for_orientation=options.
area_threshold_for_orientation,
disable_image_stat_gating=options.
disable_image_stat_gating,
orientation_consensus=options.orientation_consensus,
fake_timestamp=options.fake_timestamp,
)
tracker.set_killed_tracker_callback(h5saver.save_tro)
# copy timestamp data into newly created kalmanized file
if hasattr(results.root, 'trigger_clock_info'):
results.root.trigger_clock_info._f_copy(h5file.root)
data2d = results.root.data2d_distorted
frame_count = 0
last_frame = None
frame_data = collections.defaultdict(list)
time_frame_all_cam_timestamps = []
time_frame_all_camns = []
if 1:
time1 = time.time()
if do_full_kalmanization:
print 'loading all frame numbers...'
frames_array = numpy.asarray(data2d.read(field='frame'))
time2 = time.time()
if do_full_kalmanization:
print 'done in %.1f sec' % (time2 - time1)
if (not options.disable_image_stat_gating
and 'cur_val' in data2d.colnames):
warnings.warn(
'No pre-filtering of data based on zero '
'probability -- more data association work is '
'being done than necessary')
if len(frames_array) == 0:
# no data
print 'No 2D data. Nothing to do.'
return
if do_full_kalmanization:
print '2D data range: approximately %d<frame<%d' % (
frames_array[0], frames_array[-1])
if do_full_kalmanization:
accum_frame_spread = None
else:
accum_frame_spread = []
accum_frame_spread_fno = []
accum_frame_all_timestamps = []
accum_frame_all_camns = []
max_all_check_times = -np.inf
for row_start, row_stop in utils.iter_non_overlapping_chunk_start_stops(
frames_array,
min_chunk_size=500000,
size_increment=1000,
status_fd=sys.stdout):
print 'Doing initial scan of approx frame range %d-%d.' % (
frames_array[row_start], frames_array[row_stop - 1])
this_frames_array = frames_array[row_start:row_stop]
if start_frame is not None:
if this_frames_array.max() < start_frame:
continue
if stop_frame is not None:
if this_frames_array.min() > stop_frame:
continue
data2d_recarray = data2d.read(start=row_start, stop=row_stop)
this_frames = data2d_recarray['frame']
print 'Examining frames %d-%d in detail.' % (this_frames[0],
this_frames[-1])
this_row_idxs = np.argsort(this_frames)
for ii in range(len(this_row_idxs) + 1):
if ii >= len(this_row_idxs):
finish_frame = True
else:
finish_frame = False
this_row_idx = this_row_idxs[ii]
row = data2d_recarray[this_row_idx]
new_frame = row['frame']
if start_frame is not None:
if new_frame < start_frame:
continue
if stop_frame is not None:
if new_frame > stop_frame:
continue
if last_frame != new_frame:
if new_frame < last_frame:
print 'new_frame', new_frame
print 'last_frame', last_frame
raise RuntimeError(
"expected continuously increasing "
"frame numbers")
finish_frame = True
if finish_frame:
# new frame
########################################
# Data for this frame is complete
if last_frame is not None:
this_frame_spread = 0.0
if len(time_frame_all_cam_timestamps) > 1:
check_times = np.array(
time_frame_all_cam_timestamps)
check_times -= check_times.min()
this_frame_spread = check_times.max()
if accum_frame_spread is not None:
accum_frame_spread.append(
this_frame_spread)
accum_frame_spread_fno.append(last_frame)
accum_frame_all_timestamps.append(
time_frame_all_cam_timestamps)
accum_frame_all_camns.append(
time_frame_all_camns)
max_all_check_times = max(
this_frame_spread, max_all_check_times)
if this_frame_spread > sync_error_threshold:
if this_frame_spread == max_all_check_times:
print '%s frame %d: sync diff: %.1f msec' % (
os.path.split(
results.filename)[-1],
last_frame,
this_frame_spread * 1000.0)
if debug > 5:
print
print 'frame_data for frame %d' % (
last_frame, )
pprint.pprint(dict(frame_data))
print
if do_full_kalmanization:
if this_frame_spread > sync_error_threshold:
if debug > 5:
print(
'frame sync error (spread %.1f msec), '
'skipping' %
(this_frame_spread * 1e3, ))
print
warnings.warn(
'Synchronization error detected, '
'but continuing analysis without '
'potentially bad data.')
else:
process_frame(reconstructor,
tracker,
last_frame,
frame_data,
camn2cam_id,
debug=debug)
frame_count += 1
if do_full_kalmanization and frame_count % 1000 == 0:
time2 = time.time()
dur = time2 - time1
fps = frame_count / dur
print 'frame % 10d, kalmanization/data association speed: % 8.1f fps' % (
last_frame, fps)
time1 = time2
frame_count = 0
########################################
frame_data = collections.defaultdict(list)
time_frame_all_cam_timestamps = [] # clear values
time_frame_all_camns = [] # clear values
last_frame = new_frame
camn = row['camn']
try:
cam_id = camn2cam_id[camn]
except KeyError:
# This will happen if cameras were re-synchronized (and
# thus gain new cam_ids) immediately before saving was
# turned on in MainBrain. The reason is that the network
# buffers are still full of old data coming in from the
# cameras.
warnings.warn('WARNING: no cam_id for camn '
'%d, skipping this row of data' % camn)
continue
if cam_id in exclude_cam_ids:
# exclude this camera
continue
if camn in exclude_camns:
# exclude this camera
continue
time_frame_all_cam_timestamps.append(row['timestamp'])
time_frame_all_camns.append(row['camn'])
if do_full_kalmanization:
x_distorted = row['x']
if numpy.isnan(x_distorted):
# drop point -- not found
continue
y_distorted = row['y']
(x_undistorted,
y_undistorted) = reconstructor.undistort(
cam_id, (x_distorted, y_distorted))
(area, slope, eccentricity,
frame_pt_idx) = (row['area'], row['slope'],
row['eccentricity'],
row['frame_pt_idx'])
if 'cur_val' in row.dtype.fields:
cur_val = row['cur_val']
else:
cur_val = None
if 'mean_val' in row.dtype.fields:
mean_val = row['mean_val']
else:
mean_val = None
if 'sumsqf_val' in row.dtype.fields:
sumsqf_val = row['sumsqf_val']
else:
sumsqf_val = None
# FIXME: cache this stuff?
pmat_inv = reconstructor.get_pmat_inv(cam_id)
camera_center = reconstructor.get_camera_center(cam_id)
camera_center = numpy.hstack((camera_center[:,
0], [1]))
camera_center_meters = reconstructor.get_camera_center(
cam_id)
camera_center_meters = numpy.hstack(
(camera_center_meters[:, 0], [1]))
helper = reconstructor.get_reconstruct_helper_dict(
)[cam_id]
rise = slope
run = 1.0
if np.isinf(rise):
if rise > 0:
rise = 1.0
run = 0.0
else:
rise = -1.0
run = 0.0
(p1, p2, p3, p4, ray0, ray1, ray2, ray3, ray4,
ray5) = do_3d_operations_on_2d_point(
helper, x_undistorted, y_undistorted, pmat_inv,
camera_center, x_distorted, y_distorted, rise,
run)
line_found = not numpy.isnan(p1)
pluecker_hz_meters = (ray0, ray1, ray2, ray3, ray4,
ray5)
# Keep in sync with kalmanize.py and data_descriptions.py
pt_undistorted = (x_undistorted, y_undistorted, area,
slope, eccentricity, p1, p2, p3, p4,
line_found, frame_pt_idx, cur_val,
mean_val, sumsqf_val)
projected_line_meters = geom.line_from_HZline(
pluecker_hz_meters)
frame_data[camn].append(
(pt_undistorted, projected_line_meters))
if do_full_kalmanization:
tracker.kill_all_trackers() # done tracking
if not do_full_kalmanization:
os.unlink(dest_filename)
if accum_frame_spread is not None:
# save spread data to file for analysis
accum_frame_spread = np.array(accum_frame_spread)
accum_frame_spread_fno = np.array(accum_frame_spread_fno)
if options.dest_file is not None:
accum_frame_spread_filename = options.dest_file
else:
accum_frame_spread_filename = src_filename + '.spreadh5'
cam_ids = cam_id2camns.keys()
cam_ids.sort()
camn_order = []
for cam_id in cam_ids:
camn_order.extend(cam_id2camns[cam_id])
camn_order = np.array(camn_order)
cam_id_array = np.array(cam_ids)
N_cams = len(camn_order)
N_frames = len(accum_frame_spread_fno)
all_timestamps = np.empty((N_frames, N_cams), dtype=np.float)
all_timestamps.fill(np.nan)
for i, (timestamps, camns) in enumerate(
zip(accum_frame_all_timestamps, accum_frame_all_camns)):
for j, camn in enumerate(camn_order):
try:
idx = camns.index(camn)
except ValueError:
continue # not found, skip
timestamp = timestamps[idx]
all_timestamps[i, j] = timestamp
h5 = tables.open_file(accum_frame_spread_filename, mode='w')
h5.create_array(h5.root, 'spread', accum_frame_spread,
'frame timestamp spreads (sec)')
h5.create_array(h5.root, 'framenumber', accum_frame_spread_fno,
'frame number')
h5.create_array(h5.root, 'all_timestamps', all_timestamps,
'all timestamps')
h5.create_array(h5.root, 'camn_order', camn_order, 'camn_order')
h5.create_array(h5.root, 'cam_id_array', cam_id_array, 'cam_id_array')
h5.close()
print 'saved %s' % accum_frame_spread_filename
if max_all_check_times > sync_error_threshold:
if not options.keep_sync_errors:
if do_full_kalmanization:
print 'max_all_check_times %.2f msec' % (max_all_check_times *
1000.0)
handle, target = tempfile.mkstemp(
os.path.split(dest_filename)[1])
os.unlink(target) # remove original file there
shutil.move(dest_filename, target)
raise ValueError(
'Synchonization errors exist in the data. Moved result file'
' to ensure it is not confused with valid data. The new '
'location is: %s' % (target, ))
else:
sys.exit(1) # sync error
else:
if not do_full_kalmanization:
print '%s no sync differences greater than %.1f msec' % (
os.path.split(src_filename)[-1],
sync_error_threshold * 1000.0,
)
def retrack_reuse_data_association(
h5_filename=None,
output_h5_filename=None,
kalman_filename=None,
start=None,
stop=None,
less_ram=False,
show_progress=False,
show_progress_json=False,
):
if os.path.exists(output_h5_filename):
raise RuntimeError("will not overwrite old file '%s'" %
output_h5_filename)
ca = core_analysis.get_global_CachingAnalyzer()
with ca.kalman_analysis_context(kalman_filename,
data2d_fname=h5_filename) as h5_context:
R = h5_context.get_reconstructor()
if less_ram:
ML_estimates_2d_idxs = h5_context.get_pytable_node(
'ML_estimates_2d_idxs')
else:
ML_estimates_2d_idxs = h5_context.load_entire_table(
'ML_estimates_2d_idxs')
use_obj_ids = h5_context.get_unique_obj_ids()
extra = h5_context.get_extra_info()
dt = 1.0 / extra['frames_per_second']
dynamic_model_name = extra['dynamic_model_name']
kalman_model = dynamic_models.get_kalman_model(name=dynamic_model_name,
dt=dt)
kalman_model['max_frames_skipped'] = 2**62 # close to max i64
fps = extra['frames_per_second']
camn2cam_id, cam_id2camns = h5_context.get_caminfo_dicts()
parsed = h5_context.read_textlog_header()
if 'trigger_CS3' not in parsed:
parsed['trigger_CS3'] = 'unknown'
textlog_save_lines = [
'retrack_reuse_data_association running at %s fps, (top %s, trigger_CS3 %s, flydra_version %s)'
%
(str(fps), str(parsed.get('top', 'unknown')),
str(parsed['trigger_CS3']), flydra_analysis.version.__version__),
'original file: %s' % (kalman_filename, ),
'dynamic model: %s' % (dynamic_model_name, ),
'reconstructor file: %s' % (kalman_filename, ),
]
with open_file_safe(output_h5_filename,
mode="w",
title="tracked Flydra data file",
delete_on_error=True) as output_h5:
h5saver = KalmanSaver(
output_h5,
R,
cam_id2camns=cam_id2camns,
min_observations_to_save=0,
textlog_save_lines=textlog_save_lines,
dynamic_model_name=dynamic_model_name,
dynamic_model=kalman_model,
)
# associate framenumbers with timestamps using 2d .h5 file
if less_ram:
data2d = h5_context.get_pytable_node('data2d_distorted',
from_2d_file=True)
h5_framenumbers = data2d.cols.frame[:]
else:
data2d = h5_context.load_entire_table('data2d_distorted',
from_2d_file=True)
h5_framenumbers = data2d['frame']
h5_frame_qfi = result_utils.QuickFrameIndexer(h5_framenumbers)
if show_progress:
string_widget = StringWidget()
objs_per_sec_widget = progressbar.FileTransferSpeed(
unit='obj_ids ')
widgets = [
string_widget, objs_per_sec_widget,
progressbar.Percentage(),
progressbar.Bar(),
progressbar.ETA()
]
pbar = progressbar.ProgressBar(
widgets=widgets, maxval=len(use_obj_ids)).start()
for obj_id_enum, obj_id in enumerate(use_obj_ids):
if show_progress:
string_widget.set_string('[obj_id: % 5d]' % obj_id)
pbar.update(obj_id_enum)
if show_progress_json and obj_id_enum % 100 == 0:
rough_percent_done = float(obj_id_enum) / len(
use_obj_ids) * 100.0
result_utils.do_json_progress(rough_percent_done)
tro = None
first_frame_per_obj = True
obj_3d_rows = h5_context.load_dynamics_free_MLE_position(
obj_id)
for this_3d_row in obj_3d_rows:
# iterate over each sample in the current camera
framenumber = this_3d_row['frame']
if start is not None:
if not framenumber >= start:
continue
if stop is not None:
if not framenumber <= stop:
continue
h5_2d_row_idxs = h5_frame_qfi.get_frame_idxs(framenumber)
if len(h5_2d_row_idxs) == 0:
# At the start, there may be 3d data without 2d data.
continue
# If there was a 3D ML estimate, there must be 2D data.
frame2d = data2d[h5_2d_row_idxs]
obs_2d_idx = this_3d_row['obs_2d_idx']
kobs_2d_data = ML_estimates_2d_idxs[int(obs_2d_idx)]
# Parse VLArray.
this_camns = kobs_2d_data[0::2]
this_camn_idxs = kobs_2d_data[1::2]
# Now, for each camera viewing this object at this
# frame, extract images.
observation_camns = []
observation_idxs = []
data_dict = {}
used_camns_and_idxs = []
cam_ids_and_points2d = []
for camn, frame_pt_idx in zip(this_camns, this_camn_idxs):
try:
cam_id = camn2cam_id[camn]
except KeyError:
warnings.warn('camn %d not found' % (camn, ))
continue
# find 2D point corresponding to object
cond = ((frame2d['camn'] == camn) &
(frame2d['frame_pt_idx'] == frame_pt_idx))
idxs = np.nonzero(cond)[0]
if len(idxs) == 0:
#no frame for that camera (start or stop of file)
continue
elif len(idxs) > 1:
print "MEGA WARNING MULTIPLE 2D POINTS\n", camn, frame_pt_idx, "\n\n"
continue
idx = idxs[0]
frame2d_row = frame2d[idx]
x2d_real = frame2d_row['x'], frame2d_row['y']
pt_undistorted = R.undistort(cam_id, x2d_real)
x2d_area = frame2d_row['area']
observation_camns.append(camn)
observation_idxs.append(idx)
candidate_point_list = []
data_dict[camn] = candidate_point_list
used_camns_and_idxs.append((camn, frame_pt_idx, None))
# with no orientation
observed_2d = (pt_undistorted[0], pt_undistorted[1],
x2d_area)
cam_ids_and_points2d.append((cam_id, observed_2d))
if first_frame_per_obj:
if len(cam_ids_and_points2d) < 2:
warnings.warn(
'some 2D data seems to be missing, cannot completely reconstruct'
)
else:
X3d = R.find3d(
cam_ids_and_points2d,
return_line_coords=False,
simulate_via_tracking_dynamic_model=kalman_model
)
# first frame
tro = TrackedObject(
R,
obj_id,
framenumber,
X3d, # obs0_position
None, # obs0_Lcoords
observation_camns, # first_observation_camns
observation_idxs, # first_observation_idxs
kalman_model=kalman_model,
)
del X3d
first_frame_per_obj = False
else:
tro.calculate_a_posteriori_estimate(
framenumber,
data_dict,
camn2cam_id,
skip_data_association=True,
original_camns_and_idxs=used_camns_and_idxs,
original_cam_ids_and_points2d=cam_ids_and_points2d,
)
# done with all data for this obj_id
if tro is not None:
tro.kill()
h5saver.save_tro(tro, force_obj_id=obj_id)
if show_progress_json:
result_utils.do_json_progress(100)
if not os.path.isdir(data_src):
braidz = ".braidz"
assert data_src.endswith(braidz)
zipname = data_src
data_dir = tempfile.mkdtemp(suffix=".braid")
archive = zipfile.ZipFile(zipname, mode="r")
archive.extractall(data_dir)
unconverted_output_dir = os.path.join(data_src[:-len(braidz)]+'.unconverted')
also_delete_braidz = data_src
else:
data_dir = data_src
unconverted_output_dir = os.path.join(data_src+'.unconverted')
delete_original = not args.no_delete
with open_file_safe(
dest_filename, mode="w", title="tracked Flydra data file", delete_on_error=True
) as h5file:
do_2d_only = vars(args)["2d_only"]
kest_csv_fname = os.path.join(data_dir, "kalman_estimates.csv")
kest_csv_gz_fname = os.path.join(data_dir, "kalman_estimates.csv.gz")
if not (os.path.exists(kest_csv_fname) or os.path.exists(kest_csv_gz_fname)):
do_2d_only = True
if do_2d_only:
print("converting 2D data only")
else:
convert_program = "compute-flydra1-compat"
if not os.path.exists(computed_dir(data_dir)):
cmd = [convert_program, "--help"]
