def setupOutputs(self):
self.Predictions.meta.shape = self.Features.meta.shape
self.Predictions.meta.dtype = object
self.Predictions.meta.axistags = None
self.Predictions.meta.mapping_dtype = numpy.uint8
self.Probabilities.meta.shape = self.Features.meta.shape
self.Probabilities.meta.dtype = object
self.Probabilities.meta.mapping_dtype = numpy.float32
self.Probabilities.meta.axistags = None
self.BadObjects.meta.shape = self.Features.meta.shape
self.BadObjects.meta.dtype = object
self.BadObjects.meta.mapping_dtype = numpy.uint8
self.BadObjects.meta.axistags = None
if self.LabelsCount.ready():
nlabels = self.LabelsCount[:].wait()
nlabels = int(nlabels[0])
self.ProbabilityChannels.resize(nlabels)
for oslot in self.ProbabilityChannels:
oslot.meta.shape = self.Features.meta.shape
oslot.meta.dtype = object
oslot.meta.axistags = None
oslot.meta.mapping_dtype = numpy.float32
self.lock = RequestLock()
self.prob_cache = dict()
self.bad_objects = dict()
def test_RequestLock():
assert Request.global_thread_pool.num_workers > 0, \
"This test must be used with the real threadpool."
lockA = RequestLock()
lockB = RequestLock()
def log_request_system_status():
status = (
"*************************\n" +
'lockA.pending: {}\n'.format(len(lockA._pendingRequests)) +
'lockB.pending: {}\n'.format(len(lockB._pendingRequests))
#+ "suspended Requests: {}\n".format( len(Request.global_suspend_set) )
+ "global job queue: {}\n".format(
len(Request.global_thread_pool.unassigned_tasks)))
for worker in Request.global_thread_pool.workers:
status += "{} queued tasks: {}\n".format(worker.name,
len(worker.job_queue))
status += "*****************************************************"
logger.debug(status)
running = [True]
def periodic_status():
while running[0]:
time.sleep(0.5)
log_request_system_status()
# Uncomment these lines to print periodic status while the test runs...
status_thread = threading.Thread(target=periodic_status)
status_thread.daemon = True
status_thread.start()
try:
_impl_test_lock(lockA, lockB, Request, 1000)
except:
log_request_system_status()
running[0] = False
status_thread.join()
global paused
paused = False
Request.reset_thread_pool(Request.global_thread_pool.num_workers)
if lockA.locked():
lockA.release()
if lockB.locked():
lockB.release()
raise
log_request_system_status()
running[0] = False
status_thread.join()
def __init__(self, *args, **kwargs):
super(OpFeatureMatrixCache, self).__init__(*args, **kwargs)
self._lock = RequestLock()
self.progressSignal = OrderedSignal()
self._progress_lock = RequestLock()
self._blockshape = None
self._dirty_blocks = set()
self._blockwise_feature_matrices = {}
self._block_locks = {} # One lock per stored block
self._init_blocks(None, None)
def __init__(self, *args, **kwargs):
super(OpFeatureMatrixCache, self).__init__(*args, **kwargs)
self._blockshape = None
self._lock = RequestLock()
self.progressSignal = OrderedSignal()
self._progress_lock = RequestLock()
# In these set/dict members, the block id (dict key)
# is simply the block's start coordinate (as a tuple)
self._blockwise_feature_matrices = {}
self._dirty_blocks = set()
self._block_locks = {} # One lock per stored block
def __init__(self, *args, **kwargs):
super(OpPatchCreator, self).__init__(*args, **kwargs)
self.patches = None
self.posns = None
self.lock = RequestLock()
self.opGrid = opGridCreator.OpGridCreator(graph=Graph())
self.GridOutput.connect(self.opGrid.Output)
self.opGrid.GridStartVertical.connect(self.GridStartVertical)
self.opGrid.GridStartHorizontal.connect(self.GridStartHorizontal)
self.opGrid.GridWidth.connect(self.GridWidth)
self.opGrid.GridHeight.connect(self.GridHeight)
self.opGrid.PatchWidth.connect(self.PatchWidth)
self.opGrid.PatchHeight.connect(self.PatchHeight)
def __init__(self, *args, **kwargs):
super(OpCompressedCache, self).__init__(*args, **kwargs)
self._blockshape = None
self._cacheFiles = {}
self._dirtyBlocks = set()
self._lock = RequestLock()
self._blockLocks = {}
def __init__(self, *args, **kwargs):
super(OpUnblockedArrayCache, self).__init__(*args, **kwargs)
self._lock = RequestLock()
self._resetBlocks()
# Now that we're initialized, it's safe to register with the memory manager
self.registerWithMemoryManager()
def setupOutputs(self):
self.Predictions.meta.shape = self.Features.meta.shape
self.Predictions.meta.dtype = object
self.Predictions.meta.axistags = None
self.Predictions.meta.mapping_dtype = numpy.uint8
self.Probabilities.meta.shape = self.Features.meta.shape
self.Probabilities.meta.dtype = object
self.Probabilities.meta.mapping_dtype = numpy.float32
self.Probabilities.meta.axistags = None
self.BadObjects.meta.shape = self.Features.meta.shape
self.BadObjects.meta.dtype = object
self.BadObjects.meta.mapping_dtype = numpy.uint8
self.BadObjects.meta.axistags = None
if self.LabelsCount.ready():
nlabels = self.LabelsCount[:].wait()
nlabels = int(nlabels[0])
self.ProbabilityChannels.resize(nlabels)
for oslot in self.ProbabilityChannels:
oslot.meta.shape = self.Features.meta.shape
oslot.meta.dtype = object
oslot.meta.axistags = None
oslot.meta.mapping_dtype = numpy.float32
self.lock = RequestLock()
self.prob_cache = dict()
self.bad_objects = dict()
def __init__(self, *args, **kwargs):
super(OpUnmanagedCompressedCache, self).__init__(*args, **kwargs)
self._lock = RequestLock()
self._init_cache(None)
self._block_id_counter = itertools.count(
) # Used to ensure unique in-memory file names
self._ignore_ideal_blockshape = False
def predict_probabilities(self, X):
logger.debug( "Predicting with parallel vigra RF" )
X = numpy.asarray(X, dtype=numpy.float32)
# As each forest completes, aggregate results in a shared array.
# (Must put in a list so we can update it in this closure.)
total_predictions = [None]
prediction_lock = RequestLock()
def update_predictions(forest, forest_predictions):
forest_predictions *= forest.treeCount()
with prediction_lock:
if total_predictions[0] is None:
total_predictions[0] = forest_predictions
else:
total_predictions[0] += forest_predictions
# Create a request for each forest
pool = RequestPool()
for forest in self._forests:
req = Request( partial( forest.predictProbabilities, X ) )
req.notify_finished( partial(update_predictions, forest) )
pool.add( req )
del req
pool.wait()
total_predictions[0] /= self._num_trees
return total_predictions[0]
def predict_probabilities(self, X):
logger.debug("Predicting with parallel vigra RF")
X = numpy.asarray(X, dtype=numpy.float32)
assert X.ndim == 2
if self._feature_names is not None:
# For some reason, vigra doesn't seem to check this for us...
assert X.shape[1] == len(self._feature_names), \
"Feature count doesn't match the training data."
# As each forest completes, aggregate results in a shared array.
# (Must put in a list so we can update it in this closure.)
total_predictions = [None]
prediction_lock = RequestLock()
def update_predictions(forest, forest_predictions):
forest_predictions *= forest.treeCount()
with prediction_lock:
if total_predictions[0] is None:
total_predictions[0] = forest_predictions
else:
total_predictions[0] += forest_predictions
# Create a request for each forest
pool = RequestPool()
for forest in self._forests:
req = Request(partial(forest.predictProbabilities, X))
req.notify_finished(partial(update_predictions, forest))
pool.add(req)
del req
pool.wait()
total_predictions[0] /= self._num_trees
return total_predictions[0]
def _update_block(self, block_start):
if block_start not in self._block_locks:
with self._lock:
if block_start not in self._block_locks:
self._block_locks[block_start] = RequestLock()
with self._block_locks[block_start]:
if block_start not in self._dirty_blocks:
# Nothing to do if this block isn't actually dirty
# (For parallel requests, its theoretically possible.)
return
block_roi = getBlockBounds(self.LabelImage.meta.shape,
self._blockshape, block_start)
# TODO: Shrink the requested roi using the nonzero blocks slot...
# ...or just get rid of the nonzero blocks slot...
labels_and_features_matrix = self._extract_feature_matrix(
block_roi)
with self._lock:
self._dirty_blocks.remove(block_start)
if labels_and_features_matrix.shape[0] > 0:
self._blockwise_feature_matrices[
block_start] = labels_and_features_matrix
else:
try:
del self._blockwise_feature_matrices[block_start]
except KeyError:
pass
def _fetch_and_store_block(self, block_roi, out):
if out is not None:
roi_shape = numpy.array(block_roi[1]) - block_roi[0]
assert (out.shape == roi_shape).all()
# Get lock for this block (create first if necessary)
with self._lock:
if block_roi not in self._block_locks:
self._block_locks[block_roi] = RequestLock()
block_lock = self._block_locks[block_roi]
# Handle identical simultaneous requests for the same block
# without preventing parallel requests for different blocks.
with block_lock:
if block_roi in self._block_data:
if out is None:
# Extra [:] here is in case we are decompressing from a chunkedarray
return self._block_data[block_roi][:]
else:
# Extra [:] here is in case we are decompressing from a chunkedarray
self.Output.stype.copy_data(out,
self._block_data[block_roi][:])
return out
req = self.Input(*block_roi)
if out is not None:
req.writeInto(out)
block_data = req.wait()
self._store_block_data(block_roi, block_data)
return block_data
def test_RequestLock():
assert Request.global_thread_pool.num_workers > 0, "This test must be used with the real threadpool."
lockA = RequestLock()
lockB = RequestLock()
def log_request_system_status():
status = (
"*************************\n"
+ "lockA.pending: {}\n".format(len(lockA._pendingRequests))
+ "lockB.pending: {}\n".format(len(lockB._pendingRequests))
# + "suspended Requests: {}\n".format( len(Request.global_suspend_set) )
+ "global job queue: {}\n".format(len(Request.global_thread_pool.unassigned_tasks))
)
for worker in Request.global_thread_pool.workers:
status += "{} queued tasks: {}\n".format(worker.name, len(worker.job_queue))
status += "*****************************************************"
logger.debug(status)
running = [True]
def periodic_status():
while running[0]:
time.sleep(0.5)
log_request_system_status()
# Uncomment these lines to print periodic status while the test runs...
status_thread = threading.Thread(target=periodic_status)
status_thread.daemon = True
status_thread.start()
try:
_impl_test_lock(lockA, lockB, Request, 1000)
except:
log_request_system_status()
running[0] = False
status_thread.join()
global paused
paused = False
Request.reset_thread_pool(Request.global_thread_pool.num_workers)
if lockA.locked():
lockA.release()
if lockB.locked():
lockB.release()
raise
log_request_system_status()
running[0] = False
status_thread.join()
def setInSlot(self, slot, subindex, roi, block_data):
assert slot == self.Input
block_roi = (tuple(roi.start), tuple(roi.stop))
with self._lock:
if block_roi not in self._block_locks:
self._block_locks[block_roi] = RequestLock()
block_lock = self._block_locks[block_roi]
with block_lock:
self._store_block_data(block_roi, block_data)
def test_cancellation_behavior():
"""
If a request is cancelled while it was waiting on a lock,
it should raise the CancellationException.
"""
lock = RequestLock()
lock.acquire()
def f():
try:
with lock:
assert False
except Request.CancellationException:
pass
else:
assert False
finished = [False]
cancelled = [False]
failed = [False]
def handle_finished(result):
finished[0] = True
def handle_cancelled():
cancelled[0] = True
def handle_failed(*args):
failed[0] = True
req = Request(f)
req.notify_finished(handle_finished)
req.notify_failed(handle_failed)
req.notify_cancelled(handle_cancelled)
req.submit()
req.cancel()
time.sleep(0.1)
lock.release()
time.sleep(0.1)
assert not finished[0] and not failed[0] and cancelled[0]
def _getCacheFile(self, entire_block_roi):
"""
Get the cache file for the block that starts at block_start.
If it doesn't exist yet, create it first.
"""
block_start = tuple(entire_block_roi[0])
if block_start in self._cacheFiles:
return self._cacheFiles[block_start]
with self._lock:
if block_start not in self._cacheFiles:
# Create an in-memory hdf5 file with a unique name
# (the counter ensures that even blocks that have been deleted previously get a unique name when they are re-created).
logger.debug("Creating a cache file for block: {}".format(
list(block_start)))
filename = str(id(self)) + str(id(
self._cacheFiles)) + str(block_start) + str(
self._block_id_counter.next())
mem_file = h5py.File(filename,
driver='core',
backing_store=False,
mode='w')
# h5py will crash if the chunkshape is larger than the dataset shape.
datashape = tuple(entire_block_roi[1] - entire_block_roi[0])
chunkshape = numpy.minimum(numpy.array(datashape),
self._chunkshape)
chunkshape = tuple(chunkshape)
# Make a compressed dataset
mem_file.create_dataset(
'data',
shape=datashape,
dtype=self.Output.meta.dtype,
chunks=chunkshape,
compression='lzf') # lzf should be faster than gzip,
# with a slightly worse compression ratio
# Add mask information if needed.
if self.Output.meta.has_mask:
mem_file.create_dataset(
'mask',
shape=datashape,
dtype=bool,
chunks=chunkshape,
compression='lzf') # lzf should be faster than gzip,
# with a slightly worse compression ratio
mem_file.create_dataset('fill_value',
shape=tuple(),
dtype=self.Output.meta.dtype)
self._blockLocks[block_start] = RequestLock()
self._cacheFiles[block_start] = mem_file
self._dirtyBlocks.add(block_start)
return self._cacheFiles[block_start]
class OpGridCreator(Operator):
"""Creates list of patches from all filter responses."""
PatchWidth = InputSlot() # width of patch in pixel
PatchHeight = InputSlot() # height of patch in pixel
GridStartVertical = InputSlot() # Vertical - start of patch grid in pixel
GridStartHorizontal = InputSlot(
) # Horizontal - start of patch grid in pixel
GridWidth = InputSlot() # width of patch grid in pixel
GridHeight = InputSlot() # height of patch grid in pixel
ImageWidth = InputSlot() # width of raw image
ImageHeight = InputSlot() # height of raw image
Output = OutputSlot() # number of patches in x/y-direction
def __init__(self, *args, **kwargs):
super(OpGridCreator, self).__init__(*args, **kwargs)
self.gridArray = None
self.lock = RequestLock()
def setupOutputs(self):
self.Output.meta.shape = (self.ImageWidth.value,
self.ImageHeight.value)
# the viewer uses a different coordinate system
self.Output.meta.axistags = vigra.defaultAxistags('yx')
self.Output.meta.dtype = numpy.uint8
def execute(self, slot, subindex, roi, result):
"""create grid"""
try:
self.lock.acquire()
if self.gridArray is None:
shape = (self.ImageHeight.value, self.ImageWidth.value)
patch = (self.PatchHeight.value, self.PatchWidth.value)
offset = (self.GridStartVertical.value,
self.GridStartHorizontal.value)
grid = (self.GridHeight.value, self.GridWidth.value)
self.gridArray = make_grid(shape, patch, grid, offset)
return self.gridArray[roi.toSlice()]
finally:
self.lock.release()
def propagateDirty(self, slot, subindex, roi):
try:
self.lock.acquire()
self.gridArray = None
self.Output.setDirty(slice(None))
finally:
self.lock.release()
class OpGridCreator(Operator):
"""Creates list of patches from all filter responses."""
PatchWidth = InputSlot() # width of patch in pixel
PatchHeight = InputSlot() # height of patch in pixel
GridStartVertical = InputSlot() # Vertical - start of patch grid in pixel
GridStartHorizontal = InputSlot() # Horizontal - start of patch grid in pixel
GridWidth = InputSlot() # width of patch grid in pixel
GridHeight = InputSlot() # height of patch grid in pixel
ImageWidth = InputSlot() # width of raw image
ImageHeight = InputSlot() # height of raw image
Output = OutputSlot() # number of patches in x/y-direction
def __init__(self, *args, **kwargs):
super(OpGridCreator, self).__init__(*args, **kwargs)
self.gridArray = None
self.lock = RequestLock()
def setupOutputs(self):
self.Output.meta.shape = (self.ImageWidth.value, self.ImageHeight.value)
# the viewer uses a different coordinate system
self.Output.meta.axistags = vigra.defaultAxistags('yx')
self.Output.meta.dtype = numpy.uint8
def execute(self, slot, subindex, roi, result):
"""create grid"""
try:
self.lock.acquire()
if self.gridArray is None:
shape = (self.ImageHeight.value, self.ImageWidth.value)
patch = (self.PatchHeight.value, self.PatchWidth.value)
offset = (self.GridStartVertical.value, self.GridStartHorizontal.value)
grid = (self.GridHeight.value, self.GridWidth.value)
self.gridArray = make_grid(shape, patch, grid, offset)
return self.gridArray[roi.toSlice()]
finally:
self.lock.release()
def propagateDirty(self, slot, subindex, roi):
try:
self.lock.acquire()
self.gridArray = None
self.Output.setDirty(slice(None))
finally:
self.lock.release()
def execute(self, slot, subindex, roi, result):
with self._lock:
# Does this roi happen to fit ENTIRELY within an existing stored block?
outer_rois = containing_rois(self._block_data.keys(),
(roi.start, roi.stop))
if len(outer_rois) > 0:
# Use the first one we found
block_roi = self._standardize_roi(*outer_rois[0])
block_relative_roi = numpy.array(
(roi.start, roi.stop)) - block_roi[0]
self.Output.stype.copy_data(
result, self._block_data[block_roi][roiToSlice(
*block_relative_roi)])
return
# Standardize roi for usage as dict key
block_roi = self._standardize_roi(roi.start, roi.stop)
# Get lock for this block (create first if necessary)
with self._lock:
if block_roi not in self._block_locks:
self._block_locks[block_roi] = RequestLock()
block_lock = self._block_locks[block_roi]
# Handle identical simultaneous requests
with block_lock:
try:
self.Output.stype.copy_data(result,
self._block_data[block_roi])
return
except KeyError: # Not yet stored: Request it now.
# We attach a special attribute to the array to allow the upstream operator
# to optionally tell us not to bother caching the data.
self.Input(roi.start, roi.stop).writeInto(result).block()
if self.Input.meta.dontcache:
# The upstream operator says not to bother caching the data.
# (For example, see OpCacheFixer.)
return
block = result.copy()
with self._lock:
# Store the data.
# First double-check that the block wasn't removed from the
# cache while we were requesting it.
# (Could have happened via propagateDirty() or eventually the arrayCacheMemoryMgr)
if block_roi in self._block_locks:
self._block_data[block_roi] = block
self._last_access_times[block_roi] = time.time()
def __init__(self, *args, **kwargs):
super(OpPatchCreator, self).__init__(*args, **kwargs)
self.patches = None
self.posns = None
self.lock = RequestLock()
self.opGrid = opGridCreator.OpGridCreator(graph=Graph())
self.GridOutput.connect(self.opGrid.Output)
self.opGrid.GridStartVertical.connect(self.GridStartVertical)
self.opGrid.GridStartHorizontal.connect(self.GridStartHorizontal)
self.opGrid.GridWidth.connect(self.GridWidth)
self.opGrid.GridHeight.connect(self.GridHeight)
self.opGrid.PatchWidth.connect(self.PatchWidth)
self.opGrid.PatchHeight.connect(self.PatchHeight)
def execute(self, slot, subindex, roi, result):
assert slot == self.ConcatenatedOutput
self.progressSignal(0.0)
num_dirty_slots = len(self._dirty_slots)
subtask_progress = {}
progress_lock = RequestLock()
def forward_progress_updates(feature_slot, progress):
with progress_lock:
subtask_progress[feature_slot] = progress
total_progress = 0.95 * sum(
subtask_progress.values()) / num_dirty_slots
self.progressSignal(total_progress)
logger.debug( "Updating features for {} dirty images out of {}"\
"".format( len(self._dirty_slots), len(self.FeatureMatrices) ) )
pool = RequestPool()
subresults = []
for feature_slot, progress_slot in zip(self.FeatureMatrices,
self.ProgressSignals):
subresults.append([None])
req = feature_slot[:]
req.writeInto(subresults[-1])
# Only use progress for slots that were dirty.
# The others are going to be really fast.
if feature_slot in self._dirty_slots:
sub_progress_signal = progress_slot.value
sub_progress_signal.subscribe(
partial(forward_progress_updates, feature_slot))
pool.add(req)
pool.wait()
# Reset dirty slots
self._dirty_slots = set()
# Since the subresults are returned in 'value' slots,
# we have to unpack them from their single-element lists.
subresult_list = list(itertools.chain(*subresults))
total_matrix = numpy.concatenate(subresult_list, axis=0)
self.progressSignal(100.0)
result[0] = total_matrix
def _getCacheFile(self, entire_block_roi):
"""
Get the cache file for the block that starts at block_start.
If it doesn't exist yet, create it first.
"""
block_start = tuple(entire_block_roi[0])
if block_start in self._cacheFiles:
return self._cacheFiles[block_start]
with self._lock:
if block_start not in self._cacheFiles:
# Create an in-memory hdf5 file with a unique name
logger.debug("Creating a cache file for block: {}".format(
list(block_start)))
filename = str(id(self)) + str(id(
self._cacheFiles)) + str(block_start)
mem_file = h5py.File(filename,
driver='core',
backing_store=False,
mode='w')
# h5py will crash if the chunkshape is larger than the dataset shape.
datashape = tuple(entire_block_roi[1] - entire_block_roi[0])
chunkshape = numpy.minimum(numpy.array(datashape),
self._chunkshape)
chunkshape = tuple(chunkshape)
# Make a compressed dataset
mem_file.create_dataset(
'data',
shape=datashape,
dtype=self.Output.meta.dtype,
chunks=chunkshape,
compression='lzf') # lzf should be faster than gzip,
# with a slightly worse compression ratio
self._blockLocks[block_start] = RequestLock()
self._cacheFiles[block_start] = mem_file
self._dirtyBlocks.add(block_start)
return self._cacheFiles[block_start]
def execute(self, slot, subindex, roi, result):
with self._lock:
# Does this roi happen to fit ENTIRELY within an existing stored block?
outer_rois = containing_rois( self._block_data.keys(), (roi.start, roi.stop) )
if len(outer_rois) > 0:
# Use the first one we found
block_roi = self._standardize_roi( *outer_rois[0] )
block_relative_roi = numpy.array( (roi.start, roi.stop) ) - block_roi[0]
result[:] = self._block_data[block_roi][ roiToSlice(*block_relative_roi) ]
return
# Standardize roi for usage as dict key
block_roi = self._standardize_roi( roi.start, roi.stop )
# Get lock for this block (create first if necessary)
with self._lock:
if block_roi not in self._block_locks:
self._block_locks[block_roi] = RequestLock()
block_lock = self._block_locks[block_roi]
# Handle identical simultaneous requests
with block_lock:
try:
result[:] = self._block_data[block_roi]
return
except KeyError:
# Not yet stored: Request it now.
self.Input(roi.start, roi.stop).writeInto(result).block()
block = result.copy()
with self._lock:
# Store the data.
# First double-check that the block wasn't removed from the
# cache while we were requesting it.
# (Could have happened via propagateDirty() or eventually the arrayCacheMemoryMgr)
if block_roi in self._block_locks:
self._block_data[block_roi] = block
def test_cancellation_behavior():
"""
If a request is cancelled while it was waiting on a lock,
it should raise the CancellationException.
"""
lock = RequestLock()
lock.acquire()
def f():
try:
with lock:
assert False
except Request.CancellationException:
pass
else:
assert False
finished = [False]
cancelled = [False]
failed = [False]
def handle_finished(result):
finished[0] = True
def handle_cancelled():
cancelled[0] = True
def handle_failed(*args):
failed[0] = True
req = Request(f)
req.notify_finished(handle_finished)
req.notify_failed(handle_failed)
req.notify_cancelled(handle_cancelled)
req.submit()
req.cancel()
time.sleep(0.1)
lock.release()
time.sleep(0.1)
assert not finished[0] and not failed[0] and cancelled[0]
def __init__(self, *args, **kwargs):
super(OpGridCreator, self).__init__(*args, **kwargs)
self.gridArray = None
self.lock = RequestLock()
class OpObjectPredict(Operator):
"""Predicts object labels in a single image.
Performs prediction on all objects in a time slice at once, and
caches the result.
"""
# WARNING: right now we predict and cache a whole time slice. We
# expect this to be fast because there are relatively few objects
# compared to the number of pixels in pixel classification. If
# this should be too slow, we should instead cache at the object
# level, and only predict for objects visible in the roi.
name = "OpObjectPredict"
Features = InputSlot(rtype=List, stype=Opaque)
SelectedFeatures = InputSlot(rtype=List, stype=Opaque)
Classifier = InputSlot()
LabelsCount = InputSlot(stype='integer')
InputProbabilities = InputSlot(stype=Opaque, rtype=List, optional=True)
Predictions = OutputSlot(stype=Opaque, rtype=List)
Probabilities = OutputSlot(stype=Opaque, rtype=List)
CachedProbabilities = OutputSlot(stype=Opaque, rtype=List)
ProbabilityChannels = OutputSlot(stype=Opaque, rtype=List, level=1)
BadObjects = OutputSlot(stype=Opaque, rtype=List)
#SegmentationThreshold = 0.5
def setupOutputs(self):
self.Predictions.meta.shape = self.Features.meta.shape
self.Predictions.meta.dtype = object
self.Predictions.meta.axistags = None
self.Predictions.meta.mapping_dtype = numpy.uint8
self.Probabilities.meta.shape = self.Features.meta.shape
self.Probabilities.meta.dtype = object
self.Probabilities.meta.mapping_dtype = numpy.float32
self.Probabilities.meta.axistags = None
self.BadObjects.meta.shape = self.Features.meta.shape
self.BadObjects.meta.dtype = object
self.BadObjects.meta.mapping_dtype = numpy.uint8
self.BadObjects.meta.axistags = None
if self.LabelsCount.ready():
nlabels = self.LabelsCount[:].wait()
nlabels = int(nlabels[0])
self.ProbabilityChannels.resize(nlabels)
for oslot in self.ProbabilityChannels:
oslot.meta.shape = self.Features.meta.shape
oslot.meta.dtype = object
oslot.meta.axistags = None
oslot.meta.mapping_dtype = numpy.float32
self.lock = RequestLock()
self.prob_cache = dict()
self.bad_objects = dict()
def execute(self, slot, subindex, roi, result):
assert slot in [self.Predictions,
self.Probabilities,
self.CachedProbabilities,
self.ProbabilityChannels,
self.BadObjects]
times = roi._l
if len(times) == 0:
# we assume that 0-length requests are requesting everything
times = range(self.Predictions.meta.shape[0])
if slot is self.CachedProbabilities:
return {t: self.prob_cache[t] for t in times if t in self.prob_cache}
forests=self.inputs["Classifier"][:].wait()
if forests is None or forests[0] is None:
# this happens if there was no data to train with
return dict((t, numpy.array([])) for t in times)
feats = {}
prob_predictions = {}
selected = self.SelectedFeatures([]).wait()
# FIXME: self.prob_cache is shared, so we need to block.
# However, this makes prediction single-threaded.
self.lock.acquire()
try:
for t in times:
if t in self.prob_cache:
continue
tmpfeats = self.Features([t]).wait()
ftmatrix, _, col_names = make_feature_array(tmpfeats, selected)
rows, cols = replace_missing(ftmatrix)
self.bad_objects[t] = numpy.zeros((ftmatrix.shape[0],))
self.bad_objects[t][rows] = 1
feats[t] = ftmatrix
prob_predictions[t] = [0] * len(forests)
def predict_forest(_t, forest_index):
# Note: We can't use RandomForest.predictLabels() here because we're training in parallel,
# and we have to average the PROBABILITIES from all forests.
# Averaging the label predictions from each forest is NOT equivalent.
# For details please see wikipedia:
# http://en.wikipedia.org/wiki/Electoral_College_%28United_States%29#Irrelevancy_of_national_popular_vote
# (^-^)
prob_predictions[_t][forest_index] = forests[forest_index].predictProbabilities(feats[_t].astype(numpy.float32))
# predict the data with all the forests in parallel
pool = RequestPool()
for t in times:
if t in self.prob_cache:
continue
for i, f in enumerate(forests):
req = Request( partial(predict_forest, t, i) )
pool.add(req)
pool.wait()
pool.clean()
for t in times:
if t not in self.prob_cache:
# prob_predictions is a dict-of-lists-of-arrays, indexed as follows:
# prob_predictions[t][forest_index][object_index, class_index]
# Stack the forests together and average them.
stacked_predictions = numpy.array( prob_predictions[t] )
averaged_predictions = numpy.average( stacked_predictions, axis=0 )
assert averaged_predictions.shape[0] == len(feats[t])
self.prob_cache[t] = averaged_predictions
self.prob_cache[t][0] = 0 # Background probability is always zero
if slot == self.Probabilities:
return { t : self.prob_cache[t] for t in times }
elif slot == self.Predictions:
# FIXME: Support SegmentationThreshold again...
labels = dict()
for t in times:
prob_sum = numpy.sum(self.prob_cache[t], axis=1)
labels[t] = 1 + numpy.argmax(self.prob_cache[t], axis=1)
labels[t][0] = 0 # Background gets the zero label
return labels
elif slot == self.ProbabilityChannels:
try:
prob_single_channel = {t: self.prob_cache[t][:, subindex[0]]
for t in times}
except:
# no probabilities available for this class; return zeros
prob_single_channel = {t: numpy.zeros((self.prob_cache[t].shape[0], 1))
for t in times}
return prob_single_channel
elif slot == self.BadObjects:
return { t : self.bad_objects[t] for t in times }
else:
assert False, "Unknown input slot"
finally:
self.lock.release()
def propagateDirty(self, slot, subindex, roi):
self.prob_cache = {}
if slot is self.InputProbabilities:
self.prob_cache = self.InputProbabilities([]).wait()
self.Predictions.setDirty(())
self.Probabilities.setDirty(())
self.ProbabilityChannels.setDirty(())
class OpPatchCreator(Operator):
"""Patchifies an image."""
PatchWidth = InputSlot() # width of patch in pixel
PatchHeight = InputSlot() # height of patch in pixel
PatchOverlapVertical = InputSlot() # vertical overlap between patches in pixels
PatchOverlapHorizontal = InputSlot() # horizontal overlap between patches in pixels
GridStartVertical = InputSlot() # X - start of patch grid in pixel
GridStartHorizontal = InputSlot() # Y - start of patch grid in pixel
GridWidth = InputSlot() # width of patch grid in pixel
GridHeight = InputSlot() # height of patch grid in pixel
RawInput = InputSlot() # raw input image
FilteredInput = InputSlot() # filtered input image
Patches = OutputSlot() # output patches
Positions = OutputSlot() # output positions of patches
NumPatches = OutputSlot() # number of patches in x/y-direction
GridOutput = OutputSlot()
def __init__(self, *args, **kwargs):
super(OpPatchCreator, self).__init__(*args, **kwargs)
self.patches = None
self.posns = None
self.lock = RequestLock()
self.opGrid = opGridCreator.OpGridCreator(graph=Graph())
self.GridOutput.connect(self.opGrid.Output)
self.opGrid.GridStartVertical.connect(self.GridStartVertical)
self.opGrid.GridStartHorizontal.connect(self.GridStartHorizontal)
self.opGrid.GridWidth.connect(self.GridWidth)
self.opGrid.GridHeight.connect(self.GridHeight)
self.opGrid.PatchWidth.connect(self.PatchWidth)
self.opGrid.PatchHeight.connect(self.PatchHeight)
def setupOutputs(self):
skipVertical = self.PatchHeight.value - self.PatchOverlapVertical.value
skipHorizontal = self.PatchWidth.value - self.PatchOverlapHorizontal.value
if skipVertical <= 0 or skipHorizontal <= 0:
return
# total number of patches in x-direction
numPatchesVertical = (self.GridHeight.value - self.PatchHeight.value) // skipVertical + 1
# total number of patches in y-direction
numPatchesHorizontal = (self.GridWidth.value - self.PatchWidth.value) // skipHorizontal + 1
# total number of patches on the image
totNumPatches = numPatchesVertical * numPatchesHorizontal
# number of pixel per patch
numPixelsPerPatch = self.PatchWidth.value * self.PatchHeight.value
# set shape of output data
self.NumPatches.meta.shape = (2,)
self.NumPatches.meta.dtype = numpy.uint32
self.NumPatches.meta.axistags = None
self.Positions.meta.shape = (totNumPatches, 2)
self.Positions.meta.dtype = numpy.uint32
self.Positions.meta.axistags = None
n_channels = self.FilteredInput.meta.shape[2]
self.Patches.meta.shape = (totNumPatches, self.PatchWidth.value,
self.PatchHeight.value,
n_channels)
self.Patches.meta.dtype = numpy.float32
self.Patches.meta.axistags = None
# set input slots for operator opGridCreator
self.opGrid.ImageHeight.setValue(self.RawInput.meta.shape[1])
self.opGrid.ImageWidth.setValue(self.RawInput.meta.shape[0])
def execute(self, slot, subindex, roi, result):
"""Create patches from filtered input image slot.
shape of output patches [number of patches, number of pixels
per patch, number of filter responses = channels]
"""
skipVertical = self.PatchHeight.value - self.PatchOverlapVertical.value
skipHorizontal = self.PatchWidth.value - self.PatchOverlapHorizontal.value
if slot is self.NumPatches:
pWidth = self.PatchWidth.value
pHeight = self.PatchHeight.value
gWidth = self.GridWidth.value
gHeight = self.GridHeight.value
numPatchesVertical = int((gHeight - pHeight) / skipVertical) + 1
numPatchesHorizontal = int((gWidth - pWidth) / skipHorizontal) + 1
numpatches = numpy.zeros((2,))
numpatches[:] = (numPatchesVertical, numPatchesHorizontal)
return numpatches
try:
self.lock.acquire()
if self.patches is None:
img = self.FilteredInput[:].wait()
pWidth = self.PatchWidth.value
pHeight = self.PatchHeight.value
overlapVertical = self.PatchOverlapVertical.value
overlapHorizontal = self.PatchOverlapHorizontal.value
gStartVertical = self.GridStartVertical.value
gStartHorizontal = self.GridStartHorizontal.value
gWidth = self.GridWidth.value
gHeight = self.GridHeight.value
img = self.FilteredInput[:].wait()
img.axistags = self.FilteredInput.meta.axistags
img = numpy.asarray(img.transposeToNumpyOrder())
self.patches, self.posns = patchify(
img,
(pHeight, pWidth),
(overlapVertical, overlapHorizontal),
(gStartVertical, gStartHorizontal),
(gHeight, gWidth)
)
if slot is self.Patches:
return self.patches
elif slot is self.Positions:
return self.posns
finally:
self.lock.release()
def propagateDirty(self, slot, subindex, roi):
try:
self.lock.acquire()
self.patches = None
self.posns = None
roi = slice(None)
self.Patches.setDirty(roi)
self.Positions.setDirty(roi)
self.NumPatches.setDirty(roi)
finally:
self.lock.release()
class OpObjectPredict(Operator):
"""Predicts object labels in a single image.
Performs prediction on all objects in a time slice at once, and
caches the result.
"""
# WARNING: right now we predict and cache a whole time slice. We
# expect this to be fast because there are relatively few objects
# compared to the number of pixels in pixel classification. If
# this should be too slow, we should instead cache at the object
# level, and only predict for objects visible in the roi.
name = "OpObjectPredict"
Features = InputSlot(rtype=List, stype=Opaque)
SelectedFeatures = InputSlot(rtype=List, stype=Opaque)
Classifier = InputSlot()
LabelsCount = InputSlot(stype='integer')
InputProbabilities = InputSlot(stype=Opaque, rtype=List, optional=True)
Predictions = OutputSlot(stype=Opaque, rtype=List)
Probabilities = OutputSlot(stype=Opaque, rtype=List)
CachedProbabilities = OutputSlot(stype=Opaque, rtype=List)
ProbabilityChannels = OutputSlot(stype=Opaque, rtype=List, level=1)
BadObjects = OutputSlot(stype=Opaque, rtype=List)
#SegmentationThreshold = 0.5
def setupOutputs(self):
self.Predictions.meta.shape = self.Features.meta.shape
self.Predictions.meta.dtype = object
self.Predictions.meta.axistags = None
self.Predictions.meta.mapping_dtype = numpy.uint8
self.Probabilities.meta.shape = self.Features.meta.shape
self.Probabilities.meta.dtype = object
self.Probabilities.meta.mapping_dtype = numpy.float32
self.Probabilities.meta.axistags = None
self.BadObjects.meta.shape = self.Features.meta.shape
self.BadObjects.meta.dtype = object
self.BadObjects.meta.mapping_dtype = numpy.uint8
self.BadObjects.meta.axistags = None
if self.LabelsCount.ready():
nlabels = self.LabelsCount[:].wait()
nlabels = int(nlabels[0])
self.ProbabilityChannels.resize(nlabels)
for oslot in self.ProbabilityChannels:
oslot.meta.shape = self.Features.meta.shape
oslot.meta.dtype = object
oslot.meta.axistags = None
oslot.meta.mapping_dtype = numpy.float32
self.lock = RequestLock()
self.prob_cache = dict()
self.bad_objects = dict()
def execute(self, slot, subindex, roi, result):
assert slot in [
self.Predictions, self.Probabilities, self.CachedProbabilities,
self.ProbabilityChannels, self.BadObjects
]
times = roi._l
if len(times) == 0:
# we assume that 0-length requests are requesting everything
times = range(self.Predictions.meta.shape[0])
if slot is self.CachedProbabilities:
return {
t: self.prob_cache[t]
for t in times if t in self.prob_cache
}
forests = self.inputs["Classifier"][:].wait()
if forests is None or forests[0] is None:
# this happens if there was no data to train with
return dict((t, numpy.array([])) for t in times)
feats = {}
prob_predictions = {}
selected = self.SelectedFeatures([]).wait()
# FIXME: self.prob_cache is shared, so we need to block.
# However, this makes prediction single-threaded.
self.lock.acquire()
try:
for t in times:
if t in self.prob_cache:
continue
tmpfeats = self.Features([t]).wait()
ftmatrix, _, col_names = make_feature_array(tmpfeats, selected)
rows, cols = replace_missing(ftmatrix)
self.bad_objects[t] = numpy.zeros((ftmatrix.shape[0], ))
self.bad_objects[t][rows] = 1
feats[t] = ftmatrix
prob_predictions[t] = [0] * len(forests)
def predict_forest(_t, forest_index):
# Note: We can't use RandomForest.predictLabels() here because we're training in parallel,
# and we have to average the PROBABILITIES from all forests.
# Averaging the label predictions from each forest is NOT equivalent.
# For details please see wikipedia:
# http://en.wikipedia.org/wiki/Electoral_College_%28United_States%29#Irrelevancy_of_national_popular_vote
# (^-^)
prob_predictions[_t][forest_index] = forests[
forest_index].predictProbabilities(feats[_t].astype(
numpy.float32))
# predict the data with all the forests in parallel
pool = RequestPool()
for t in times:
if t in self.prob_cache:
continue
for i, f in enumerate(forests):
req = Request(partial(predict_forest, t, i))
pool.add(req)
pool.wait()
pool.clean()
for t in times:
if t not in self.prob_cache:
# prob_predictions is a dict-of-lists-of-arrays, indexed as follows:
# prob_predictions[t][forest_index][object_index, class_index]
# Stack the forests together and average them.
stacked_predictions = numpy.array(prob_predictions[t])
averaged_predictions = numpy.average(stacked_predictions,
axis=0)
assert averaged_predictions.shape[0] == len(feats[t])
self.prob_cache[t] = averaged_predictions
self.prob_cache[t][
0] = 0 # Background probability is always zero
if slot == self.Probabilities:
return {t: self.prob_cache[t] for t in times}
elif slot == self.Predictions:
# FIXME: Support SegmentationThreshold again...
labels = dict()
for t in times:
prob_sum = numpy.sum(self.prob_cache[t], axis=1)
labels[t] = 1 + numpy.argmax(self.prob_cache[t], axis=1)
labels[t][0] = 0 # Background gets the zero label
return labels
elif slot == self.ProbabilityChannels:
try:
prob_single_channel = {
t: self.prob_cache[t][:, subindex[0]]
for t in times
}
except:
# no probabilities available for this class; return zeros
prob_single_channel = {
t: numpy.zeros((self.prob_cache[t].shape[0], 1))
for t in times
}
return prob_single_channel
elif slot == self.BadObjects:
return {t: self.bad_objects[t] for t in times}
else:
assert False, "Unknown input slot"
finally:
self.lock.release()
def propagateDirty(self, slot, subindex, roi):
self.prob_cache = {}
if slot is self.InputProbabilities:
self.prob_cache = self.InputProbabilities([]).wait()
self.Predictions.setDirty(())
self.Probabilities.setDirty(())
self.ProbabilityChannels.setDirty(())
def __init__(self, *args, **kwargs):
super( OpUnblockedArrayCache, self ).__init__(*args, **kwargs)
self._lock = RequestLock()
self._block_data = {}
self._block_locks = {}
def __init__(self, *args, **kwargs):
super(OpGridCreator, self).__init__(*args, **kwargs)
self.gridArray = None
self.lock = RequestLock()
def __init__(self, *args, **kwargs):
super(self.__class__, self).__init__(*args, **kwargs)
self._blockPipelines = {} # indexed by blockstart
self._lock = RequestLock()
def execute(self, slot, subindex, roi, result):
assert slot == self.LabelAndFeatureMatrix
self.progressSignal(0.0)
# Technically, this could result in strange progress reporting if execute()
# is called by multiple threads in parallel.
# This could be fixed with some fancier progress state, but
# (1) We don't expect that to by typical, and
# (2) progress reporting is merely informational.
num_dirty_blocks = len(self._dirty_blocks)
remaining_dirty = [num_dirty_blocks]
def update_progress(result):
remaining_dirty[0] -= 1
percent_complete = 95.0 * (num_dirty_blocks -
remaining_dirty[0]) / num_dirty_blocks
self.progressSignal(percent_complete)
# Update all dirty blocks in the cache
logger.debug("Updating {} dirty blocks".format(num_dirty_blocks))
# Before updating the blocks, ensure that the necessary block locks exist
# It's better to do this now instead of inside each request
# to avoid contention over self._lock
with self._lock:
for block_start in self._dirty_blocks:
if block_start not in self._block_locks:
self._block_locks[block_start] = RequestLock()
# Update each block in its own request.
pool = RequestPool()
reqs = {}
for block_start in self._dirty_blocks:
req = Request(partial(self._get_features_for_block, block_start))
req.notify_finished(update_progress)
reqs[block_start] = req
pool.add(req)
pool.wait()
# Now store the results we got.
# It's better to store the blocks here -- rather than within each request -- to
# avoid contention over self._lock from within every block's request.
with self._lock:
for block_start, req in reqs.items():
if req.result is None:
# 'None' means the block wasn't dirty. No need to update.
continue
labels_and_features_matrix = req.result
self._dirty_blocks.remove(block_start)
if labels_and_features_matrix.shape[0] > 0:
# Update the block entry with the new matrix.
self._blockwise_feature_matrices[
block_start] = labels_and_features_matrix
else:
# All labels were removed from the block,
# So the new feature matrix is empty.
# Just delete its entry from our list.
try:
del self._blockwise_feature_matrices[block_start]
except KeyError:
pass
# Concatenate the all blockwise results
if self._blockwise_feature_matrices:
total_feature_matrix = numpy.concatenate(
self._blockwise_feature_matrices.values(), axis=0)
else:
# No label points at all.
# Return an empty label&feature matrix (of the correct shape)
num_feature_channels = self.FeatureImage.meta.shape[-1]
total_feature_matrix = numpy.ndarray(shape=(0, 1 +
num_feature_channels),
dtype=numpy.float32)
self.progressSignal(100.0)
logger.debug("After update, there are {} clean blocks".format(
len(self._blockwise_feature_matrices)))
result[0] = total_feature_matrix
class OpPatchCreator(Operator):
"""Patchifies an image."""
PatchWidth = InputSlot() # width of patch in pixel
PatchHeight = InputSlot() # height of patch in pixel
PatchOverlapVertical = InputSlot(
) # vertical overlap between patches in pixels
PatchOverlapHorizontal = InputSlot(
) # horizontal overlap between patches in pixels
GridStartVertical = InputSlot() # X - start of patch grid in pixel
GridStartHorizontal = InputSlot() # Y - start of patch grid in pixel
GridWidth = InputSlot() # width of patch grid in pixel
GridHeight = InputSlot() # height of patch grid in pixel
RawInput = InputSlot() # raw input image
FilteredInput = InputSlot() # filtered input image
Patches = OutputSlot() # output patches
Positions = OutputSlot() # output positions of patches
NumPatches = OutputSlot() # number of patches in x/y-direction
GridOutput = OutputSlot()
def __init__(self, *args, **kwargs):
super(OpPatchCreator, self).__init__(*args, **kwargs)
self.patches = None
self.posns = None
self.lock = RequestLock()
self.opGrid = opGridCreator.OpGridCreator(graph=Graph())
self.GridOutput.connect(self.opGrid.Output)
self.opGrid.GridStartVertical.connect(self.GridStartVertical)
self.opGrid.GridStartHorizontal.connect(self.GridStartHorizontal)
self.opGrid.GridWidth.connect(self.GridWidth)
self.opGrid.GridHeight.connect(self.GridHeight)
self.opGrid.PatchWidth.connect(self.PatchWidth)
self.opGrid.PatchHeight.connect(self.PatchHeight)
def setupOutputs(self):
skipVertical = self.PatchHeight.value - self.PatchOverlapVertical.value
skipHorizontal = self.PatchWidth.value - self.PatchOverlapHorizontal.value
if skipVertical <= 0 or skipHorizontal <= 0:
return
# total number of patches in x-direction
numPatchesVertical = (self.GridHeight.value -
self.PatchHeight.value) // skipVertical + 1
# total number of patches in y-direction
numPatchesHorizontal = (self.GridWidth.value -
self.PatchWidth.value) // skipHorizontal + 1
# total number of patches on the image
totNumPatches = numPatchesVertical * numPatchesHorizontal
# number of pixel per patch
numPixelsPerPatch = self.PatchWidth.value * self.PatchHeight.value
# set shape of output data
self.NumPatches.meta.shape = (2, )
self.NumPatches.meta.dtype = numpy.uint32
self.NumPatches.meta.axistags = None
self.Positions.meta.shape = (totNumPatches, 2)
self.Positions.meta.dtype = numpy.uint32
self.Positions.meta.axistags = None
n_channels = self.FilteredInput.meta.shape[2]
self.Patches.meta.shape = (totNumPatches, self.PatchWidth.value,
self.PatchHeight.value, n_channels)
self.Patches.meta.dtype = numpy.float32
self.Patches.meta.axistags = None
# set input slots for operator opGridCreator
self.opGrid.ImageHeight.setValue(self.RawInput.meta.shape[1])
self.opGrid.ImageWidth.setValue(self.RawInput.meta.shape[0])
def execute(self, slot, subindex, roi, result):
"""Create patches from filtered input image slot.
shape of output patches [number of patches, number of pixels
per patch, number of filter responses = channels]
"""
skipVertical = self.PatchHeight.value - self.PatchOverlapVertical.value
skipHorizontal = self.PatchWidth.value - self.PatchOverlapHorizontal.value
if slot is self.NumPatches:
pWidth = self.PatchWidth.value
pHeight = self.PatchHeight.value
gWidth = self.GridWidth.value
gHeight = self.GridHeight.value
numPatchesVertical = ((gHeight - pHeight) // skipVertical) + 1
numPatchesHorizontal = ((gWidth - pWidth) // skipHorizontal) + 1
numpatches = numpy.zeros((2, ))
numpatches[:] = (numPatchesVertical, numPatchesHorizontal)
return numpatches
try:
self.lock.acquire()
if self.patches is None:
img = self.FilteredInput[:].wait()
pWidth = self.PatchWidth.value
pHeight = self.PatchHeight.value
overlapVertical = self.PatchOverlapVertical.value
overlapHorizontal = self.PatchOverlapHorizontal.value
gStartVertical = self.GridStartVertical.value
gStartHorizontal = self.GridStartHorizontal.value
gWidth = self.GridWidth.value
gHeight = self.GridHeight.value
img = self.FilteredInput[:].wait()
img.axistags = self.FilteredInput.meta.axistags
img = numpy.asarray(img.transposeToNumpyOrder())
self.patches, self.posns = patchify(
img, (pHeight, pWidth),
(overlapVertical, overlapHorizontal),
(gStartVertical, gStartHorizontal), (gHeight, gWidth))
if slot is self.Patches:
return self.patches
elif slot is self.Positions:
return self.posns
finally:
self.lock.release()
def propagateDirty(self, slot, subindex, roi):
try:
self.lock.acquire()
self.patches = None
self.posns = None
roi = slice(None)
self.Patches.setDirty(roi)
self.Positions.setDirty(roi)
self.NumPatches.setDirty(roi)
finally:
self.lock.release()
def __init__(self, *args, **kwargs):
super(OpCompressedCache, self).__init__(*args, **kwargs)
self._lock = RequestLock()
self._init_cache(None)
def __init__(self, *args, **kwargs):
super(OpTiffReader, self).__init__(*args, **kwargs)
self._filepath = None
self._tiff_file = None
self._page_shape = None
self._tiff_file_lock = RequestLock()
