def get_memory_usage_data_layer(self, layer_name):
'''
this function return memory usage for data given a specific layer
batch_size is considered
'''
assert self._compiled, 'the network is not compiled'
assert isstring(
layer_name), 'the name of layer queried should be a string'
assert self._layers.has_key(layer_name), 'no layer queried exists'
# we treat activation layer as in-place layer and don't store data in it
if isinstance(self._layers[layer_name], Activation):
return 0
# datashape = (self._batch_size, ) + self._blobs[layer_name]['data'].shape
datashape = (self._batch_size, ) + self._blobs[layer_name]['datashape']
layer = self._layers[layer_name]
num_pixel = reduce(mul, datashape)
if layer.datatype == 'single':
return num_pixel * 4 # single has 4 bytes
elif layer.datatype == 'double':
return num_pixel * 8 # double has 8 bytes
elif layer.datatype == 'uint':
return num_pixel # unsigned integer has 1 byte
elif layer.datatype == 'boolean':
return num_pixel # boolean has 4 bytes
else:
assert False, 'unknown error while calculating memory usage for data'
def get_recording_type(filename, debug=True):
'''
extract the recording type, sentence or neutral tongue or expression
'''
if debug:
assert isstring(filename), 'input filename is not a string'
substrings = filename.split('--')
return substrings[1]
def get_person_id(filename, debug=True):
'''
extract the person ID from MUGSY filename
'''
if debug:
assert isstring(filename), 'input filename is not a string'
substrings = filename.split('_')
return substrings[1]
def get_rotate_degree_v2(camera_id, debug=True):
if debug:
assert isstring(
camera_id
), 'the input camera id is not a string for getting rotation degree'
assert camera_id in get_camera_list(
), 'the camera id requested: %s does not exist' % camera_id
return rotate_degree_v2[camera_id]
def get_frame_number(filename, debug=True):
'''
extract the frame number from MUGSY filename
'''
if debug:
assert isstring(filename), 'input filename is not a string'
substrings = filename.split('--')
return int(substrings[3])
def get_recording_id(filename, debug=True):
'''
extract the recording id, including date and person id and dot flag
'''
if debug:
assert isstring(filename), 'input filename is not a string'
substrings = filename.split('--')
return substrings[0]
def get_camera_id(filename, debug=True):
'''
extract the camera ID from MUGSY filename
'''
if debug:
assert isstring(filename), 'input filename is not a string'
# print filename
substrings = filename.split('--')
return substrings[2]
def get_labeler_id(filename, debug=True):
'''
return the real image id and the labeler id, this function assume the name is separated by '--'
'''
if debug:
assert isstring(filename), 'input filename is not a string'
substrings = filename.split('--')
labeler_id = substrings[-1]
return labeler_id
def get_filename(recording_id,
recording_type,
camera_id,
frame_number,
labeler_id,
debug=True):
'''
return the full filename given all info
'''
if debug:
assert isstring(recording_id), 'recording id is not a string'
assert isstring(recording_type), 'recording type is not a string'
assert isscalar(frame_number), 'frame number is not a scalar'
assert isstring(labeler_id), 'labeler id is not a string'
assert camera_id in get_camera_list(
), 'camera id %s is not in the camera list' % camera_id
return '--'.join([
recording_id, recording_type, camera_id,
'%05d' % (frame_number), labeler_id
])
def load_hdf5_file(hdf5_file, dataname, debug=True):
'''
load a single hdf5 file
'''
if debug:
assert is_path_exists(hdf5_file) and isfile(
hdf5_file), 'input hdf5 path does not exist: %s' % hdf5_file
assert islist(dataname), 'dataset queried is not correct'
assert all(
isstring(dataset_tmp)
for dataset_tmp in dataname), 'dataset queried is not correct'
hdf5 = h5py.File(hdf5_file, 'r')
datadict = dict()
for dataset in dataname:
datadict[dataset] = np.array(hdf5[dataset])
return datadict
def __init__(self,
name,
function,
bottom=None,
datatype=None,
paramtype=None):
super(Activation, self).__init__(name=name,
bottom=bottom,
datatype=datatype,
paramtype=paramtype)
assert isstring(
function), 'the function used in dense layer should be a string'
assert any(function is item for item in ACTIVATION_FUNCTION), \
'type of parameter should be one of "%s"' \
% functools.reduce(lambda x, y: str(x) + '" "' + str(y), ACTIVATION_FUNCTION)
assert self._bottom is None or len(self._bottom) == 1, \
'Activation layer can only have one bottom layer'
self._function = function
def rand_load_hdf5_from_folder(hdf5_src, dataname, debug=True):
'''
randomly load a single hdf5 file from a hdf5 folder
'''
if debug:
assert is_path_exists(hdf5_src) and isfolder(
hdf5_src), 'input hdf5 path does not exist: %s' % hdf5_src
assert islist(dataname), 'dataset queried is not correct'
assert all(
isstring(dataset_tmp)
for dataset_tmp in dataname), 'dataset queried is not correct'
hdf5list, num_hdf5_files = load_list_from_folder(folder_path=hdf5_src,
ext_filter='.hdf5')
check_index = random.randrange(0, num_hdf5_files)
hdf5_path_sample = hdf5list[check_index]
hdf5_file = h5py.File(hdf5_path_sample, 'r')
datadict = dict()
for dataset in dataname:
datadict[dataset] = np.array(hdf5_file[dataset])
return datadict
def __init__(self, name, datatype=None, paramtype=None):
if datatype is not None:
self._datatype_check(datatype)
else:
datatype = 'single'
print 'datatype of the layer is not defined.' \
'By default, we use single floating point to save the data'
if paramtype is not None:
self._paramtype_check(paramtype)
else:
paramtype = 'single'
print 'paramtype of the layer is not defined. By default,' \
'we use single floating point to save the parameter'
assert isstring(name), 'the name of input layer should be a string'
self._name = name
# self._data = None
# self._params = None
self._datatype = datatype
self._paramtype = paramtype
self._top = None
self._bottom = None
def remove(self, layer_name):
assert isstring(
layer_name), 'the layer should be queried by a string name'
if self._blobs.has_key(layer_name):
assert not isinstance(self._layers[layer_name], Input), \
'the input layer is not able to delete. ' \
'You might want to use reshape function to change the input shape.'
# TODO: test if reference
previous_layer = self._layers[layer_name].bottom[0]
if self._layers[layer_name].top is not None:
next_layer = self._layers[layer_name].top[0]
else:
next_layer = None
self._layers[layer_name].bottom[0].top = next_layer
self._layers[layer_name].top[0].bottom = previous_layer
del self._blobs[layer_name]
del self._layers[layer_name]
self._nb_entries -= 1
else:
assert False, 'No layer queried existing'
self._compiled = False
def _paramtype_check(self, paramtype):
assert isstring(paramtype), 'the type of parameter should be a string'
assert any(paramtype is item for item in PARAMTYPE), \
'type of parameter should be one of "%s"' \
% functools.reduce(lambda x, y: str(x) + '" "' + str(y), PARAMTYPE)
def generate_hdf5(save_dir,
data_src,
data_name='data',
batch_size=1,
ext_filter='png',
label_src1=None,
label_name1='label',
label_preprocess_function1=identity,
label_range1=None,
label_src2=None,
label_name2='label2',
label_preprocess_function2=identity,
label_range2=None,
debug=True,
vis=False):
'''
# this function creates data in hdf5 format from a image path
# input parameter
# data_src: source of image data, which can be a list of image path, a txt file contains a list of image path, a folder contains a set of images, a list of numpy array image data
# label_src: source of label data, which can be none, a file contains a set of labels, a dictionary of labels, a 1-d numpy array data, a list of label data
# save_dir: where to store the hdf5 data
# batch_size: how many image to store in a single hdf file
# ext_filder: what format of data to use for generating hdf5 data
'''
# parse input
assert is_path_exists_or_creatable(
save_dir), 'save path should be a folder to save all hdf5 files'
mkdir_if_missing(save_dir)
assert isstring(
data_name), 'dataset name is not correct' # name for hdf5 data
# convert data source to a list of numpy array image data
if isfolder(data_src):
print 'data is loading from %s with extension .%s' % (data_src,
ext_filter)
filelist, num_data = load_list_from_folder(data_src,
ext_filter=ext_filter)
datalist = None
elif isfile(data_src):
print 'data is loading from %s with extension .%s' % (data_src,
ext_filter)
filelist, num_data = load_list_from_file(data_src)
datalist = None
elif islist(data_src):
if debug:
assert all(
isimage(data_tmp) for data_tmp in data_src
), 'input data source is not a list of numpy array image data'
datalist = data_src
num_data = len(datalist)
filelist = None
else:
assert False, 'data source format is not correct.'
if debug:
assert (datalist is None and filelist is not None) or (
filelist is None and datalist is not None), 'data is not correct'
if datalist is not None:
assert len(datalist) == num_data, 'number of data is not equal'
if filelist is not None:
assert len(filelist) == num_data, 'number of data is not equal'
# convert label source to a list of numpy array label
if label_src1 is None:
labeldict1 = None
labellist1 = None
elif isfile(label_src1):
assert is_path_exists(label_src1), 'file not found'
_, _, ext = fileparts(label_src1)
assert ext == '.json', 'only json extension is supported'
labeldict1 = json.load(label_src1)
num_label1 = len(labeldict1)
assert num_data == num_label1, 'number of data and label is not equal.'
labellist1 = None
elif isdict(label_src1):
labeldict1 = label_src1
labellist1 = None
elif isnparray(label_src1):
if debug:
assert label_src1.ndim == 1, 'only 1-d label is supported'
labeldict1 = None
labellist1 = label_src1
elif islist(label_src1):
if debug:
assert all(
np.array(label_tmp).size == 1
for label_tmp in label_src1), 'only 1-d label is supported'
labellist1 = label_src1
labeldict1 = None
else:
assert False, 'label source format is not correct.'
assert isfunction(label_preprocess_function1
), 'label preprocess function is not correct.'
# convert label source to a list of numpy array label
if label_src2 is None:
labeldict2 = None
labellist2 = None
elif isfile(label_src2):
assert is_path_exists(label_src2), 'file not found'
_, _, ext = fileparts(label_src2)
assert ext == '.json', 'only json extension is supported'
labeldict2 = json.load(label_src2)
num_label2 = len(labeldict2)
assert num_data == num_label2, 'number of data and label is not equal.'
labellist2 = None
elif isdict(label_src2):
labeldict2 = label_src2
labellist2 = None
elif isnparray(label_src2):
if debug:
assert label_src2.ndim == 1, 'only 1-d label is supported'
labeldict2 = None
labellist2 = label_src2
elif islist(label_src2):
if debug:
assert all(
np.array(label_tmp).size == 1
for label_tmp in label_src2), 'only 1-d label is supported'
labellist2 = label_src2
labeldict2 = None
else:
assert False, 'label source format is not correct.'
assert isfunction(label_preprocess_function2
), 'label preprocess function is not correct.'
# warm up
if datalist is not None:
size_data = datalist[0].shape
else:
size_data = imread(filelist[0]).shape
if labeldict1 is not None:
if debug:
assert isstring(label_name1), 'label name is not correct'
labels1 = np.zeros((batch_size, 1), dtype='float32')
# label_value1 = [float(label_tmp_char) for label_tmp_char in labeldict1.values()]
# label_range1 = np.array([min(label_value1), max(label_value1)])
if labellist1 is not None:
labels1 = np.zeros((batch_size, 1), dtype='float32')
# label_range1 = [np.min(labellist1), np.max(labellist1)]
if label_src1 is not None and debug:
assert label_range1 is not None, 'label range is not correct'
assert (labeldict1 is not None and labellist1 is None) or (
labellist1 is not None
and labeldict1 is None), 'label is not correct'
if labeldict2 is not None:
if debug:
assert isstring(label_name2), 'label name is not correct'
labels2 = np.zeros((batch_size, 1), dtype='float32')
# label_value2 = [float(label_tmp_char) for label_tmp_char in labeldict2.values()]
# label_range2 = np.array([min(label_value2), max(label_value2)])
if labellist2 is not None:
labels2 = np.zeros((batch_size, 1), dtype='float32')
# label_range2 = [np.min(labellist2), np.max(labellist2)]
if label_src2 is not None and debug:
assert label_range2 is not None, 'label range is not correct'
assert (labeldict2 is not None and labellist2 is None) or (
labellist2 is not None
and labeldict2 is None), 'label is not correct'
# start generating
count_hdf = 1 # count number of hdf5 file
clock = Timer()
datalist_batch = list()
for i in xrange(num_data):
clock.tic()
if filelist is not None:
imagefile = filelist[i]
_, name, _ = fileparts(imagefile)
img = imread(imagefile).astype('float32')
max_value = np.max(img)
if max_value > 1 and max_value <= 255:
img = img / 255.0 # [rows,col,channel,numbers], scale the image data to (0, 1)
if debug:
min_value = np.min(img)
assert min_value >= 0 and min_value <= 1, 'data is not in [0, 1]'
if datalist is not None:
img = datalist[i]
if debug:
assert size_data == img.shape
datalist_batch.append(img)
# process label
if labeldict1 is not None:
if debug:
assert len(filelist) == len(
labeldict1), 'file list is not equal to label dictionary'
labels1[i % batch_size, 0] = float(labeldict1[name])
if labellist1 is not None:
labels1[i % batch_size, 0] = float(labellist1[i])
if labeldict2 is not None:
if debug:
assert len(filelist) == len(
labeldict2), 'file list is not equal to label dictionary'
labels2[i % batch_size, 0] = float(labeldict2[name])
if labellist2 is not None:
labels2[i % batch_size, 0] = float(labellist2[i])
# save to hdf5
if i % batch_size == 0:
data = preprocess_image_caffe(
datalist_batch, debug=debug, vis=vis
) # swap channel, transfer from list of HxWxC to NxCxHxW
# write to hdf5 format
if filelist is not None:
save_path = os.path.join(save_dir, '%s.hdf5' % name)
else:
save_path = os.path.join(save_dir,
'image_%010d.hdf5' % count_hdf)
h5f = h5py.File(save_path, 'w')
h5f.create_dataset(data_name, data=data, dtype='float32')
if (labeldict1 is not None) or (labellist1 is not None):
labels1 = label_preprocess_function1(data=labels1,
data_range=label_range1,
debug=debug)
h5f.create_dataset(label_name1, data=labels1, dtype='float32')
labels1 = np.zeros((batch_size, 1), dtype='float32')
if (labeldict2 is not None) or (labellist2 is not None):
labels2 = label_preprocess_function2(data=labels2,
data_range=label_range2,
debug=debug)
h5f.create_dataset(label_name2, data=labels2, dtype='float32')
labels2 = np.zeros((batch_size, 1), dtype='float32')
h5f.close()
count_hdf = count_hdf + 1
del datalist_batch[:]
if debug:
assert len(datalist_batch) == 0, 'list has not been cleared'
average_time = clock.toc()
print(
'saving to %s: %d/%d, average time:%.3f, elapsed time:%s, estimated time remaining:%s'
% (save_path, i + 1, num_data, average_time,
format_time(average_time * i),
format_time(average_time * (num_data - i))))
return count_hdf - 1, num_data
def _datatype_check(self, datatype):
assert isstring(datatype), 'the type of data should be a string'
assert any(datatype is item for item in DATATYPE), \
'type of data should be one of "%s"' \
% functools.reduce(lambda x, y: str(x) + '" "' + str(y), DATATYPE)
