tensorcv.dataflow package

Subpackages

• tensorcv.dataflow.dataset package
  • Submodules
  • tensorcv.dataflow.dataset.BSDS500 module
  • tensorcv.dataflow.dataset.CIFAR module
  • tensorcv.dataflow.dataset.MNIST module
  • Module contents

Submodules

tensorcv.dataflow.base module

class tensorcv.dataflow.base.DataFlow

Bases: object

base class for dataflow

after_reading()

before_read_setup(**kwargs)

epochs_completed

next_batch()

next_batch_dict()

reset_epochs_completed(val)

reset_state()

set_batch_size(batch_size)

setup(epoch_val, batch_size, **kwargs)

size()

class tensorcv.dataflow.base.RNGDataFlow

Bases: tensorcv.dataflow.base.DataFlow

suffle_data()

tensorcv.dataflow.common module

tensorcv.dataflow.common.dense_to_one_hot(labels_dense, num_classes)

Convert class labels from scalars to one-hot vectors.

tensorcv.dataflow.common.get_file_list(file_dir, file_ext, sub_name=None)

tensorcv.dataflow.common.get_folder_list(folder_dir)

tensorcv.dataflow.common.get_folder_names(folder_dir)

tensorcv.dataflow.common.input_val_range(in_mat)

tensorcv.dataflow.common.load_image(im_path, read_channel=None, pf=<function identity>, resize=None, resize_crop=None)

tensorcv.dataflow.common.print_warning(warning_str)

tensorcv.dataflow.common.reverse_label_dict(label_dict)

tensorcv.dataflow.common.tanh_normalization(data, half_in_val)

tensorcv.dataflow.image module

class tensorcv.dataflow.image.ImageData(ext_name, data_dir='', shuffle=True, normalize=None)

Bases: tensorcv.dataflow.base.RNGDataFlow

next_batch()

size()

class tensorcv.dataflow.image.DataFromFile(ext_name, data_dir='', num_channel=None, shuffle=True, normalize=None, batch_dict_name=None, normalize_fnc=<function identity>)

Bases: tensorcv.dataflow.base.RNGDataFlow

Base class for image from files

get_sample_data()

next_batch()

next_batch_dict()

class tensorcv.dataflow.image.ImageLabelFromFolder(ext_name, data_dir='', num_channel=None, label_dict=None, num_class=None, one_hot=False, shuffle=True, normalize=None, resize=None, resize_crop=None, batch_dict_name=None, pf=<function identity>)

Bases: tensorcv.dataflow.image.ImageFromFile

read image data with label in subfolder name

__init__(ext_name, data_dir='', num_channel=None, label_dict=None, num_class=None, one_hot=False, shuffle=True, normalize=None, resize=None, resize_crop=None, batch_dict_name=None, pf=<function identity>)

Parameters:label_dict (dict) – empty or full

get_data_list()

get_label_list()

set_data_list(new_data_list)

size()

class tensorcv.dataflow.image.ImageLabelFromFile(ext_name, data_dir='', label_file_name='', num_channel=None, one_hot=False, label_dict={}, num_class=None, shuffle=True, normalize=None, resize=None, resize_crop=None, batch_dict_name=None, pf=<function identity>)

Bases: tensorcv.dataflow.image.ImageLabelFromFolder

read image data with label in a separate file txt

class tensorcv.dataflow.image.ImageFromFile(ext_name, data_dir='', num_channel=None, shuffle=True, normalize=None, normalize_fnc=<function identity>, resize=None, resize_crop=None, batch_dict_name=None, pf=<function identity>)

Bases: tensorcv.dataflow.image.DataFromFile

get_data_list()

set_data_list(new_data_list)

set_pf(pf)

size()

suffle_data()

class tensorcv.dataflow.image.ImageDenseLabel(ext_name, im_pre, label_pre, mask_pre=None, data_dir='', num_channel=None, shuffle=True, normalize=None, normalize_fnc=<function identity>, resize=None, resize_crop=None, batch_dict_name=None, is_binary=False)

Bases: tensorcv.dataflow.image.ImageFromFile

get_data_list()

get_label_list()

set_data_list(new_data_list)

tensorcv.dataflow.matlab module

class tensorcv.dataflow.matlab.MatlabData(data_dir='', mat_name_list=None, mat_type_list=None, shuffle=True, normalize=None)

Bases: tensorcv.dataflow.base.RNGDataFlow

dataflow from .mat file with mask

next_batch()

size()

tensorcv.dataflow.randoms module

class tensorcv.dataflow.randoms.RandomVec(len_vec=100)

Bases: tensorcv.dataflow.base.DataFlow

random vector input

next_batch()

reset_state()

size()

Module contents