3.10.1.20.1.3. opengate.sources.gansources

3.10.1.20.1.3.1. Classes

VoxelizedSourcePDFSampler	This is an alternative to GateSPSVoxelsPosDistribution (c++)
VoxelizedSourceConditionGenerator
GANSource	GAN source: the Generator produces particles
GANPairsSource	GAN source: the Generator produces pairs of particles (for PET)
GANSourceDefaultGenerator	This class manage the base components of a particle generator.
GANSourceDefaultPairsGenerator	Like GANSourceDefaultGenerator but for pairs of particle (PET)
GANSourceConditionalGenerator	This class manage the base components of a particle generator.
GANSourceConditionalPairsGenerator	Generate pairs of particles with a GAN, considering conditional vectors.

3.10.1.20.1.3.2. Functions

import_gaga_phsp()

3.10.1.20.1.3.3. Module Contents

opengate.sources.gansources.import_gaga_phsp()

class opengate.sources.gansources.VoxelizedSourcePDFSampler(itk_image, version=1)

This is an alternative to GateSPSVoxelsPosDistribution (c++) It is needed because the cond voxel source is used on python side.

There are two versions, version 2 is much slower (do not use)

image

version

imga

pdf

linear_indices

init_cdf()

searchsorted2d(a, b)

sample_indices_slower(n, rs=np.random)

This version seems slower than the other version with np random choice

samples_g4(n)

sample_indices(n, rs=np.random)

sample_indices_phys(n, rs=np.random)

class opengate.sources.gansources.VoxelizedSourceConditionGenerator(activity_source_filename, rs=np.random, use_activity_origin=False)

activity_source_filename

compute_directions = False

use_activity_origin

translation = [0, 0, 0]

rotation

image = None

rs

img_info = None

sampler = None

points_offset = None

is_initialized = False

initialize_source()

generate_condition(n)

class opengate.sources.gansources.GANSource(user_info)

Bases: opengate.sources.generic.GenericSource

GAN source: the Generator produces particles Input is a neural network Generator trained with a GAN

type_name = 'GANSource'

static set_default_user_info(user_info)

create_g4_source()

initialize(run_timing_intervals)

set_default_generator()

class opengate.sources.gansources.GANPairsSource(user_info)

Bases: GANSource

GAN source: the Generator produces pairs of particles (for PET) Input is a neural network Generator trained with a GAN

type_name = 'GANPairsSource'

static set_default_user_info(user_info)

create_g4_source()

set_default_generator()

class opengate.sources.gansources.GANSourceDefaultGenerator(user_info)

This class manage the base components of a particle generator.

• In the constructor, the module ‘gaga’ is imported. It is only imported in the constructor to only required

this module if it is used

• ‘initialize’ function: the GAN is loaded and the list of keys is initialized

• ‘generator’ function: default generator

• ‘get_output_keys’ function: map the user defined keys to the ones of the generator. There are two usages, either

with on single primary (3 values for position, direction), or paired primary (6 values).

• ‘move_backward’ function: consider all particles positions and move their backward according to their direction,

using the factor provided by the user in ‘user_info.backward_distance’. This is useful to allow generating particles that do not intersect with the detector.

• ‘copy_generated_particle_to_g4’ function: copy all the particles (pos, dir, time, energy) to the cpp part.

user_info

gaga = None

indexes_are_build = None

lock = None

initialize_is_done = False

keys_output = None

gan_info = None

gpu_mode = None

__getstate__()

initialize()

read_gan_and_keys()

get_output_keys()

get_output_keys_with_lock()

check_parameters(g)

fatal(txt)

get_position_index(g, the_keys, n)

get_direction_index(g, the_keys, n)

get_energy_index(g, the_keys, n)

get_time_index(g, the_keys, n)

get_weight_index(g, the_keys, n)

get_gan_key_index(all_keys, user_keys, n)

Consider ‘user_keys’ in the list of all keys and return the indexes Special case: if the key name is a float value, we consider the value instead of the index.

generator(source)

Main function that will be called from the cpp side every time a batch of particles should be created. Once created here, the particles are copied to cpp. (Yes maybe the copy could be avoided, but I did not manage to do it)

copy_generated_particle_to_g4(source, g, fake)

move_backward(g, fake)

class opengate.sources.gansources.GANSourceDefaultPairsGenerator(user_info)

Bases: GANSourceDefaultGenerator

Like GANSourceDefaultGenerator but for pairs of particle (PET)

is_paired = True

__getstate__()

check_parameters(g)

get_energy_index(g, the_keys, n)

get_time_index(g, the_keys, n)

get_weight_index(g, the_keys, n)

generator(source)

Main function that will be called from the cpp side every time a batch of particles should be created. Once created here, the particles are copied to cpp. (Yes maybe the copy could be avoided, but I did not manage to do it)

copy_generated_particle_to_g4(source, g, fake)

move_backward(g, fake)

class opengate.sources.gansources.GANSourceConditionalGenerator(user_info, generate_condition_function)

Bases: GANSourceDefaultGenerator

This class manage the base components of a particle generator.

• In the constructor, the module ‘gaga’ is imported. It is only imported in the constructor to only required

this module if it is used

• ‘initialize’ function: the GAN is loaded and the list of keys is initialized

• ‘generator’ function: default generator

• ‘get_output_keys’ function: map the user defined keys to the ones of the generator. There are two usages, either

with on single primary (3 values for position, direction), or paired primary (6 values).

• ‘move_backward’ function: consider all particles positions and move their backward according to their direction,

using the factor provided by the user in ‘user_info.backward_distance’. This is useful to allow generating particles that do not intersect with the detector.

• ‘copy_generated_particle_to_g4’ function: copy all the particles (pos, dir, time, energy) to the cpp part.

generate_condition

generator(source)

Generate particles with a GAN, considering conditional vectors.

class opengate.sources.gansources.GANSourceConditionalPairsGenerator(user_info, sphere_radius, generate_condition_function)

Bases: GANSourceDefaultPairsGenerator

Generate pairs of particles with a GAN, considering conditional vectors.

The parameter sphere_radius is required : it is the radius of the sphere that surround the source during the training.

sphere_radius

generate_condition

__getstate__()

generator(source)

Main function that will be called from the cpp side every time a batch of particles should be created. Once created here, the particles are copied to cpp. (Yes maybe the copy could be avoided, but I did not manage to do it)