discopat.nn_training.torch_detection_utils.utils

Functions

all_gather(data)	Run all_gather on arbitrary picklable data (not necessarily tensors).
collate_fn(batch)
get_rank()
get_world_size()
is_dist_avail_and_initialized()
is_main_process()
mkdir(path)
reduce_dict(input_dict[, average])	Reduce the values in the dictionary from all processes so that all processes.
setup_for_distributed(is_master)	Disable printing when not in master process.

Classes

MetricLogger([delimiter])
SmoothedValue([window_size, fmt])	Track a series of values and provide access to smoothed values over a window or the global series average.

class discopat.nn_training.torch_detection_utils.utils.MetricLogger(delimiter='\t')

Bases: object

add_meter(name, meter)

log_every(iterable, print_freq, header=None)

synchronize_between_processes()

update(**kwargs)

class discopat.nn_training.torch_detection_utils.utils.SmoothedValue(window_size=20, fmt=None)

Bases: object

Track a series of values and provide access to smoothed values over a window or the global series average.

property avg

property global_avg

property max

property median

synchronize_between_processes()

Warning: does not synchronize the deque!.

update(value, n=1)

property value

discopat.nn_training.torch_detection_utils.utils.all_gather(data)

Run all_gather on arbitrary picklable data (not necessarily tensors).

Parameters:

data – any picklable object

Returns:

list of data gathered from each rank

Return type:

list[data]

discopat.nn_training.torch_detection_utils.utils.collate_fn(batch)

discopat.nn_training.torch_detection_utils.utils.get_rank()

discopat.nn_training.torch_detection_utils.utils.get_world_size()

discopat.nn_training.torch_detection_utils.utils.is_dist_avail_and_initialized()

discopat.nn_training.torch_detection_utils.utils.is_main_process()

discopat.nn_training.torch_detection_utils.utils.mkdir(path)

discopat.nn_training.torch_detection_utils.utils.reduce_dict(input_dict, average=True)

Reduce the values in the dictionary from all processes so that all processes.

Parameters:

• input_dict (dict) – all the values will be reduced

• average (bool) – whether to do average or sum have the averaged results.

Returns a dict with the same fields as input_dict, after reduction.

discopat.nn_training.torch_detection_utils.utils.setup_for_distributed(is_master)

Disable printing when not in master process.