def print_class_histogram(roidbs):
"""
Args:
roidbs (list[dict]): the same format as the output of `training_roidbs`.
"""
class_names = DatasetRegistry.get_metadata(cfg.DATA.TRAIN[0],
'class_names')
# labels are in [1, NUM_CATEGORY], hence +2 for bins
hist_bins = np.arange(cfg.DATA.NUM_CATEGORY + 2)
# Histogram of ground-truth objects
gt_hist = np.zeros((cfg.DATA.NUM_CATEGORY + 1, ), dtype=np.int)
for entry in roidbs:
# filter crowd?
gt_inds = np.where((entry["class"] > 0) & (entry["is_crowd"] == 0))[0]
gt_classes = entry["class"][gt_inds]
if len(gt_classes):
assert gt_classes.max() <= len(class_names) - 1
gt_hist += np.histogram(gt_classes, bins=hist_bins)[0]
data = list(
itertools.chain(*[[class_names[i + 1], v]
for i, v in enumerate(gt_hist[1:])]))
COL = min(6, len(data))
total_instances = sum(data[1::2])
data.extend([None] * ((COL - len(data) % COL) % COL))
data.extend(["total", total_instances])
data = itertools.zip_longest(*[data[i::COL] for i in range(COL)])
# the first line is BG
table = tabulate(data,
headers=["class", "#box"] * (COL // 2),
tablefmt="pipe",
stralign="center",
numalign="left")
logger.info("Ground-Truth category distribution:\n" +
colored(table, "cyan"))
def finalize_configs(is_training):
"""
Run some sanity checks, and populate some configs from others
"""
_C.freeze(False) # populate new keys now
if isinstance(_C.DATA.VAL, six.string_types
): # support single string (the typical case) as well
_C.DATA.VAL = (_C.DATA.VAL, )
if isinstance(_C.DATA.TRAIN, six.string_types): # support single string
_C.DATA.TRAIN = (_C.DATA.TRAIN, )
# finalize dataset definitions ...
from dataset import DatasetRegistry
datasets = list(_C.DATA.TRAIN) + list(_C.DATA.VAL)
_C.DATA.CLASS_NAMES = DatasetRegistry.get_metadata(datasets[0],
"class_names")
_C.DATA.NUM_CATEGORY = len(_C.DATA.CLASS_NAMES) - 1
assert _C.BACKBONE.NORM in ['FreezeBN', 'SyncBN', 'GN',
'None'], _C.BACKBONE.NORM
if _C.BACKBONE.NORM != 'FreezeBN':
assert not _C.BACKBONE.FREEZE_AFFINE
assert _C.BACKBONE.FREEZE_AT in [0, 1, 2]
_C.RPN.NUM_ANCHOR = len(_C.RPN.ANCHOR_SIZES) * len(_C.RPN.ANCHOR_RATIOS)
assert len(_C.FPN.ANCHOR_STRIDES) == len(_C.RPN.ANCHOR_SIZES)
# image size into the backbone has to be multiple of this number
_C.FPN.RESOLUTION_REQUIREMENT = _C.FPN.ANCHOR_STRIDES[
3] # [3] because we build FPN with features r2,r3,r4,r5
if _C.MODE_FPN:
size_mult = _C.FPN.RESOLUTION_REQUIREMENT * 1.
_C.PREPROC.MAX_SIZE = np.ceil(
_C.PREPROC.MAX_SIZE / size_mult) * size_mult
assert _C.FPN.PROPOSAL_MODE in ['Level', 'Joint']
assert _C.FPN.FRCNN_HEAD_FUNC.endswith('_head')
assert _C.FPN.MRCNN_HEAD_FUNC.endswith('_head')
assert _C.FPN.NORM in ['None', 'GN']
if _C.FPN.CASCADE:
# the first threshold is the proposal sampling threshold
assert _C.CASCADE.IOUS[0] == _C.FRCNN.FG_THRESH
assert len(_C.CASCADE.BBOX_REG_WEIGHTS) == len(_C.CASCADE.IOUS)
if is_training:
train_scales = _C.PREPROC.TRAIN_SHORT_EDGE_SIZE
if isinstance(
train_scales,
(list, tuple)) and train_scales[1] - train_scales[0] > 100:
# don't autotune if augmentation is on
os.environ['TF_CUDNN_USE_AUTOTUNE'] = '0'
os.environ['TF_AUTOTUNE_THRESHOLD'] = '1'
assert _C.TRAINER in ['horovod', 'replicated'], _C.TRAINER
lr = _C.TRAIN.LR_SCHEDULE
if isinstance(lr, six.string_types):
if lr.endswith("x"):
LR_SCHEDULE_KITER = {
"{}x".format(k): [180 * k - 120, 180 * k - 40, 180 * k]
for k in range(2, 10)
}
LR_SCHEDULE_KITER["1x"] = [120, 160, 180]
_C.TRAIN.LR_SCHEDULE = [
x * 1000 for x in LR_SCHEDULE_KITER[lr]
]
else:
_C.TRAIN.LR_SCHEDULE = eval(lr)
# setup NUM_GPUS
if _C.TRAINER == 'horovod':
import horovod.tensorflow as hvd
ngpu = hvd.size()
logger.info("Horovod Rank={}, Size={}, LocalRank={}".format(
hvd.rank(), hvd.size(), hvd.local_rank()))
else:
assert 'OMPI_COMM_WORLD_SIZE' not in os.environ
ngpu = get_num_gpu()
assert ngpu > 0, "Has to train with GPU!"
assert ngpu % 8 == 0 or 8 % ngpu == 0, "Can only train with 1,2,4 or >=8 GPUs, but found {} GPUs".format(
ngpu)
else:
# autotune is too slow for inference
os.environ['TF_CUDNN_USE_AUTOTUNE'] = '0'
ngpu = get_num_gpu()
if _C.TRAIN.NUM_GPUS is None:
_C.TRAIN.NUM_GPUS = ngpu
else:
if _C.TRAINER == 'horovod':
assert _C.TRAIN.NUM_GPUS == ngpu
else:
assert _C.TRAIN.NUM_GPUS <= ngpu
_C.freeze()
logger.info("Config: ------------------------------------------\n" +
str(_C))
def finalize_configs(is_training):
"""
Run some sanity checks, and populate some configs from others
"""
_C.freeze(False) # populate new keys now
if isinstance(_C.DATA.VAL, six.string_types
): # support single string (the typical case) as well
_C.DATA.VAL = (_C.DATA.VAL, )
if isinstance(_C.DATA.TRAIN, six.string_types): # support single string
_C.DATA.TRAIN = (_C.DATA.TRAIN, )
# finalize dataset definitions ...
from dataset import DatasetRegistry
datasets = list(_C.DATA.TRAIN) + list(_C.DATA.VAL)
# _C.DATA.CLASS_NAMES = ["BG", "class1", "class2", "class3", "class4", "class5", "class6"]
# _C.DATA.CLASS_NAMES = [
# "person", "bicycle", "car", "motorcycle", "airplane", "bus", "train", "truck", "boat", "traffic light", "fire hydrant", "stop sign", "parking meter", "bench", "bird", "cat", "dog", "horse", "sheep", "cow", "elephant", "bear", "zebra", "giraffe", "backpack", "umbrella", "handbag", "tie", "suitcase", "frisbee", "skis", "snowboard", "sports ball", "kite", "baseball bat", "baseball glove", "skateboard", "surfboard", "tennis racket", "bottle", "wine glass", "cup", "fork", "knife", "spoon", "bowl", "banana", "apple", "sandwich", "orange", "broccoli", "carrot", "hot dog", "pizza", "donut", "cake", "chair", "couch", "potted plant", "bed", "dining table", "toilet", "tv", "laptop", "mouse", "remote", "keyboard", "cell phone", "microwave", "oven", "toaster", "sink", "refrigerator", "book", "clock", "vase", "scissors", "teddy bear", "hair drier", "toothbrush"] # noqa
# _C.DATA.CLASS_NAMES = ["BG"] + _C.DATA.CLASS_NAMES
# print(datasets[0])
_C.DATA.CLASS_NAMES = DatasetRegistry.get_metadata(datasets[0],
"class_names")
# print(_C.DATA.CLASS_NAMES)
_C.DATA.NUM_CATEGORY = len(_C.DATA.CLASS_NAMES) - 1
assert _C.BACKBONE.NORM in ['FreezeBN', 'SyncBN', 'GN',
'None'], _C.BACKBONE.NORM
if _C.BACKBONE.NORM != 'FreezeBN':
assert not _C.BACKBONE.FREEZE_AFFINE
assert _C.BACKBONE.FREEZE_AT in [0, 1, 2]
_C.RPN.NUM_ANCHOR = len(_C.RPN.ANCHOR_SIZES) * len(_C.RPN.ANCHOR_RATIOS)
assert len(_C.FPN.ANCHOR_STRIDES) == len(_C.RPN.ANCHOR_SIZES)
# image size into the backbone has to be multiple of this number
_C.FPN.RESOLUTION_REQUIREMENT = _C.FPN.ANCHOR_STRIDES[
3] # [3] because we build FPN with features r2,r3,r4,r5
if _C.MODE_FPN:
size_mult = _C.FPN.RESOLUTION_REQUIREMENT * 1.
_C.PREPROC.MAX_SIZE = np.ceil(
_C.PREPROC.MAX_SIZE / size_mult) * size_mult
assert _C.FPN.PROPOSAL_MODE in ['Level', 'Joint']
assert _C.FPN.FRCNN_HEAD_FUNC.endswith('_head')
assert _C.FPN.MRCNN_HEAD_FUNC.endswith('_head')
assert _C.FPN.NORM in ['None', 'GN']
if _C.FPN.CASCADE:
# the first threshold is the proposal sampling threshold
assert _C.CASCADE.IOUS[0] == _C.FRCNN.FG_THRESH
assert len(_C.CASCADE.BBOX_REG_WEIGHTS) == len(_C.CASCADE.IOUS)
if is_training:
train_scales = _C.PREPROC.TRAIN_SHORT_EDGE_SIZE
if isinstance(
train_scales,
(list, tuple)) and train_scales[1] - train_scales[0] > 100:
# don't autotune if augmentation is on
os.environ['TF_CUDNN_USE_AUTOTUNE'] = '0'
os.environ['TF_AUTOTUNE_THRESHOLD'] = '1'
assert _C.TRAINER in ['horovod', 'replicated'], _C.TRAINER
lr = _C.TRAIN.LR_SCHEDULE
if isinstance(lr, six.string_types):
if lr.endswith("x"):
LR_SCHEDULE_KITER = {
"{}x".format(k): [180 * k - 120, 180 * k - 40, 180 * k]
for k in range(2, 10)
}
LR_SCHEDULE_KITER["1x"] = [120, 160, 180]
_C.TRAIN.LR_SCHEDULE = [
x * 1000 for x in LR_SCHEDULE_KITER[lr]
]
else:
_C.TRAIN.LR_SCHEDULE = eval(lr)
# setup NUM_GPUS
if _C.TRAINER == 'horovod':
import horovod.tensorflow as hvd
ngpu = hvd.size()
logger.info("Horovod Rank={}, Size={}, LocalRank={}".format(
hvd.rank(), hvd.size(), hvd.local_rank()))
else:
assert 'OMPI_COMM_WORLD_SIZE' not in os.environ
ngpu = get_num_gpu()
assert ngpu > 0, "Has to train with GPU!"
assert ngpu % 8 == 0 or 8 % ngpu == 0, "Can only train with 1,2,4 or >=8 GPUs, but found {} GPUs".format(
ngpu)
else:
# autotune is too slow for inference
os.environ['TF_CUDNN_USE_AUTOTUNE'] = '0'
ngpu = get_num_gpu()
if _C.TRAIN.NUM_GPUS is None:
_C.TRAIN.NUM_GPUS = ngpu
else:
if _C.TRAINER == 'horovod':
assert _C.TRAIN.NUM_GPUS == ngpu
else:
assert _C.TRAIN.NUM_GPUS <= ngpu
_C.freeze()
logger.info("Config: ------------------------------------------\n" +
str(_C))
