def __init__(self,
dataset=CocoDataSet().__dict__,
fields=['image', 'gt_box', 'gt_label', 'gt_score'],
image_shape=[3, 608, 608],
sample_transforms=[
DecodeImage(to_rgb=True, with_mixup=True),
MixupImage(alpha=1.5, beta=1.5),
NormalizeBox(),
RandomDistort(),
ExpandImage(max_ratio=4., prob=.5,
mean=[123.675, 116.28, 103.53]),
CropImage([[1, 1, 1.0, 1.0, 1.0, 1.0, 0.0, 0.0],
[1, 50, 0.3, 1.0, 0.5, 2.0, 0.1, 1.0],
[1, 50, 0.3, 1.0, 0.5, 2.0, 0.3, 1.0],
[1, 50, 0.3, 1.0, 0.5, 2.0, 0.5, 1.0],
[1, 50, 0.3, 1.0, 0.5, 2.0, 0.7, 1.0],
[1, 50, 0.3, 1.0, 0.5, 2.0, 0.9, 1.0],
[1, 50, 0.3, 1.0, 0.5, 2.0, 0.0, 1.0]]),
RandomInterpImage(target_size=608),
RandomFlipImage(is_normalized=True),
NormalizeImage(
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225],
is_scale=True,
is_channel_first=False),
Permute(to_bgr=False),
],
batch_transforms=[
RandomShape(sizes=[
320, 352, 384, 416, 448, 480, 512, 544, 576, 608
])
],
batch_size=8,
shuffle=True,
samples=-1,
drop_last=True,
with_background=False,
num_workers=8,
bufsize=128,
use_process=True,
num_max_boxes=50,
mixup_epoch=250):
sample_transforms.append(ArrangeYOLO())
super(YoloTrainFeed, self).__init__(
dataset,
fields,
image_shape,
sample_transforms,
batch_transforms,
batch_size=batch_size,
shuffle=shuffle,
samples=samples,
drop_last=drop_last,
with_background=with_background,
num_workers=num_workers,
bufsize=bufsize,
use_process=use_process)
self.num_max_boxes = num_max_boxes
self.mixup_epoch = mixup_epoch
self.mode = 'TRAIN'
def __init__(self,
dataset=CocoDataSet().__dict__,
fields=['image', 'gt_box', 'gt_label', 'gt_score'],
image_shape=[3, 608, 608],
sample_transforms=[
DecodeImage(to_rgb=True, with_mixup=True),
MixupImage(alpha=1.5, beta=1.5),
ColorDistort(),
RandomExpand(fill_value=[123.675, 116.28, 103.53]),
RandomCrop(),
RandomFlipImage(is_normalized=False),
Resize(target_dim=608, interp='random'),
NormalizePermute(
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.120, 57.375]),
NormalizeBox(),
],
batch_transforms=[
RandomShape(sizes=[
320, 352, 384, 416, 448, 480, 512, 544, 576, 608
])
],
batch_size=8,
shuffle=True,
samples=-1,
drop_last=True,
with_background=False,
num_workers=8,
bufsize=128,
use_process=True,
memsize=None,
num_max_boxes=50,
mixup_epoch=250,
class_aware_sampling=False):
sample_transforms.append(ArrangeYOLO())
super(YoloTrainFeed, self).__init__(
dataset,
fields,
image_shape,
sample_transforms,
batch_transforms,
batch_size=batch_size,
shuffle=shuffle,
samples=samples,
drop_last=drop_last,
with_background=with_background,
num_workers=num_workers,
bufsize=bufsize,
use_process=use_process,
memsize=memsize,
class_aware_sampling=class_aware_sampling)
self.num_max_boxes = num_max_boxes
self.mixup_epoch = mixup_epoch
self.mode = 'TRAIN'
def __init__(self,
dataset=VocDataSet().__dict__,
fields=['image', 'gt_box', 'gt_label'],
image_shape=[3, 300, 300],
sample_transforms=[
DecodeImage(to_rgb=True, with_mixup=False),
NormalizeBox(),
RandomDistort(brightness_lower=0.875,
brightness_upper=1.125,
is_order=True),
ExpandImage(max_ratio=4, prob=0.5),
CropImage(batch_sampler=[[1, 1, 1.0, 1.0, 1.0, 1.0, 0.0, 0.0],
[1, 50, 0.3, 1.0, 0.5, 2.0, 0.1, 0.0],
[1, 50, 0.3, 1.0, 0.5, 2.0, 0.3, 0.0],
[1, 50, 0.3, 1.0, 0.5, 2.0, 0.5, 0.0],
[1, 50, 0.3, 1.0, 0.5, 2.0, 0.7, 0.0],
[1, 50, 0.3, 1.0, 0.5, 2.0, 0.9, 0.0],
[1, 50, 0.3, 1.0, 0.5, 2.0, 0.0, 1.0]],
satisfy_all=False, avoid_no_bbox=False),
ResizeImage(target_size=300, use_cv2=False, interp=1),
RandomFlipImage(is_normalized=True),
Permute(),
NormalizeImage(mean=[127.5, 127.5, 127.5],
std=[127.502231, 127.502231, 127.502231],
is_scale=False)
],
batch_transforms=[],
batch_size=32,
shuffle=True,
samples=-1,
drop_last=True,
num_workers=8,
bufsize=10,
use_process=True,
memsize=None):
sample_transforms.append(ArrangeSSD())
super(SSDTrainFeed, self).__init__(
dataset,
fields,
image_shape,
sample_transforms,
batch_transforms,
batch_size=batch_size,
shuffle=shuffle,
samples=samples,
drop_last=drop_last,
num_workers=num_workers,
bufsize=bufsize,
use_process=use_process,
memsize=None)
self.mode = 'TRAIN'
def __init__(
self,
dataset=VocDataSet(VOC_VAL_ANNOTATION).__dict__,
fields=['image', 'im_shape', 'im_id', 'gt_box',
'gt_label', 'is_difficult'],
image_shape=[3, 300, 300],
sample_transforms=[
DecodeImage(to_rgb=True, with_mixup=False),
NormalizeBox(),
ResizeImage(target_size=300, use_cv2=False, interp=1),
Permute(),
NormalizeImage(
mean=[127.5, 127.5, 127.5],
std=[127.502231, 127.502231, 127.502231],
is_scale=False)
],
batch_transforms=[],
batch_size=64,
shuffle=False,
samples=-1,
drop_last=True,
num_workers=8,
bufsize=10,
use_process=False,
memsize=None):
sample_transforms.append(ArrangeEvalSSD(fields))
super(SSDEvalFeed, self).__init__(
dataset,
fields,
image_shape,
sample_transforms,
batch_transforms,
batch_size=batch_size,
shuffle=shuffle,
samples=samples,
drop_last=drop_last,
num_workers=num_workers,
bufsize=bufsize,
use_process=use_process,
memsize=memsize)
self.mode = 'VAL'