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(COCO_VAL_ANNOTATION,
COCO_VAL_IMAGE_DIR).__dict__,
fields=['image', 'im_info', 'im_id', 'im_shape'],
image_shape=[3, 800, 1333],
sample_transforms=[
DecodeImage(to_rgb=True),
NormalizeImage(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225],
is_scale=True,
is_channel_first=False),
ResizeImage(target_size=800, max_size=1333, interp=1),
Permute(to_bgr=False)
],
batch_transforms=[PadBatch()],
batch_size=1,
shuffle=False,
samples=-1,
drop_last=False,
num_workers=2,
use_padded_im_info=True):
sample_transforms.append(ArrangeTestRCNN())
super(FasterRCNNEvalFeed, 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,
use_padded_im_info=use_padded_im_info)
self.mode = 'VAL'
def __init__(self,
dataset=SimpleDataSet(VOC_TEST_ANNOTATION).__dict__,
fields=['image', 'im_id'],
image_shape=[3, 300, 300],
sample_transforms=[
DecodeImage(to_rgb=True),
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=1,
shuffle=False,
samples=-1,
drop_last=False,
num_workers=8,
bufsize=10,
use_process=False):
sample_transforms.append(ArrangeTestSSD())
if isinstance(dataset, dict):
dataset = SimpleDataSet(**dataset)
super(SSDTestFeed, 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)
self.mode = 'TEST'
def test_loader(self):
coco_loader = VOCDataSet(
dataset_dir=self.image_dir,
image_dir=self.root_path,
anno_path=self.anno_path,
sample_num=240,
use_default_label=False,
label_list='/path/to/your/fl_fruit/label_list.txt')
sample_trans = [
DecodeImage(to_rgb=True),
RandomFlipImage(),
NormalizeImage(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225],
is_scale=True,
is_channel_first=False),
ResizeImage(target_size=800, max_size=1333, interp=1),
Permute(to_bgr=False)
]
batch_trans = [
PadBatch(pad_to_stride=32, use_padded_im_info=True),
]
inputs_def = {
'fields':
['image', 'im_info', 'im_id', 'gt_bbox', 'gt_class', 'is_crowd'],
}
data_loader = Reader(coco_loader,
sample_transforms=sample_trans,
batch_transforms=batch_trans,
batch_size=1,
shuffle=True,
drop_empty=True,
inputs_def=inputs_def)()
return data_loader
def test_loader_multi_threads(self):
coco_loader = COCODataSet(dataset_dir=self.root_path,
image_dir=self.image_dir,
anno_path=self.anno_path,
sample_num=10)
sample_trans = [
DecodeImage(to_rgb=True),
ResizeImage(target_size=800, max_size=1333, interp=1),
Permute(to_bgr=False)
]
batch_trans = [
PadBatch(pad_to_stride=32, use_padded_im_info=True),
]
inputs_def = {
'fields': [
'image', 'im_info', 'im_id', 'gt_bbox', 'gt_class', 'is_crowd',
'gt_mask'
],
}
data_loader = Reader(coco_loader,
sample_transforms=sample_trans,
batch_transforms=batch_trans,
batch_size=2,
shuffle=True,
drop_empty=True,
worker_num=2,
use_process=False,
bufsize=8,
inputs_def=inputs_def)()
for i in range(2):
for samples in data_loader:
for sample in samples:
im_shape = sample[0].shape
self.assertEqual(im_shape[0], 3)
self.assertEqual(im_shape[1] % 32, 0)
self.assertEqual(im_shape[2] % 32, 0)
im_info_shape = sample[1].shape
self.assertEqual(im_info_shape[-1], 3)
im_id_shape = sample[2].shape
self.assertEqual(im_id_shape[-1], 1)
gt_bbox_shape = sample[3].shape
self.assertEqual(gt_bbox_shape[-1], 4)
gt_class_shape = sample[4].shape
self.assertEqual(gt_class_shape[-1], 1)
self.assertEqual(gt_class_shape[0], gt_bbox_shape[0])
is_crowd_shape = sample[5].shape
self.assertEqual(is_crowd_shape[-1], 1)
self.assertEqual(is_crowd_shape[0], gt_bbox_shape[0])
mask = sample[6]
self.assertEqual(len(mask), gt_bbox_shape[0])
self.assertEqual(mask[0][0].shape[-1], 2)
data_loader.reset()
def __init__(self,
dataset=CocoDataSet(COCO_VAL_ANNOTATION,
COCO_VAL_IMAGE_DIR).__dict__,
fields=['image', 'im_size', 'im_id', 'gt_box',
'gt_label', 'is_difficult'],
image_shape=[3, 608, 608],
sample_transforms=[
DecodeImage(to_rgb=True),
ResizeImage(target_size=608, interp=2),
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=[],
batch_size=8,
shuffle=False,
samples=-1,
drop_last=False,
with_background=False,
num_workers=8,
num_max_boxes=50,
use_process=False,
memsize=None):
sample_transforms.append(ArrangeEvalYOLO())
super(YoloEvalFeed, 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,
use_process=use_process,
memsize=memsize)
self.num_max_boxes = num_max_boxes
self.mode = 'VAL'
self.bufsize = 128
# support image shape config, resize image with image_shape
for i, trans in enumerate(sample_transforms):
if isinstance(trans, ResizeImage):
sample_transforms[i] = ResizeImage(
target_size=self.image_shape[-1],
interp=trans.interp)
if isinstance(trans, Resize):
sample_transforms[i].target_dim = self.image_shape[-1]
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=CocoDataSet().__dict__,
fields=[
'image', 'im_info', 'im_id', 'gt_box', 'gt_label',
'is_crowd'
],
image_shape=[None, 3, None, None],
sample_transforms=[
DecodeImage(to_rgb=True),
RandomFlipImage(prob=0.5),
NormalizeImage(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225],
is_scale=True,
is_channel_first=False),
ResizeImage(target_size=800, max_size=1333, interp=1),
Permute(to_bgr=False)
],
batch_transforms=[PadBatch()],
batch_size=1,
shuffle=True,
samples=-1,
drop_last=False,
bufsize=10,
num_workers=2,
use_process=False,
memsize=None,
class_aware_sampling=False):
# XXX this should be handled by the data loader, since `fields` is
# given, just collect them
sample_transforms.append(ArrangeRCNN())
super(FasterRCNNTrainFeed, self).__init__(
dataset,
fields,
image_shape,
sample_transforms,
batch_transforms,
batch_size=batch_size,
shuffle=shuffle,
samples=samples,
drop_last=drop_last,
bufsize=bufsize,
num_workers=num_workers,
use_process=use_process,
memsize=memsize,
class_aware_sampling=class_aware_sampling)
# XXX these modes should be unified
self.mode = 'TRAIN'
def __init__(self,
dataset=CocoDataSet().__dict__,
fields=[
'image', 'im_info', 'im_id', 'gt_box', 'gt_label',
'is_crowd', 'gt_mask'
],
image_shape=[None, 3, None, None],
sample_transforms=[
DecodeImage(to_rgb=True),
RandomFlipImage(prob=0.5, is_mask_flip=True),
NormalizeImage(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225],
is_scale=True,
is_channel_first=False),
ResizeImage(target_size=800,
max_size=1333,
interp=1,
use_cv2=True),
Permute(to_bgr=False, channel_first=True)
],
batch_transforms=[PadBatch()],
batch_size=1,
shuffle=True,
samples=-1,
drop_last=False,
num_workers=2,
use_process=False,
use_padded_im_info=False):
sample_transforms.append(ArrangeRCNN(is_mask=True))
super(MaskRCNNTrainFeed, 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,
use_process=use_process)
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'
def __init__(self,
dataset=SimpleDataSet(COCO_VAL_ANNOTATION,
COCO_VAL_IMAGE_DIR).__dict__,
fields=['image', 'im_size', 'im_id'],
image_shape=[3, 608, 608],
sample_transforms=[
DecodeImage(to_rgb=True),
ResizeImage(target_size=608, interp=2),
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=[],
batch_size=1,
shuffle=False,
samples=-1,
drop_last=False,
with_background=False,
num_workers=8,
num_max_boxes=50,
use_process=False):
sample_transforms.append(ArrangeTestYOLO())
if isinstance(dataset, dict):
dataset = SimpleDataSet(**dataset)
super(YoloTestFeed, 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,
use_process=use_process)
self.mode = 'TEST'
self.bufsize = 128
def __init__(self,
dataset=SimpleDataSet(COCO_VAL_ANNOTATION,
COCO_VAL_IMAGE_DIR).__dict__,
fields=['image', 'im_info', 'im_id', 'im_shape'],
image_shape=[3, 800, 1333],
sample_transforms=[
DecodeImage(to_rgb=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, channel_first=True)
],
batch_transforms=[PadBatch()],
batch_size=1,
shuffle=False,
samples=-1,
drop_last=False,
num_workers=2,
use_process=False,
use_padded_im_info=True):
sample_transforms.append(ArrangeTestRCNN())
if isinstance(dataset, dict):
dataset = SimpleDataSet(**dataset)
super(MaskRCNNTestFeed, 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,
use_process=use_process,
use_padded_im_info=use_padded_im_info)
self.mode = 'TEST'
