def get_config(is_train):
class General:
log_frequency = 10
name = __name__.rsplit("/")[-1].rsplit(".")[-1]
batch_image = 2 if is_train else 1
fp16 = False
class KvstoreParam:
kvstore = "nccl"
batch_image = General.batch_image
gpus = [0, 1, 2, 3, 4, 5, 6, 7]
fp16 = General.fp16
class NormalizeParam:
normalizer = normalizer_factory(type="fixbn")
class BackboneParam:
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
class NeckParam:
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
class RpnParam:
num_class = 1 + 80
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
batch_image = General.batch_image
class anchor_generate:
scale = (4 * 2**0, 4 * 2**(1.0 / 3.0), 4 * 2**(2.0 / 3.0))
ratio = (0.5, 1.0, 2.0)
stride = (8, 16, 32, 64, 128)
image_anchor = None
class head:
conv_channel = 256
mean = None
std = None
class proposal:
pre_nms_top_n = 1000
post_nms_top_n = None
nms_thr = None
min_bbox_side = None
min_det_score = 0.05 # filter score in network
class subsample_proposal:
proposal_wo_gt = None
image_roi = None
fg_fraction = None
fg_thr = None
bg_thr_hi = None
bg_thr_lo = None
class bbox_target:
num_reg_class = None
class_agnostic = None
weight = None
mean = None
std = None
class focal_loss:
alpha = 0.25
gamma = 2.0
class BboxParam:
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
num_class = None
image_roi = None
batch_image = None
class regress_target:
class_agnostic = None
mean = None
std = None
class RoiParam:
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
out_size = None
stride = None
class DatasetParam:
if is_train:
image_set = ("coco_train2014", "coco_valminusminival2014")
else:
image_set = ("coco_minival2014", )
backbone = Backbone(BackboneParam)
neck = Neck(NeckParam)
rpn_head = RpnHead(RpnParam)
detector = Detector()
if is_train:
train_sym = detector.get_train_symbol(backbone, neck, rpn_head)
test_sym = None
else:
train_sym = None
test_sym = detector.get_test_symbol(backbone, neck, rpn_head)
class ModelParam:
train_symbol = train_sym
test_symbol = test_sym
from_scratch = False
random = True
memonger = False
memonger_until = "stage3_unit21_plus"
class pretrain:
prefix = "pretrain_model/resnet-v1-101"
epoch = 0
fixed_param = ["conv0", "stage1", "gamma", "beta"]
class OptimizeParam:
class optimizer:
type = "sgd"
lr = 0.005 / 8 * len(KvstoreParam.gpus) * KvstoreParam.batch_image
momentum = 0.9
wd = 0.0001
clip_gradient = None
class schedule:
begin_epoch = 0
end_epoch = 6
lr_iter = [
60000 * 16 //
(len(KvstoreParam.gpus) * KvstoreParam.batch_image), 80000 *
16 // (len(KvstoreParam.gpus) * KvstoreParam.batch_image)
]
class warmup:
type = "gradual"
lr = 0.005 / 8 * len(
KvstoreParam.gpus) * KvstoreParam.batch_image / 3
iter = 500
class TestParam:
min_det_score = 0 # filter appended boxes
max_det_per_image = 100
process_roidb = lambda x: x
process_output = lambda x, y: x
class model:
prefix = "experiments/{}/checkpoint".format(General.name)
epoch = OptimizeParam.schedule.end_epoch
class nms:
type = "nms"
thr = 0.5
class coco:
annotation = "data/coco/annotations/instances_minival2014.json"
# data processing
class NormParam:
mean = (122.7717, 115.9465, 102.9801) # RGB order
std = (1.0, 1.0, 1.0)
class ResizeParam:
short = 800
long = 1333
class PadParam:
short = 800
long = 1333
max_num_gt = 100
class AnchorTarget2DParam:
def __init__(self):
self.generate = self._generate()
class _generate:
def __init__(self):
self.short = (100, 50, 25, 13, 7)
self.long = (167, 84, 42, 21, 11)
self.stride = (8, 16, 32, 64, 128)
scales = (4 * 2**0, 4 * 2**(1.0 / 3.0), 4 * 2**(2.0 / 3.0))
aspects = (0.5, 1.0, 2.0)
class assign:
allowed_border = 9999
pos_thr = 0.5
neg_thr = 0.4
min_pos_thr = 0.0
class sample:
image_anchor = None
pos_fraction = None
class RenameParam:
mapping = dict(image="data")
from core.detection_input import ReadRoiRecord, Resize2DImageBbox, \
ConvertImageFromHwcToChw, Flip2DImageBbox, Pad2DImageBbox, \
RenameRecord
from models.retinanet.input import PyramidAnchorTarget2D, Norm2DImage
if is_train:
transform = [
ReadRoiRecord(None),
Norm2DImage(NormParam),
Resize2DImageBbox(ResizeParam),
Flip2DImageBbox(),
Pad2DImageBbox(PadParam),
ConvertImageFromHwcToChw(),
PyramidAnchorTarget2D(AnchorTarget2DParam()),
RenameRecord(RenameParam.mapping)
]
data_name = ["data"]
label_name = ["rpn_cls_label", "rpn_reg_target", "rpn_reg_weight"]
else:
transform = [
ReadRoiRecord(None),
Norm2DImage(NormParam),
Resize2DImageBbox(ResizeParam),
ConvertImageFromHwcToChw(),
RenameRecord(RenameParam.mapping)
]
data_name = ["data", "im_info", "im_id", "rec_id"]
label_name = []
from models.retinanet import metric
rpn_acc_metric = metric.FGAccMetric("FGAcc", ["cls_loss_output"],
["rpn_cls_label"])
metric_list = [rpn_acc_metric]
return General, KvstoreParam, RpnParam, RoiParam, BboxParam, DatasetParam, \
ModelParam, OptimizeParam, TestParam, \
transform, data_name, label_name, metric_list
def get_config(is_train):
class General:
log_frequency = 10
name = __name__.rsplit("/")[-1].rsplit(".")[-1]
batch_image = 2 if is_train else 1
fp16 = False
class KvstoreParam:
kvstore = "nccl"
batch_image = General.batch_image
gpus = [0, 1, 2, 3, 4, 5, 6, 7]
fp16 = General.fp16
class NormalizeParam:
# normalizer = normalizer_factory(type="syncbn", ndev=8, wd_mult=1.0)
normalizer = normalizer_factory(type="gn")
class BackboneParam:
fp16 = General.fp16
# normalizer = NormalizeParam.normalizer
normalizer = normalizer_factory(type="fixbn")
class NeckParam:
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
class HeadParam:
num_class = 1 + 80
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
batch_image = General.batch_image
class point_generate:
num_points = 9
scale = 4
stride = (8, 16, 32, 64, 128)
# transform = "minmax"
transform = "moment"
class head:
conv_channel = 256
point_conv_channel = 256
mean = None
std = None
class proposal:
pre_nms_top_n = 1000
post_nms_top_n = None
nms_thr = None
min_bbox_side = None
class point_target:
target_scale = 4
num_pos = 1
class bbox_target:
pos_iou_thr = 0.5
neg_iou_thr = 0.5
min_pos_iou = 0.0
class focal_loss:
alpha = 0.25
gamma = 2.0
class BboxParam:
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
num_class = None
image_roi = None
batch_image = None
class regress_target:
class_agnostic = None
mean = None
std = None
class RoiParam:
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
out_size = None
stride = None
class DatasetParam:
if is_train:
image_set = ("coco_train2017", )
else:
image_set = ("coco_val2017", )
backbone = Backbone(BackboneParam)
neck = Neck(NeckParam)
head = Head(HeadParam)
detector = Detector()
if is_train:
train_sym = detector.get_train_symbol(backbone, neck, head)
test_sym = None
else:
train_sym = None
test_sym = detector.get_test_symbol(backbone, neck, head)
class ModelParam:
train_symbol = train_sym
test_symbol = test_sym
from_scratch = False
random = True
memonger = False
memonger_until = "stage3_unit21_plus"
class pretrain:
prefix = "pretrain_model/resnet-v1-50"
epoch = 0
fixed_param = ["conv0", "stage1", "gamma", "beta"]
excluded_param = ["gn"]
class OptimizeParam:
class optimizer:
type = "sgd"
lr = 0.005 / 8 * len(KvstoreParam.gpus) * KvstoreParam.batch_image
momentum = 0.9
wd = 0.0001
clip_gradient = None
class schedule:
begin_epoch = 0
end_epoch = 6
lr_iter = [
60000 * 16 //
(len(KvstoreParam.gpus) * KvstoreParam.batch_image), 80000 *
16 // (len(KvstoreParam.gpus) * KvstoreParam.batch_image)
]
class warmup:
type = "gradual"
lr = 0.005 / 8 * len(
KvstoreParam.gpus) * KvstoreParam.batch_image / 3
iter = 500
class TestParam:
min_det_score = 0.05 # filter appended boxes
max_det_per_image = 100
def process_roidb(x):
return x
def process_output(x, y):
return x
class model:
prefix = "experiments/{}/checkpoint".format(General.name)
epoch = OptimizeParam.schedule.end_epoch
class nms:
type = "nms"
thr = 0.5
class coco:
annotation = "data/coco/annotations/instances_minival2014.json"
# data processing
class NormParam:
mean = (122.7717, 115.9465, 102.9801) # RGB order
std = (1.0, 1.0, 1.0)
class ResizeParam:
short = 800
long = 1333
class PadParam:
short = 800
long = 1333
max_num_gt = 100
class RenameParam:
mapping = dict(image="data")
from core.detection_input import ReadRoiRecord, Resize2DImageBbox, \
ConvertImageFromHwcToChw, Flip2DImageBbox, Pad2DImageBbox, \
RenameRecord
from models.retinanet.input import Norm2DImage
if is_train:
transform = [
ReadRoiRecord(None),
Norm2DImage(NormParam),
Resize2DImageBbox(ResizeParam),
Flip2DImageBbox(),
Pad2DImageBbox(PadParam),
ConvertImageFromHwcToChw(),
RenameRecord(RenameParam.mapping)
]
data_name = ["data"]
label_name = ["gt_bbox"]
else:
transform = [
ReadRoiRecord(None),
Norm2DImage(NormParam),
Resize2DImageBbox(ResizeParam),
Pad2DImageBbox(PadParam),
ConvertImageFromHwcToChw(),
RenameRecord(RenameParam.mapping)
]
data_name = ["data", "im_info", "im_id", "rec_id"]
label_name = []
from models.retinanet import metric as cls_metric
import core.detection_metric as box_metric
cls_acc_metric = cls_metric.FGAccMetric(
"FGAcc", ["cls_loss_output", "point_refine_labels_output"], [])
box_init_l1_metric = box_metric.L1(
"InitL1", ["pts_init_loss_output", "points_init_labels_output"], [])
box_refine_l1_metric = box_metric.L1(
"RefineL1", ["pts_refine_loss_output", "point_refine_labels_output"],
[])
metric_list = [cls_acc_metric, box_init_l1_metric, box_refine_l1_metric]
return General, KvstoreParam, HeadParam, RoiParam, BboxParam, DatasetParam, \
ModelParam, OptimizeParam, TestParam, \
transform, data_name, label_name, metric_list
def get_config(is_train):
class General:
log_frequency = 10
name = __name__.rsplit("/")[-1].rsplit(".")[-1]
batch_image = 3 if is_train else 1
fp16 = True
class KvstoreParam:
kvstore = "local"
batch_image = General.batch_image
gpus = [0, 1, 2, 3, 4, 5, 6, 7]
fp16 = General.fp16
class NormalizeParam:
normalizer = normalizer_factory(type="syncbn", ndev=8, wd_mult=1.0)
class BackboneParam:
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
depth = 50
class NeckParam:
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
dim_reduced = 384
num_stage = 3
S0_kernel = 1
class RpnParam:
num_class = 1 + 80
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
batch_image = General.batch_image
sync_loss = True
class anchor_generate:
scale = (4 * 2**0, 4 * 2**(1.0 / 3.0), 4 * 2**(2.0 / 3.0))
ratio = (0.5, 1.0, 2.0)
stride = (8, 16, 32, 64, 128)
image_anchor = None
class head:
conv_channel = 256
mean = None
std = None
class proposal:
pre_nms_top_n = 1000
post_nms_top_n = None
nms_thr = None
min_bbox_side = None
min_det_score = 0.05 # filter score in network
class focal_loss:
alpha = 0.25
gamma = 2.0
class BboxParam:
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
num_class = None
image_roi = None
batch_image = None
class RoiParam:
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
out_size = None
stride = None
class DatasetParam:
if is_train:
image_set = ("coco_train2017", "coco_val2017")
else:
image_set = ("coco_test-dev2017", )
backbone = Backbone(BackboneParam)
neck = Neck(NeckParam)
rpn_head = RpnHead(RpnParam)
detector = Detector()
if is_train:
train_sym = detector.get_train_symbol(backbone, neck, rpn_head)
test_sym = None
else:
train_sym = None
test_sym = detector.get_test_symbol(backbone, neck, rpn_head)
class ModelParam:
train_symbol = train_sym
test_symbol = test_sym
from_scratch = False
random = True
memonger = False
memonger_until = "stage4_unit3_relu"
class pretrain:
prefix = "pretrain_model/resnet%s_v1b" % BackboneParam.depth
epoch = 0
fixed_param = ["conv0"]
class OptimizeParam:
class optimizer:
type = "sgd"
lr = 0.01 / 8 * len(KvstoreParam.gpus) * KvstoreParam.batch_image
momentum = 0.9
wd = 0.0001
clip_gradient = None
class schedule:
begin_epoch = 0
end_epoch = 25
lr_iter = [
15272 * 15 * 16 //
(len(KvstoreParam.gpus) * KvstoreParam.batch_image), 15272 *
20 * 16 // (len(KvstoreParam.gpus) * KvstoreParam.batch_image)
]
class warmup:
type = "gradual"
lr = 0.001 / 8 * len(KvstoreParam.gpus) * KvstoreParam.batch_image
iter = 15272 * 1 * 16 // (len(KvstoreParam.gpus) *
KvstoreParam.batch_image)
class TestParam:
min_det_score = 0 # filter appended boxes
max_det_per_image = 100
process_roidb = lambda x: x
process_output = lambda x, y: x
class model:
prefix = "experiments/{}/checkpoint".format(General.name)
epoch = OptimizeParam.schedule.end_epoch
class nms:
type = "nms"
thr = 0.5
class coco:
annotation = "data/coco/annotations/instances_val2017.json"
# data processing
class NormParam:
mean = (123.688, 116.779, 103.939) # RGB order
std = (58.393, 57.12, 57.375)
class ResizeParam:
short = 1280
long = 1280
scale_min = 0.8
scale_max = 1.2
class PadParam:
short = ResizeParam.short
long = ResizeParam.long
max_num_gt = 100
class AnchorTarget2DParam:
def __init__(self):
self.generate = self._generate()
class _generate:
def __init__(self):
self.short = (160, 80, 40, 20, 10)
self.long = (160, 80, 40, 20, 10)
self.stride = (8, 16, 32, 64, 128)
scales = (4 * 2**0, 4 * 2**(1.0 / 3.0), 4 * 2**(2.0 / 3.0))
aspects = (0.5, 1.0, 2.0)
class assign:
allowed_border = 9999
pos_thr = 0.5
neg_thr = 0.5
min_pos_thr = 0.0
class sample:
image_anchor = None
pos_fraction = None
class RenameParam:
mapping = dict(image="data")
from core.detection_input import ReadRoiRecord, Resize2DImageBbox, \
ConvertImageFromHwcToChw, Flip2DImageBbox, Pad2DImageBbox, \
RenameRecord
from models.NASFPN.input import RandResizeCrop2DImageBbox, ResizeCrop2DImageBbox
from models.retinanet.input import PyramidAnchorTarget2D, Norm2DImage, \
AverageFgCount
if is_train:
transform = {
"sample": [
ReadRoiRecord(None),
Norm2DImage(NormParam),
RandResizeCrop2DImageBbox(ResizeParam),
Flip2DImageBbox(),
Pad2DImageBbox(PadParam),
ConvertImageFromHwcToChw(),
PyramidAnchorTarget2D(AnchorTarget2DParam()),
RenameRecord(RenameParam.mapping)
],
"batch": [AverageFgCount("rpn_fg_count")]
}
data_name = ["data"]
label_name = [
"rpn_cls_label", "rpn_fg_count", "rpn_reg_target", "rpn_reg_weight"
]
else:
transform = [
ReadRoiRecord(None),
Norm2DImage(NormParam),
ResizeCrop2DImageBbox(ResizeParam),
Pad2DImageBbox(PadParam),
ConvertImageFromHwcToChw(),
RenameRecord(RenameParam.mapping)
]
data_name = ["data", "im_info", "im_id", "rec_id"]
label_name = []
from models.retinanet import metric
rpn_acc_metric = metric.FGAccMetric("FGAcc", ["cls_loss_output"],
["rpn_cls_label"])
metric_list = [rpn_acc_metric]
return General, KvstoreParam, RpnParam, RoiParam, BboxParam, DatasetParam, \
ModelParam, OptimizeParam, TestParam, \
transform, data_name, label_name, metric_list
def get_config(is_train):
class General:
log_frequency = 10
name = __name__.rsplit("/")[-1].rsplit(".")[-1]
batch_image = 2 if is_train else 1
fp16 = False
class KvstoreParam:
kvstore = "nccl"
batch_image = General.batch_image
gpus = [0, 1, 2, 3, 4, 5, 6, 7]
fp16 = General.fp16
class NormalizeParam:
normalizer = normalizer_factory(type="fixbn")
class BackboneParam:
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
class NeckParam:
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
class RpnParam:
num_class = 1 + 80
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
batch_image = General.batch_image
class anchor_generate:
scale = (4 * 2**0, 4 * 2**(1.0 / 3.0), 4 * 2**(2.0 / 3.0))
ratio = (0.5, 1.0, 2.0)
stride = (8, 16, 32, 64, 128)
max_side = 1440
class anchor_assign:
allowed_border = 9999
bbox_thr = 0.6
pre_anchor_top_n = 50
class head:
conv_channel = 256
mean = (.0, .0, .0, .0)
std = (0.1, 0.1, 0.2, 0.2)
class proposal:
pre_nms_top_n = 1000
post_nms_top_n = None
nms_thr = None
min_bbox_side = None
class subsample_proposal:
proposal_wo_gt = None
image_roi = None
fg_fraction = None
fg_thr = None
bg_thr_hi = None
bg_thr_lo = None
class bbox_target:
num_reg_class = None
class_agnostic = None
weight = None
mean = None
std = None
class focal_loss:
alpha = 0.5
gamma = 2.0
class BboxParam:
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
num_class = None
image_roi = None
batch_image = None
class regress_target:
class_agnostic = None
mean = None
std = None
class RoiParam:
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
out_size = None
stride = None
class DatasetParam:
if is_train:
image_set = ("coco_train2017", )
else:
image_set = ("coco_val2017", )
backbone = Backbone(BackboneParam)
neck = Neck(NeckParam)
rpn_head = RpnHead(RpnParam)
detector = Detector()
if is_train:
train_sym = detector.get_train_symbol(backbone, neck, rpn_head)
test_sym = None
else:
train_sym = None
test_sym = detector.get_test_symbol(backbone, neck, rpn_head)
class ModelParam:
train_symbol = train_sym
test_symbol = test_sym
from_scratch = False
random = True
memonger = False
memonger_until = "stage3_unit21_plus"
class pretrain:
prefix = "pretrain_model/resnet-v1-101"
epoch = 0
fixed_param = ["conv0", "stage1", "gamma", "beta"]
def process_weight(sym, arg, aux):
for stride in RpnParam.anchor_generate.stride:
add_anchor_to_arg(sym, arg, aux,
RpnParam.anchor_generate.max_side, stride,
RpnParam.anchor_generate.scale,
RpnParam.anchor_generate.ratio)
class OptimizeParam:
class optimizer:
type = "sgd"
lr = 0.005 / 8 * len(KvstoreParam.gpus) * KvstoreParam.batch_image
momentum = 0.9
wd = 0.0001
clip_gradient = 35
class schedule:
begin_epoch = 0
end_epoch = 6
lr_iter = [
60000 * 16 //
(len(KvstoreParam.gpus) * KvstoreParam.batch_image), 80000 *
16 // (len(KvstoreParam.gpus) * KvstoreParam.batch_image)
]
class warmup:
type = "gradual"
lr = 0.005 / 8 * len(
KvstoreParam.gpus) * KvstoreParam.batch_image / 3
iter = 1000
class TestParam:
min_det_score = 0.05 # filter appended boxes
max_det_per_image = 100
def process_roidb(x):
return x # noqa: E704
def process_output(x, y):
return x # noqa: E704
class model:
prefix = "experiments/{}/checkpoint".format(General.name)
epoch = OptimizeParam.schedule.end_epoch
class nms:
type = "nms"
thr = 0.5
class coco:
annotation = "data/coco/annotations/instances_minival2014.json"
# data processing
class NormParam:
mean = (122.7717, 115.9465, 102.9801) # RGB order
std = (1.0, 1.0, 1.0)
class ResizeParam:
short = 800
long = 1333
class PadParam:
short = 800
long = 1333
max_num_gt = 100
class RenameParam:
mapping = dict(image="data")
from core.detection_input import ReadRoiRecord, Resize2DImageBbox, \
ConvertImageFromHwcToChw, Flip2DImageBbox, Pad2DImageBbox, \
RenameRecord
from models.retinanet.input import Norm2DImage
if is_train:
transform = [
ReadRoiRecord(None),
Norm2DImage(NormParam),
Resize2DImageBbox(ResizeParam),
Flip2DImageBbox(),
Pad2DImageBbox(PadParam),
ConvertImageFromHwcToChw(),
RenameRecord(RenameParam.mapping)
]
data_name = ["data"]
label_name = ["gt_bbox", "im_info"]
else:
transform = [
ReadRoiRecord(None),
Norm2DImage(NormParam),
Resize2DImageBbox(ResizeParam),
ConvertImageFromHwcToChw(),
RenameRecord(RenameParam.mapping)
]
data_name = ["data", "im_info", "im_id", "rec_id"]
label_name = []
import core.detection_metric as metric
pos_loss = metric.ScalarLoss("PosLoss", ["positive_loss_output"], [])
neg_loss = metric.ScalarLoss("NegLoss", ["negative_loss_output"], [])
metric_list = [pos_loss, neg_loss]
return General, KvstoreParam, RpnParam, RoiParam, BboxParam, DatasetParam, \
ModelParam, OptimizeParam, TestParam, \
transform, data_name, label_name, metric_list