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
depth = 50
class NeckParam:
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
class RpnParam:
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
batch_image = General.batch_image
class anchor_generate:
scale = (8, )
ratio = (0.5, 1.0, 2.0)
stride = (4, 8, 16, 32, 64)
image_anchor = 256
class head:
conv_channel = 256
mean = (0, 0, 0, 0)
std = (1, 1, 1, 1)
class proposal:
pre_nms_top_n = 2000 if is_train else 1000
post_nms_top_n = 2000 if is_train else 1000
nms_thr = 0.7
min_bbox_side = 0
class subsample_proposal:
proposal_wo_gt = False
image_roi = 512
fg_fraction = 0.25
fg_thr = 0.5
bg_thr_hi = 0.5
bg_thr_lo = 0.0
class bbox_target:
num_reg_class = 81
class_agnostic = False
weight = (1.0, 1.0, 1.0, 1.0)
mean = (0.0, 0.0, 0.0, 0.0)
std = (0.1, 0.1, 0.2, 0.2)
class BboxParam:
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
num_class = 1 + 80
image_roi = 512
batch_image = General.batch_image
class regress_target:
class_agnostic = False
mean = (0.0, 0.0, 0.0, 0.0)
std = (0.1, 0.1, 0.2, 0.2)
class RoiParam:
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
out_size = 7
stride = (4, 8, 16, 32)
roi_canonical_scale = 224
roi_canonical_level = 4
class KDParam:
stage = 'c5'
channel = 2048
grad_scale = 5
class DatasetParam:
if is_train:
image_set = ("coco_train2017", )
else:
image_set = ("coco_val2017", )
backbone = Backbone(BackboneParam)
neck = Neck(NeckParam)
rpn_head = RpnHead(RpnParam)
roi_extractor = RoiExtractor(RoiParam)
bbox_head = BboxHead(BboxParam)
kd_head = KDHead(KDParam)
detector = Detector()
if is_train:
train_sym = detector.get_train_symbol(backbone, neck, rpn_head,
roi_extractor, bbox_head,
kd_head)
rpn_test_sym = None
test_sym = None
else:
train_sym = None
rpn_test_sym = detector.get_rpn_test_symbol(backbone, neck, rpn_head)
test_sym = detector.get_test_symbol(backbone, neck, rpn_head,
roi_extractor, bbox_head)
class ModelParam:
train_symbol = train_sym
test_symbol = test_sym
rpn_test_symbol = rpn_test_sym
from_scratch = False
random = True
memonger = False
memonger_until = "stage3_unit21_plus"
class pretrain:
prefix = "pretrain_model/resnet%s_v1b" % BackboneParam.depth
epoch = 0
fixed_param = ["conv0", "stage1", "gamma", "beta"]
class teacher_param:
prefix = 'teacher_model/faster_r152v1b_fpn_2x/checkpoint'
epoch = 12
endpoint = ['stage4_unit3_relu_output']
data_name = ['data']
label_name = ['teacher_label']
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 = 6
lr_iter = [
60000 * 16 //
(len(KvstoreParam.gpus) * KvstoreParam.batch_image), 80000 *
16 // (len(KvstoreParam.gpus) * KvstoreParam.batch_image)
]
class warmup:
type = "gradual"
lr = 0.01 / 8 * len(
KvstoreParam.gpus) * KvstoreParam.batch_image / 3.0
iter = 500
class TestParam:
min_det_score = 0.05
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 = tuple(i * 255 for i in (0.485, 0.456, 0.406)) # RGB order
std = tuple(i * 255 for i in (0.229, 0.224, 0.225))
# data processing
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.stride = (4, 8, 16, 32, 64)
self.short = (200, 100, 50, 25, 13)
self.long = (334, 167, 84, 42, 21)
scales = (8)
aspects = (0.5, 1.0, 2.0)
class assign:
allowed_border = 0
pos_thr = 0.7
neg_thr = 0.3
min_pos_thr = 0.0
class sample:
image_anchor = 256
pos_fraction = 0.5
class RenameParam:
mapping = dict(image="data")
from core.detection_input import ReadRoiRecord, Resize2DImageBbox, \
ConvertImageFromHwcToChw, Flip2DImageBbox, Pad2DImageBbox, \
RenameRecord, Norm2DImage
from models.FPN.input import PyramidAnchorTarget2D
if is_train:
transform = [
ReadRoiRecord(None),
Norm2DImage(NormParam),
Resize2DImageBbox(ResizeParam),
Flip2DImageBbox(),
Pad2DImageBbox(PadParam),
ConvertImageFromHwcToChw(),
PyramidAnchorTarget2D(AnchorTarget2DParam()),
RenameRecord(RenameParam.mapping)
]
data_name = ["data", "im_info", "gt_bbox"]
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 = []
import core.detection_metric as metric
rpn_acc_metric = metric.AccWithIgnore("RpnAcc", ["rpn_cls_loss_output"],
["rpn_cls_label"])
rpn_l1_metric = metric.L1("RpnL1", ["rpn_reg_loss_output"],
["rpn_cls_label"])
# for bbox, the label is generated in network so it is an output
box_acc_metric = metric.AccWithIgnore(
"RcnnAcc", ["bbox_cls_loss_output", "bbox_label_blockgrad_output"], [])
box_l1_metric = metric.L1(
"RcnnL1", ["bbox_reg_loss_output", "bbox_label_blockgrad_output"], [])
scalar_metric = metric.ScalarLoss("fitloss", ["fit_loss_output"], [])
metric_list = [
rpn_acc_metric, rpn_l1_metric, box_acc_metric, box_l1_metric,
scalar_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 = True
loader_worker = 24
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
depth = 50
class NeckParam:
fp16 = General.fp16
normalizer = normalizer_factory(type="localbn")
class RpnParam:
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
batch_image = General.batch_image
nnvm_proposal = True
nnvm_rpn_target = False
class anchor_generate:
scale = (8, )
ratio = (0.5, 1, 2)
stride = (4, 8, 16, 32, 64)
max_side = 1450
class anchor_assign:
allowed_border = 1000
pos_thr = 0.7
neg_thr = 0.3
min_pos_thr = 0.0
image_anchor = 256
pos_fraction = 0.5
class head:
conv_channel = 256
mean = (0, 0, 0, 0)
std = (1, 1, 1, 1)
class proposal:
pre_nms_top_n = 3000 if is_train else 2000
post_nms_top_n = 2000 if is_train else 1000
nms_thr = 0.7
min_bbox_side = 2
class subsample_proposal:
proposal_wo_gt = False
image_roi = 512
fg_fraction = 0.5
fg_thr = 0.5
bg_thr_hi = 0.5
bg_thr_lo = 0.0
class bbox_target:
num_reg_class = 2
class_agnostic = False
weight = (1.0, 1.0, 1.0, 1.0)
mean = (0.0, 0.0, 0.0, 0.0)
std = (0.1, 0.1, 0.2, 0.2)
class BboxParam:
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
num_class = 1 + 1
image_roi = 512
batch_image = General.batch_image
class regress_target:
class_agnostic = False
mean = (0.0, 0.0, 0.0, 0.0)
std = (0.1, 0.1, 0.2, 0.2)
class RoiParam:
fp16 = General.fp16
normalizer = NormalizeParam.normalizer
out_size = 7
stride = (4, 8, 16, 32)
roi_canonical_scale = 224
roi_canonical_level = 4
class DatasetParam:
if is_train:
image_set = ("crowdhuman_train", )
else:
image_set = ("crowdhuman_val", )
backbone = Backbone(BackboneParam)
neck = Neck(NeckParam)
rpn_head = RpnHead(RpnParam)
roi_extractor = RoiExtractor(RoiParam)
bbox_head = BboxHead(BboxParam)
detector = Detector()
if is_train:
train_sym = detector.get_train_symbol(backbone, neck, rpn_head,
roi_extractor, bbox_head)
rpn_test_sym = None
test_sym = None
else:
train_sym = None
rpn_test_sym = detector.get_rpn_test_symbol(backbone, neck, rpn_head)
test_sym = detector.get_test_symbol(backbone, neck, rpn_head,
roi_extractor, bbox_head)
class ModelParam:
train_symbol = train_sym
test_symbol = test_sym
rpn_test_symbol = rpn_test_sym
from_scratch = False
random = True
memonger = False
memonger_until = "stage3_unit21_plus"
class pretrain:
prefix = "pretrain_model/resnet%s_v1b" % BackboneParam.depth
epoch = 0
fixed_param = [
"conv0", "stage1", "bn_gamma", "bn_beta", "bn0", "bn1", "bn2",
"bn3", "bn4"
]
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 = 0.01 / 8 * len(KvstoreParam.gpus) * KvstoreParam.batch_image
momentum = 0.9
wd = 0.0001
clip_gradient = None
class schedule:
begin_epoch = 0
end_epoch = 10
lr_iter = [
14960 * 16 //
(len(KvstoreParam.gpus) * KvstoreParam.batch_image), 17765 *
16 // (len(KvstoreParam.gpus) * KvstoreParam.batch_image)
]
class warmup:
type = "gradual"
lr = 0.01 / 8 * len(
KvstoreParam.gpus) * KvstoreParam.batch_image / 3.0
iter = 500
class TestParam:
min_det_score = 0.05
max_det_per_image = 300
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 = "/mnt/truenas/scratch/czh/data/crowdhuman/annotations/annotation_val.json"
# data processing
class NormParam:
mean = tuple(i * 255 for i in (0.485, 0.456, 0.406)) # RGB order
std = tuple(i * 255 for i in (0.229, 0.224, 0.225))
# data processing
class ResizeParam:
short = 800
long = 1400
class PadParam:
short = 800
long = 1400
max_num_gt = 500
class AnchorTarget2DParam:
def __init__(self):
self.generate = self._generate()
class _generate:
def __init__(self):
self.stride = (4, 8, 16, 32, 64)
self.short = (200, 100, 50, 25, 13)
self.long = (350, 175, 88, 44, 22)
scales = (8)
aspects = RpnParam.anchor_generate.ratio
class assign:
allowed_border = 1000
pos_thr = 0.7
neg_thr = 0.3
min_pos_thr = 0.0
class sample:
image_anchor = 256
pos_fraction = 0.5
class RenameParam:
mapping = dict(image="data")
from core.detection_input import ReadRoiRecord, Resize2DImageBbox, \
ConvertImageFromHwcToChw, Flip2DImageBbox, Pad2DImageBbox, \
RenameRecord, Norm2DImage
from models.crowdhuman.input import PyramidAnchorTarget2D
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"]
if not RpnParam.nnvm_rpn_target:
transform.append(PyramidAnchorTarget2D(AnchorTarget2DParam()))
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 = []
import core.detection_metric as metric
rpn_acc_metric = metric.AccWithIgnore(
"RpnAcc", ["rpn_cls_loss_output", "rpn_cls_label_blockgrad_output"],
[])
rpn_l1_metric = metric.L1(
"RpnL1", ["rpn_reg_loss_output", "rpn_cls_label_blockgrad_output"], [])
emd_metric = metric.ScalarLoss("emd", [
'cls_reg_loss_output',
], [])
metric_list = [rpn_acc_metric, rpn_l1_metric, emd_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