def train_net(image_set, year, root_path, devkit_path, pretrained, epoch,
prefix, ctx, begin_epoch, end_epoch, frequent, kv_store, work_load_list=None, resume=False):
# set up logger
logger = logging.getLogger()
logger.setLevel(logging.INFO)
# load symbol
sym = get_vgg_rpn()
feat_sym = get_vgg_rpn().get_internals()['rpn_cls_score_output']
# setup multi-gpu
config.TRAIN.BATCH_IMAGES *= len(ctx)
config.TRAIN.BATCH_SIZE *= len(ctx)
# load training data
voc, roidb = load_gt_roidb(image_set, year, root_path, devkit_path, flip=True)
train_data = AnchorLoader(feat_sym, roidb, batch_size=config.TRAIN.BATCH_SIZE, shuffle=True, mode='train',
ctx=ctx, work_load_list=work_load_list)
# infer max shape
max_data_shape = [('data', (1, 3, 1000, 1000))]
max_data_shape_dict = {k: v for k, v in max_data_shape}
_, feat_shape, _ = feat_sym.infer_shape(**max_data_shape_dict)
from rcnn.minibatch import assign_anchor
import numpy as np
label = assign_anchor(feat_shape[0], np.zeros((0, 5)), [[1000, 1000, 1.0]])
max_label_shape = [('label', label['label'].shape),
('bbox_target', label['bbox_target'].shape),
('bbox_inside_weight', label['bbox_inside_weight'].shape),
('bbox_outside_weight', label['bbox_outside_weight'].shape)]
print 'providing maximum shape', max_data_shape, max_label_shape
# load pretrained
args, auxs = load_param(pretrained, epoch, convert=True)
# initialize params
if not resume:
arg_shape, _, _ = sym.infer_shape(data=(1, 3, 224, 224))
arg_shape_dict = dict(zip(sym.list_arguments(), arg_shape))
args['rpn_conv_3x3_weight'] = mx.random.normal(mean=0, stdvar=0.01, shape=arg_shape_dict['rpn_conv_3x3_weight'])
args['rpn_conv_3x3_bias'] = mx.nd.zeros(shape=arg_shape_dict['rpn_conv_3x3_bias'])
args['rpn_cls_score_weight'] = mx.random.normal(mean=0, stdvar=0.01, shape=arg_shape_dict['rpn_cls_score_weight'])
args['rpn_cls_score_bias'] = mx.nd.zeros(shape=arg_shape_dict['rpn_cls_score_bias'])
args['rpn_bbox_pred_weight'] = mx.random.normal(mean=0, stdvar=0.01, shape=arg_shape_dict['rpn_bbox_pred_weight'])
args['rpn_bbox_pred_bias'] = mx.nd.zeros(shape=arg_shape_dict['rpn_bbox_pred_bias'])
# train
solver = Solver(prefix, sym, ctx, begin_epoch, end_epoch, kv_store, args, auxs, momentum=0.9, wd=0.0005,
learning_rate=1e-3, lr_scheduler=mx.lr_scheduler.FactorScheduler(60000, 0.1),
mutable_data_shape=True, max_data_shape=max_data_shape, max_label_shape=max_label_shape)
solver.fit(train_data, frequent=frequent)
def train_rpn(image_set, year, root_path, devkit_path, pretrained, epoch,
prefix, ctx, begin_epoch, end_epoch, frequent, kv_store, work_load_list=None, resume=False):
# set up logger
logger = logging.getLogger()
logger.setLevel(logging.INFO)
# load symbol
sym = get_vgg_rpn()
feat_sym = get_vgg_rpn().get_internals()['rpn_cls_score_output']
# setup multi-gpu
config.TRAIN.BATCH_IMAGES *= len(ctx)
config.TRAIN.BATCH_SIZE *= len(ctx)
# load training data
voc, roidb = load_gt_roidb(image_set, year, root_path, devkit_path, flip=True)
train_data = AnchorLoader(feat_sym, roidb, batch_size=config.TRAIN.BATCH_SIZE, shuffle=True, mode='train',
ctx=ctx, work_load_list=work_load_list)
# infer max shape
max_data_shape = [('data', (config.TRAIN.BATCH_SIZE, 3, 1000, 1000))]
max_data_shape_dict = {k: v for k, v in max_data_shape}
_, feat_shape, _ = feat_sym.infer_shape(**max_data_shape_dict)
from rcnn.minibatch import assign_anchor
import numpy as np
label = assign_anchor(feat_shape[0], np.zeros((0, 5)), [[1000, 1000, 1.0]])
max_label_shape = [('label', label['label'].shape),
('bbox_target', label['bbox_target'].shape),
('bbox_inside_weight', label['bbox_inside_weight'].shape),
('bbox_outside_weight', label['bbox_outside_weight'].shape)]
print 'providing maximum shape', max_data_shape, max_label_shape
# load pretrained
args, auxs = load_param(pretrained, epoch, convert=True)
# initialize params
if not resume:
input_shapes = {k: v for k, v in train_data.provide_data + train_data.provide_label}
arg_shape, _, _ = sym.infer_shape(**input_shapes)
arg_shape_dict = dict(zip(sym.list_arguments(), arg_shape))
args['rpn_conv_3x3_weight'] = mx.random.normal(0, 0.01, shape=arg_shape_dict['rpn_conv_3x3_weight'])
args['rpn_conv_3x3_bias'] = mx.nd.zeros(shape=arg_shape_dict['rpn_conv_3x3_bias'])
args['rpn_cls_score_weight'] = mx.random.normal(0, 0.01, shape=arg_shape_dict['rpn_cls_score_weight'])
args['rpn_cls_score_bias'] = mx.nd.zeros(shape=arg_shape_dict['rpn_cls_score_bias'])
args['rpn_bbox_pred_weight'] = mx.random.normal(0, 0.01, shape=arg_shape_dict['rpn_bbox_pred_weight'])
args['rpn_bbox_pred_bias'] = mx.nd.zeros(shape=arg_shape_dict['rpn_bbox_pred_bias'])
# prepare training
if config.TRAIN.FINETUNE:
fixed_param_prefix = ['conv1', 'conv2', 'conv3', 'conv4', 'conv5']
else:
fixed_param_prefix = ['conv1', 'conv2']
data_names = [k[0] for k in train_data.provide_data]
label_names = [k[0] for k in train_data.provide_label]
batch_end_callback = Speedometer(train_data.batch_size, frequent=frequent)
epoch_end_callback = mx.callback.do_checkpoint(prefix)
if config.TRAIN.HAS_RPN is True:
eval_metric = AccuracyMetric(use_ignore=True, ignore=-1)
cls_metric = LogLossMetric(use_ignore=True, ignore=-1)
else:
eval_metric = AccuracyMetric()
cls_metric = LogLossMetric()
bbox_metric = SmoothL1LossMetric()
eval_metrics = mx.metric.CompositeEvalMetric()
for child_metric in [eval_metric, cls_metric, bbox_metric]:
eval_metrics.add(child_metric)
optimizer_params = {'momentum': 0.9,
'wd': 0.0005,
'learning_rate': 0.001,
'lr_scheduler': mx.lr_scheduler.FactorScheduler(60000, 0.1),
'rescale_grad': (1.0 / config.TRAIN.BATCH_SIZE)}
# train
mod = MutableModule(sym, data_names=data_names, label_names=label_names,
logger=logger, context=ctx, work_load_list=work_load_list,
max_data_shapes=max_data_shape, max_label_shapes=max_label_shape,
fixed_param_prefix=fixed_param_prefix)
mod.fit(train_data, eval_metric=eval_metrics, epoch_end_callback=epoch_end_callback,
batch_end_callback=batch_end_callback, kvstore=kv_store,
optimizer='sgd', optimizer_params=optimizer_params,
arg_params=args, aux_params=auxs, begin_epoch=begin_epoch, num_epoch=end_epoch)
def train_rpn(
image_set,
year,
root_path,
devkit_path,
pretrained,
epoch,
prefix,
ctx,
begin_epoch,
end_epoch,
frequent,
kv_store,
work_load_list=None,
):
# load symbol
sym = get_vgg_rpn()
feat_sym = get_vgg_rpn().get_internals()["rpn_cls_score_output"]
# setup multi-gpu
config.TRAIN.BATCH_IMAGES *= len(ctx)
config.TRAIN.BATCH_SIZE *= len(ctx)
# load training data
voc, roidb = load_gt_roidb(image_set, year, root_path, devkit_path, flip=True)
train_data = AnchorLoader(
feat_sym,
roidb,
batch_size=config.TRAIN.BATCH_SIZE,
shuffle=True,
mode="train",
ctx=ctx,
work_load_list=work_load_list,
)
# infer max shape
max_data_shape = [("data", (1, 3, 1000, 1000))]
max_data_shape_dict = {k: v for k, v in max_data_shape}
_, feat_shape, _ = feat_sym.infer_shape(**max_data_shape_dict)
from rcnn.minibatch import assign_anchor
import numpy as np
label = assign_anchor(feat_shape[0], np.zeros((0, 5)), [[1000, 1000, 1.0]])
max_label_shape = [
("label", label["label"].shape),
("bbox_target", label["bbox_target"].shape),
("bbox_inside_weight", label["bbox_inside_weight"].shape),
("bbox_outside_weight", label["bbox_outside_weight"].shape),
]
print "providing maximum shape", max_data_shape, max_label_shape
# load pretrained
args, auxs = load_param(pretrained, epoch, convert=True)
# initialize params
arg_shape, _, _ = sym.infer_shape(data=(1, 3, 224, 224))
arg_shape_dict = dict(zip(sym.list_arguments(), arg_shape))
args["rpn_conv_3x3_weight"] = mx.random.normal(mean=0, stdvar=0.01, shape=arg_shape_dict["rpn_conv_3x3_weight"])
args["rpn_conv_3x3_bias"] = mx.nd.zeros(shape=arg_shape_dict["rpn_conv_3x3_bias"])
args["rpn_cls_score_weight"] = mx.random.normal(mean=0, stdvar=0.01, shape=arg_shape_dict["rpn_cls_score_weight"])
args["rpn_cls_score_bias"] = mx.nd.zeros(shape=arg_shape_dict["rpn_cls_score_bias"])
args["rpn_bbox_pred_weight"] = mx.random.normal(mean=0, stdvar=0.01, shape=arg_shape_dict["rpn_bbox_pred_weight"])
args["rpn_bbox_pred_bias"] = mx.nd.zeros(shape=arg_shape_dict["rpn_bbox_pred_bias"])
# train
solver = Solver(
prefix,
sym,
ctx,
begin_epoch,
end_epoch,
kv_store,
args,
auxs,
momentum=0.9,
wd=0.0005,
learning_rate=1e-3,
lr_scheduler=mx.lr_scheduler.FactorScheduler(60000, 0.1),
mutable_data_shape=True,
max_data_shape=max_data_shape,
max_label_shape=max_label_shape,
)
solver.fit(train_data, frequent=frequent)
def train_rpn(image_set,
year,
root_path,
devkit_path,
pretrained,
epoch,
prefix,
ctx,
begin_epoch,
end_epoch,
frequent,
kv_store,
work_load_list=None,
resume=False):
# set up logger
logger = logging.getLogger()
logger.setLevel(logging.INFO)
# load symbol
sym = get_vgg_rpn()
feat_sym = get_vgg_rpn().get_internals()['rpn_cls_score_output']
# setup multi-gpu
config.TRAIN.BATCH_IMAGES *= len(ctx)
config.TRAIN.BATCH_SIZE *= len(ctx)
# load training data
voc, roidb = load_gt_roidb(image_set,
year,
root_path,
devkit_path,
flip=True)
train_data = AnchorLoader(feat_sym,
roidb,
batch_size=config.TRAIN.BATCH_SIZE,
shuffle=True,
mode='train',
ctx=ctx,
work_load_list=work_load_list)
# infer max shape
max_data_shape = [('data', (config.TRAIN.BATCH_SIZE, 3, 1000, 1000))]
max_data_shape_dict = {k: v for k, v in max_data_shape}
_, feat_shape, _ = feat_sym.infer_shape(**max_data_shape_dict)
from rcnn.minibatch import assign_anchor
import numpy as np
label = assign_anchor(feat_shape[0], np.zeros((0, 5)), [[1000, 1000, 1.0]])
max_label_shape = [
('label', label['label'].shape),
('bbox_target', label['bbox_target'].shape),
('bbox_inside_weight', label['bbox_inside_weight'].shape),
('bbox_outside_weight', label['bbox_outside_weight'].shape)
]
print 'providing maximum shape', max_data_shape, max_label_shape
# load pretrained
args, auxs = load_param(pretrained, epoch, convert=True)
# initialize params
if not resume:
input_shapes = {
k: v
for k, v in train_data.provide_data + train_data.provide_label
}
arg_shape, _, _ = sym.infer_shape(**input_shapes)
arg_shape_dict = dict(zip(sym.list_arguments(), arg_shape))
args['rpn_conv_3x3_weight'] = mx.random.normal(
0, 0.01, shape=arg_shape_dict['rpn_conv_3x3_weight'])
args['rpn_conv_3x3_bias'] = mx.nd.zeros(
shape=arg_shape_dict['rpn_conv_3x3_bias'])
args['rpn_cls_score_weight'] = mx.random.normal(
0, 0.01, shape=arg_shape_dict['rpn_cls_score_weight'])
args['rpn_cls_score_bias'] = mx.nd.zeros(
shape=arg_shape_dict['rpn_cls_score_bias'])
args['rpn_bbox_pred_weight'] = mx.random.normal(
0, 0.01, shape=arg_shape_dict['rpn_bbox_pred_weight'])
args['rpn_bbox_pred_bias'] = mx.nd.zeros(
shape=arg_shape_dict['rpn_bbox_pred_bias'])
# prepare training
if config.TRAIN.FINETUNE:
fixed_param_prefix = ['conv1', 'conv2', 'conv3', 'conv4', 'conv5']
else:
fixed_param_prefix = ['conv1', 'conv2']
data_names = [k[0] for k in train_data.provide_data]
label_names = [k[0] for k in train_data.provide_label]
batch_end_callback = Speedometer(train_data.batch_size, frequent=frequent)
epoch_end_callback = mx.callback.do_checkpoint(prefix)
if config.TRAIN.HAS_RPN is True:
eval_metric = AccuracyMetric(use_ignore=True, ignore=-1)
cls_metric = LogLossMetric(use_ignore=True, ignore=-1)
else:
eval_metric = AccuracyMetric()
cls_metric = LogLossMetric()
bbox_metric = SmoothL1LossMetric()
eval_metrics = mx.metric.CompositeEvalMetric()
for child_metric in [eval_metric, cls_metric, bbox_metric]:
eval_metrics.add(child_metric)
optimizer_params = {
'momentum': 0.9,
'wd': 0.0005,
'learning_rate': 0.001,
'lr_scheduler': mx.lr_scheduler.FactorScheduler(60000, 0.1),
'rescale_grad': (1.0 / config.TRAIN.BATCH_SIZE)
}
# train
mod = MutableModule(sym,
data_names=data_names,
label_names=label_names,
logger=logger,
context=ctx,
work_load_list=work_load_list,
max_data_shapes=max_data_shape,
max_label_shapes=max_label_shape,
fixed_param_prefix=fixed_param_prefix)
mod.fit(train_data,
eval_metric=eval_metrics,
epoch_end_callback=epoch_end_callback,
batch_end_callback=batch_end_callback,
kvstore=kv_store,
optimizer='sgd',
optimizer_params=optimizer_params,
arg_params=args,
aux_params=auxs,
begin_epoch=begin_epoch,
num_epoch=end_epoch)
