bnm_scheduler = BNMomentumScheduler(detector, bn_lambda=bn_lbmd, last_epoch=-1)
def get_current_lr(epoch):
lr = BASE_LEARNING_RATE
for i, lr_decay_epoch in enumerate(LR_DECAY_STEPS):
if epoch >= lr_decay_epoch:
lr *= LR_DECAY_RATES[i]
return lr
def adjust_learning_rate(optimizer, epoch):
lr = get_current_lr(epoch)
for param_group in optimizer.param_groups:
param_group['lr'] = lr
# TFBoard Visualizers
TRAIN_VISUALIZER = TfVisualizer(LOG_DIR, 'train')
TEST_VISUALIZER = TfVisualizer(LOG_DIR, 'test')
# Used for Pseudo box generation and AP calculation
CONFIG_DICT = {'dataset_config': DATASET_CONFIG,
'remove_empty_box': False, 'use_3d_nms': True,
'nms_iou': 0.25, 'use_old_type_nms': False, 'cls_nms': True,
'per_class_proposal': True, 'conf_thresh': 0.05}
print('************************** GLOBAL CONFIG END **************************')
# ------------------------------------------------------------------------- GLOBAL CONFIG END
def update_ema_variables(model, ema_model, alpha, global_step):
# Use the true average until the exponential average is more correct
alpha = min(1 - 1 / (global_step + 1), alpha)
for ema_param, param in zip(ema_model.parameters(), model.parameters()):
def get_current_lr(epoch):
lr = BASE_LEARNING_RATE
for i, lr_decay_epoch in enumerate(LR_DECAY_STEPS):
if epoch >= lr_decay_epoch:
lr *= LR_DECAY_RATES[i]
return lr
def adjust_learning_rate(optimizer, epoch):
lr = get_current_lr(epoch)
for param_group in optimizer.param_groups:
param_group['lr'] = lr
# TFBoard Visualizers
TRAIN_VISUALIZER = TfVisualizer(FLAGS, 'train')
TEST_VISUALIZER = TfVisualizer(FLAGS, 'test')
# Used for AP calculation
CONFIG_DICT = {
'remove_empty_box': False,
'use_3d_nms': True,
'nms_iou': 0.25,
'use_old_type_nms': False,
'cls_nms': True,
'per_class_proposal': True,
'conf_thresh': 0.05,
'dataset_config': DATASET_CONFIG
}
# ------------------------------------------------------------------------- GLOBAL CONFIG END
def get_current_lr(epoch):
lr = BASE_LEARNING_RATE
for i, lr_decay_epoch in enumerate(LR_DECAY_STEPS):
if epoch >= lr_decay_epoch:
lr *= LR_DECAY_RATES[i]
return lr
def adjust_learning_rate(optimizer, epoch):
lr = get_current_lr(epoch)
for param_group in optimizer.param_groups:
param_group["lr"] = lr
# TFBoard Visualizers
TRAIN_VISUALIZER = TfVisualizer(FLAGS, "train")
TEST_VISUALIZER = TfVisualizer(FLAGS, "test")
# Used for AP calculation
CONFIG_DICT = {
"remove_empty_box": False,
"use_3d_nms": True,
"nms_iou": 0.25,
"use_old_type_nms": False,
"cls_nms": True,
"per_class_proposal": True,
"conf_thresh": 0.05,
"dataset_config": DATASET_CONFIG,
}
# ------------------------------------------------------------------------- GLOBAL CONFIG END