#------------------------------------------------------#
# 主干特征提取网络特征通用，使用预训练权重可以加快训练
# Init_Epoch为起始世代
# Interval_Epoch为中间训练的世代
# Epoch总训练世代
# 提示OOM或者显存不足请调小Batch_size
#------------------------------------------------------#
if True:
lr = 1e-4
Batch_size = 2
Init_Epoch = 0
Interval_Epoch = 50
model_rpn.compile(loss={
'classification': cls_loss(),
'regression': smooth_l1()
},
optimizer=keras.optimizers.Adam(lr=lr))
model_all.compile(loss={
'classification':
cls_loss(),
'regression':
smooth_l1(),
'dense_class_{}'.format(NUM_CLASSES):
class_loss_cls,
'dense_regress_{}'.format(NUM_CLASSES):
class_loss_regr(NUM_CLASSES - 1)
},
optimizer=keras.optimizers.Adam(lr=lr))
# 每个世代训练数据集长度的步数
# 根据数据集大小进行指定
EPOCH_LENGTH = len(lines)
gen = Generator(bbox_util, lines, NUM_CLASSES, solid=True)
rpn_train = gen.generate()
log_dir = "logs"
# 训练参数设置
logging = TensorBoard(log_dir=log_dir)
callback = logging
callback.set_model(model_all)
model_rpn.compile(loss={
'regression': smooth_l1(),
'classification': cls_loss()
},
optimizer=keras.optimizers.Adam(lr=Learning_rate))
model_classifier.compile(
loss=[class_loss_cls, class_loss_regr(NUM_CLASSES - 1)],
metrics={'dense_class_{}'.format(NUM_CLASSES): 'accuracy'},
optimizer=keras.optimizers.Adam(lr=Learning_rate))
model_all.compile(optimizer='sgd', loss='mae')
# 初始化参数
iter_num = 0
train_step = 0
losses = np.zeros((EPOCH_LENGTH, 5))
rpn_accuracy_rpn_monitor = []
rpn_accuracy_for_epoch = []
start_time = time.time()