NUM_CLASSES = 21
input_shape = (300, 300, 3)
priors = get_anchors()
bbox_util = BBoxUtility(NUM_CLASSES, priors)
# 0.1用于验证，0.9用于训练
val_split = 0.1
with open(annotation_path) as f:
lines = f.readlines()
np.random.seed(10101)
np.random.shuffle(lines)
np.random.seed(None)
num_val = int(len(lines)*val_split)
num_train = len(lines) - num_val
model = SSD300(input_shape, num_classes=NUM_CLASSES)
#------------------------------------------------------#
# 权值文件请看README，百度网盘下载
# 训练自己的数据集时提示维度不匹配正常
# 预测的东西都不一样了自然维度不匹配
#------------------------------------------------------#
model.load_weights('model_data/mobilenet_ssd_weights.h5', by_name=True, skip_mismatch=True)
# 训练参数设置
logging = TensorBoard(log_dir=log_dir)
checkpoint = ModelCheckpoint(log_dir + 'ep{epoch:03d}-loss{loss:.3f}-val_loss{val_loss:.3f}.h5',
monitor='val_loss', save_weights_only=True, save_best_only=True, period=1)
reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.5, patience=3, verbose=1)
early_stopping = EarlyStopping(monitor='val_loss', min_delta=0, patience=10, verbose=1)
BATCH_SIZE = 16
gen = Generator(bbox_util, BATCH_SIZE, lines[:num_train], lines[num_train:],
strategy = tf.distribute.MirroredStrategy()
else:
strategy = None
print('Number of devices: {}'.format(ngpus_per_node))
#----------------------------------------------------#
# 获取classes和anchor
#----------------------------------------------------#
class_names, num_classes = get_classes(classes_path)
num_classes += 1
anchors = get_anchors(input_shape, anchors_size)
if ngpus_per_node > 1:
with strategy.scope():
model = SSD300((input_shape[0], input_shape[1], 3),
num_classes,
weight_decay=weight_decay)
if model_path != '':
#------------------------------------------------------#
# 载入预训练权重
#------------------------------------------------------#
print('Load weights {}.'.format(model_path))
model.load_weights(model_path,
by_name=True,
skip_mismatch=True)
else:
model = SSD300((input_shape[0], input_shape[1], 3),
num_classes,
weight_decay=weight_decay)
if model_path != '':
#------------------------------------------------------#
# 这样也可以用比较大的图片训练，对于小目标有好处
#----------------------------------------------------#
input_shape = [300, 300, 3]
#----------------------------------------------------#
# 可用于设定先验框的大小，默认的anchors_size
# 是根据voc数据集设定的，大多数情况下都是通用的！
# 如果想要检测小物体，可以修改anchors_size
# 一般调小浅层先验框的大小就行了！因为浅层负责小物体检测！
# 比如anchors_size = [21,45,99,153,207,261,315]
#----------------------------------------------------#
anchors_size = [30, 60, 111, 162, 213, 264, 315]
priors = get_anchors((input_shape[0], input_shape[1]), anchors_size)
bbox_util = BBoxUtility(NUM_CLASSES, priors)
model = SSD300(input_shape, NUM_CLASSES, anchors_size)
#------------------------------------------------------#
# 权值文件请看README，百度网盘下载
# 训练自己的数据集时提示维度不匹配正常
# 预测的东西都不一样了自然维度不匹配
#------------------------------------------------------#
model_path = 'model_data/essay_mobilenet_ssd_weights.h5'
model.load_weights(model_path, by_name=True, skip_mismatch=True)
#-------------------------------------------------------------------------------#
# 训练参数的设置
# logging表示tensorboard的保存地址
# checkpoint用于设置权值保存的细节，period用于修改多少epoch保存一次
# reduce_lr用于设置学习率下降的方式
# early_stopping用于设定早停，val_loss多次不下降自动结束训练，表示模型基本收敛
#-------------------------------------------------------------------------------#
log_dir = "logs/" # use for tensorboard
annotation_path = 'train.txt'
ssd_params = SSD_PARAMS(
img_shape=(300, 300, 3), # last channel,
num_classes=2,
val_split=0.1)
priors = get_anchors()
bbox_util = BBoxUtility(ssd_params.num_classes, priors)
with open(annotation_path) as f:
lines = f.readlines()
np.random.shuffle(lines)
num_val = int(len(lines) * ssd_params.val_split)
num_train = len(lines) - num_val
model = SSD300(ssd_params.img_shape, num_classes=ssd_params.num_classes)
#model.load_weights('model_data/ssd_weights.h5', by_name=True, skip_mismatch=True)
logging = TensorBoard(log_dir=log_dir) # user for visdom
checkPoint = ModelCheckpoint(
log_dir + 'ep{epoch:03d}-loss{loss:.3f}-val_loss{val_loss:.3f}.h5',
monitor='val_loss',
save_weights_only=True,
save_best_only=True,
period=10)
reduce_lr = ReduceLROnPlateau(monitor='val_loss',
factor=0.5,
patience=2,
verbose=1)
early_stopping = EarlyStopping(monitor='val_loss',
min_delta=0,
