def generate(self):
model_path = os.path.expanduser(self.model_path)
assert model_path.endswith('.h5'), 'Keras model or weights must be a .h5 file.'
#---------------------------#
# 载入模型与权值
#---------------------------#
self.model = siamese(self.input_shape)
self.model.load_weights(self.model_path)
print('{} model loaded.'.format(model_path))
def generate(self):
model_path = os.path.expanduser(self.model_path)
assert model_path.endswith(
'.h5'), 'Keras model or weights must be a .h5 file.'
self.model = siamese(self.input_shape)
self.model.load_weights(self.model_path)
self.model.summary()
print('{} model, anchors, and classes loaded.'.format(model_path))
def generate(self):
print('Loading weights into state dict...')
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = siamese(self.input_shape)
model.load_state_dict(torch.load(self.model_path, map_location=device))
self.net = model.eval()
print('{} model, anchors, and classes loaded.'.format(self.model_path))
if self.cuda:
self.net = torch.nn.DataParallel(self.net)
cudnn.benchmark = True
self.net = self.net.cuda()
dataset_path = "datasets"
#----------------------------------------------------#
# 训练好的权值保存在logs文件夹里面
#----------------------------------------------------#
log_dir = "logs/"
#----------------------------------------------------#
# 输入图像的大小，默认为105,105,3
#----------------------------------------------------#
input_shape = [105,105,3]
#----------------------------------------------------#
# 训练自己的数据的话需要把train_own_data设置成true
# 训练自己的数据和训练omniglot数据格式不一样
#----------------------------------------------------#
train_own_data = False
model = siamese(input_shape)
#------------------------------------------------------#
# 权值文件请看README，百度网盘下载
#------------------------------------------------------#
model_path = 'model_data/vgg16_weights_tf_dim_ordering_tf_kernels_notop.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
#-------------------------------------------------------------------------------#
tensorboard = TensorBoard(log_dir=log_dir)
checkpoint_period = ModelCheckpoint(log_dir + 'ep{epoch:03d}-loss{loss:.3f}-val_loss{val_loss:.3f}.h5',
