这篇文章跟大家分享下THOR的实践应用。THOR算法的部分内容当前已经在MindSpore中开源，源码位置：
https://gitee.com/mindspore/mindspore/blob/master/mindspore/nn/optim/thor.py
MindSpore中使用THOR训练网络非常简单，下面用四行代码先来带大家看一下怎么使用。
from mindspore.nn.optim import THOR #引用二阶优化器
#创建网络
net = Net()
#调用优化器
opt = THOR(net, lr, Tensor(damping), config.momentum, config.weight_decay, config.loss_scale,
config.batch_size, split_indices=split_indices)
#增加计算图提升性能
model = ConvertModelUtils().convert_to_thor_model(model=model, network=net, loss_fn=loss, optimizer=opt,
loss_scale_manager=loss_scale, metrics={'acc'}, amp_level="O2", keep_batchnorm_fp32=False,
frequency=config.frequency)
#训练网络
model.train(config.epoch_size, dataset, callbacks=cb, sink_size=dataset.get_dataset_size(), dataset_sink_mode=True)
class THOR_Ascend(Optimizer):
def __init__(self, net, learning_rate, damping, momentum, weight_decay=0.0, loss_scale=1.0, batch_size=32,
decay_filter=lambda x: x.name not in [], split_indices=None):
params = filter(lambda x: x.requires_grad, net.get_parameters())
super(THOR_Ascend, self).__init__(learning_rate, params, weight_decay, loss_scale)
if isinstance(momentum, float) and momentum < 0.0:
raise ValueError("momentum should be at least 0.0, but got momentum {}".format(momentum))
self.momentum = Parameter(Tensor(momentum, mstype.float32), name="momentum")
self.params = self.parameters
self.moments = self.params.clone(prefix="moments", init='zeros')
self.hyper_map = C.HyperMap()
self.opt = P.ApplyMomentum()
self.net = net
self.matrix_A_cov = ParameterTuple(filter(lambda x: 'matrix_A' in x.name, net.get_parameters()))
self.matrix_G_cov = ParameterTuple(filter(lambda x: 'matrix_G' in x.name, net.get_parameters()))
...
def _get_Ainv_Ginv_Amax_Gmax_list(self, gradients, damping_step, matrix_a_allreduce, matrix_g_allreduce,
matrix_a_max_allreduce, matrix_g_max_allreduce):
"""get matrixA inverse list, matrixG inverse list, matrixA_max list, matrixG_max list"""
for i in range(len(self.params)):
thor_layer_count = self.weight_fim_idx_map[i]
conv_layer_count = self.weight_conv_idx_map[i]
layer_type = self.weight_layerType_idx_map[i]
if layer_type in [Conv, FC, Embedding]:
g = gradients[i]
matrix_A = self.matrix_A_cov[thor_layer_count]
matrix_G = self.matrix_G_cov[thor_layer_count]
matrix_A = F.depend(matrix_A, g)
matrix_G = F.depend(matrix_G, g)
A_shape = self.shape(matrix_A)
A_eye = self.eye(A_shape[0], A_shape[0], mstype.float32)
G_shape = self.shape(matrix_G)
G_eye = self.eye(G_shape[0], G_shape[0], mstype.float32)
if layer_type == Conv:
...
elif layer_type == FC:
matrix_A = matrix_A + damping * A_eye
matrix_A_inv = self.cholesky(matrix_A)
matrix_A_inv = self.vector_matmul(matrix_A_inv, matrix_A_inv)
def _get_second_gradients(self, new_grads, damping_step, gradients):
"""get second gradients for thor"""
params_len = len(self.params)
for i in range(params_len):
...
else:
...
elif layer_type == FC:
temp_a = self.matrix_A_cov[thor_layer_count]
temp_g = self.matrix_G_cov[thor_layer_count]
temp_a = self.cast(temp_a, mstype.float16)
temp_g = self.cast(temp_g, mstype.float16)
g = self.cast(g, mstype.float16)
g = self.matmul(temp_g, g)
g = self.matmul(g, temp_a)
g = self.cast(g, mstype.float32)
def construct(self, gradients):
params = self.params
moments = self.moments
damping_step = self.gather(self.damping, self.cov_step, self.axis)
damping_step = self.cast(damping_step, mstype.float32)
if self.thor:
matrix_A_allreduce = ()
matrix_G_allreduce = ()
matrix_A_max_allreduce = ()
matrix_G_max_allreduce = ()
matrix_A_allreduce, matrix_G_allreduce, matrix_A_max_allreduce, matrix_G_max_allreduce = \
self._get_Ainv_Ginv_Amax_Gmax_list(gradients, damping_step, matrix_A_allreduce, matrix_G_allreduce,
matrix_A_max_allreduce, matrix_G_max_allreduce) #计算A/G的逆
...
new_grads = ()
for i in range(len(self.params)):
...
if self.conv_layer_count > 0:#有卷积层时的处理
...
else: #都是全连接层时的处理
if layer_type == Embedding:
...
elif layer_type == FC:
temp_a = matrix_A_allreduce[thor_layer_count]
temp_g = matrix_G_allreduce[thor_layer_count]
fake_A = self.assign(self.matrix_A_cov[thor_layer_count], temp_a)
fake_G = self.assign(self.matrix_G_cov[thor_layer_count], temp_g)
g = F.depend(g, fake_A)#确保执行顺序
g = F.depend(g, fake_G)
temp_a = self.cast(temp_a, mstype.float16)
temp_g = self.cast(temp_g, mstype.float16)
g = self.cast(g, mstype.float16)
g = self.matmul(temp_g, g)
g = self.matmul(g, temp_a)#将一阶方向变为二阶方向
g = self.cast(g, mstype.float32)
elif layer_type == LayerNorm:
g = self._process_layernorm(damping_step, g)
new_grads = new_grads + (g,)
gradients = new_grads #计算后得到的更新方向
else: #该分支表示使用过时二阶信息更新参数
new_grads = ()
gradients = self._get_second_gradients(new_grads, damping_step, gradients) #调用_get_second_gradients函数计算方向THOR的实践应用
在这一节中跟大家分享下THOR的实践应用，举了两个例子分别为ResNet50和BERT，这两个例子的代码也已开源，链接如下：
ResNet50:https://gitee.com/mindspore/mindspore/blob/master/model_zoo/official/cv/resnet/train.py
BERT:
https://gitee.com/mindspore/mindspore/blob/master/model_zoo/official/nlp/bert/run_pretrain.py
ResNet50[1]?
优化器的调用方式与文中开头提到的一致，在这个例子中把具体训练过程给展开了。
首先创建了网络训练需要的训练集和网络定义为ResNet50；
随后设置THOR所需要用到的超参策略，其他超参值设定可去该目录下的src/config.py中修改；
接着创建THOR优化器，并传入设置的超参值；
然后转换模型保存二阶所需信息；
最后就可以训练网络了。
from mindspore.nn.optim import Momentum, THOR #引用二阶优化器
from src.resnet import resnet50 as resnet
from mindspore.train.model import Model
...
if __name__ == '__main__':
...
#创建网络训练过程中的训练集
dataset = create_dataset(dataset_path=args_opt.dataset_path, do_train=True, repeat_num=1,
batch_size=config.batch_size, target=target, distribute=args_opt.run_distribute)
step_size = dataset.get_dataset_size()
#创建resnet50模型
net = resnet(class_num=config.class_num)
...
# init lr
if cfg.optimizer == "Thor":
#设置超参值
from src.lr_generator import get_thor_lr
lr = get_thor_lr(0, config.lr_init, config.lr_decay, config.lr_end_epoch, step_size, decay_epochs=39)
# define loss, model
if target == "Ascend":
if args_opt.dataset == "imagenet2012":
if not config.use_label_smooth:
config.label_smooth_factor = 0.0
loss = CrossEntropySmooth(sparse=True, reduction="mean",
smooth_factor=config.label_smooth_factor, num_classes=config.class_num)
else:
loss = SoftmaxCrossEntropyWithLogits(sparse=True, reduction='mean')
loss_scale = FixedLossScaleManager(config.loss_scale, drop_overflow_update=False)
#高层抽象，集成网络模型的训练和测试
model = Model(net, loss_fn=loss, optimizer=opt, loss_scale_manager=loss_scale, metrics={'acc'},
amp_level="O2", keep_batchnorm_fp32=False)
if cfg.optimizer == "Thor" and args_opt.dataset == "imagenet2012":
from src.lr_generator import get_thor_damping
#设置超参damping
damping = get_thor_damping(0, config.damping_init, config.damping_decay, 70, step_size)
#用于通信时的并行加速
split_indices = [26, 53]
#创建THOR优化器
opt = THOR(net, lr, Tensor(damping), config.momentum, config.weight_decay, config.loss_scale,
config.batch_size, split_indices=split_indices)
#增加计算图提升性能
model = ConvertModelUtils().convert_to_thor_model(model=model, network=net, loss_fn=loss, optimizer=opt,
loss_scale_manager=loss_scale, metrics={'acc'},
amp_level="O2", keep_batchnorm_fp32=False,
frequency=config.frequency)
...
#训练网络
model.train(config.epoch_size - config.pretrain_epoch_size, dataset, callbacks=cb,
sink_size=dataset.get_dataset_size(), dataset_sink_mode=dataset_sink_mode) 
from mindspore.nn.optim import Lamb, Momentum, AdamWeightDecay, THOR #引用二阶优化器
from src import BertNetworkWithLoss
...
def _get_optimizer(args_opt, network):
"""get bert optimizer, support Lamb, Momentum, AdamWeightDecay."""
if cfg.optimizer == 'Lamb':
...
elif cfg.optimizer == "Thor":
from src.utils import get_bert_thor_lr, get_bert_thor_damping
#设置lr和damping的超参值
lr = get_bert_thor_lr(cfg.Thor.lr_max, cfg.Thor.lr_min, cfg.Thor.lr_power, cfg.Thor.lr_total_steps)
damping = get_bert_thor_damping(cfg.Thor.damping_max, cfg.Thor.damping_min, cfg.Thor.damping_power,
cfg.Thor.damping_total_steps)
split_indices = None
#设置并行加速方式
if bert_net_cfg.num_hidden_layers == 12:
if bert_net_cfg.use_relative_positions:
split_indices = [29, 58, 87, 116, 145, 174, 203, 217]
else:
split_indices = [28, 55, 82, 109, 136, 163, 190, 205]
elif bert_net_cfg.num_hidden_layers == 24:
if bert_net_cfg.use_relative_positions:
split_indices = [30, 90, 150, 210, 270, 330, 390, 421]
else:
split_indices = [38, 93, 148, 203, 258, 313, 368, 397]
#创建优化器
optimizer = THOR(network, lr, damping, cfg.Thor.momentum,
cfg.Thor.weight_decay, cfg.Thor.loss_scale, cfg.batch_size,
decay_filter=lambda x: 'layernorm' not in x.name.lower() and 'bias' not in x.name.lower(),
split_indices=split_indices)
...
return optimizer
def run_pretrain():
...
#创建数据集
ds = create_bert_dataset(device_num, rank, args_opt.do_shuffle, args_opt.data_dir, args_opt.schema_dir)
#网络和损失函数创建
net_with_loss = BertNetworkWithLoss(bert_net_cfg, True)
...
#加载初始checkpoint
if args_opt.load_checkpoint_path:
param_dict = load_checkpoint(args_opt.load_checkpoint_path)
load_param_into_net(net_with_loss, param_dict)
#动态loss缩放
if args_opt.enable_lossscale == "true":
...
#固定loss缩放值
else:
#反向过程梯度计算过程创建
net_with_grads = BertTrainOneStepCell(net_with_loss, optimizer=optimizer)
#创建网络
model = Model(net_with_grads)
#增加计算图提升性能
model = ConvertModelUtils().convert_to_thor_model(model, network=net_with_grads, optimizer=optimizer,
frequency=cfg.Thor.frequency)
#网络训练
model.train(new_repeat_count, ds, callbacks=callback,
dataset_sink_mode=(args_opt.enable_data_sink == "true"), sink_size=args_opt.data_sink_steps)
if __name__ == '__main__':
set_seed(0)
run_pretrain()
参考文献：
[1]He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.
[2]Devlin J, Chang M W, Lee K, et al. Bert: Pre-training of deep bidirectional transformers for language understanding[J]. arXiv preprint arXiv:1810.04805, 2018.
?MindSpore 高阶系列文章?
-
优化器的背景↓
技术干货 | 如何用MindSpore优化器加速收敛高度逼近最优值？
-
MindSpore自研优化器的介绍↓