ShuffleNet网络介绍
ShuffleNetV1是旷视科技提出的一种计算高效的CNN模型,和MobileNet, SqueezeNet等一样主要应用在移动端,所以模型的设计目标就是利用有限的计算资源来达到最好的模型精度。ShuffleNetV1的设计核心是引入了两种操作:Pointwise Group Convolution和Channel Shuffle,这在保持精度的同时大大降低了模型的计算量。因此,ShuffleNetV1和MobileNet类似,都是通过设计更高效的网络结构来实现模型的压缩和加速。
了解ShuffleNet更多详细内容,详见论文ShuffleNet。
如下图所示,ShuffleNet在保持不低的准确率的前提下,将参数量几乎降低到了最小,因此其运算速度较快,单位参数量对模型准确率的贡献非常高。
图片来源:Bianco S, Cadene R, Celona L, et al. Benchmark analysis of representative deep neural network architectures[J]. IEEE access, 2018, 6: 64270-64277.
本次图像分类基于shufflenet轻量模型来训练
数据下载,预处理及训练测试数据划分
from download import download
url = "https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/notebook/datasets/cifar-10-binary.tar.gz"
download(url, "./dataset", kind="tar.gz", replace=True)
import mindspore as ms
from mindspore.dataset import Cifar10Dataset
from mindspore.dataset import vision, transforms
def get_dataset(train_dataset_path, batch_size, usage):
image_trans = []
if usage == "train":
image_trans = [
vision.RandomCrop((32, 32), (4, 4, 4, 4)),
vision.RandomHorizontalFlip(prob=0.5),
vision.Resize((224, 224)),
vision.Rescale(1.0 / 255.0, 0.0),
vision.Normalize([0.4914, 0.4822, 0.4465], [0.2023, 0.1994, 0.2010]),
vision.HWC2CHW()
]
elif usage == "test":
image_trans = [
vision.Resize((224, 224)),
vision.Rescale(1.0 / 255.0, 0.0),
vision.Normalize([0.4914, 0.4822, 0.4465], [0.2023, 0.1994, 0.2010]),
vision.HWC2CHW()
]
label_trans = transforms.TypeCast(ms.int32)
dataset = Cifar10Dataset(train_dataset_path, usage=usage, shuffle=True)
dataset = dataset.map(image_trans, 'image')
dataset = dataset.map(label_trans, 'label')
dataset = dataset.batch(batch_size, drop_remainder=True)
return dataset
dataset = get_dataset("./dataset/cifar-10-batches-bin", 128, "train")
batches_per_epoch = dataset.get_dataset_size()
模型构建
from mindspore import nn
import mindspore.ops as ops
from mindspore import Tensor
class GroupConv(nn.Cell):
def __init__(self, in_channels, out_channels, kernel_size,
stride, pad_mode="pad", pad=0, groups=1, has_bias=False):
super(GroupConv, self).__init__()
self.groups = groups
self.convs = nn.CellList()
for _ in range(groups):
self.convs.append(nn.Conv2d(in_channels // groups, out_channels // groups,
kernel_size=kernel_size, stride=stride, has_bias=has_bias,
padding=pad, pad_mode=pad_mode, group=1, weight_init='xavier_uniform'))
def construct(self, x):
features = ops.split(x, split_size_or_sections=int(len(x[0]) // self.groups), axis=1)
outputs = ()
for i in range(self.groups):
outputs = outputs + (self.convs[i](features[i].astype("float32")),)
out = ops.cat(outputs, axis=1)
return out
class ShuffleV1Block(nn.Cell):
def __init__(self, inp, oup, group, first_group, mid_channels, ksize, stride):
super(ShuffleV1Block, self).__init__()
self.stride = stride
pad = ksize // 2
self.group = group
if stride == 2:
outputs = oup - inp
else:
outputs = oup
self.relu = nn.ReLU()
branch_main_1 = [
GroupConv(in_channels=inp, out_channels=mid_channels,
kernel_size=1, stride=1, pad_mode="pad", pad=0,
groups=1 if first_group else group),
nn.BatchNorm2d(mid_channels),
nn.ReLU(),
]
branch_main_2 = [
nn.Conv2d(mid_channels, mid_channels, kernel_size=ksize, stride=stride,
pad_mode='pad', padding=pad, group=mid_channels,
weight_init='xavier_uniform', has_bias=False),
nn.BatchNorm2d(mid_channels),
GroupConv(in_channels=mid_channels, out_channels=outputs,
kernel_size=1, stride=1, pad_mode="pad", pad=0,
groups=group),
nn.BatchNorm2d(outputs),
]
self.branch_main_1 = nn.SequentialCell(branch_main_1)
self.branch_main_2 = nn.SequentialCell(branch_main_2)
if stride == 2:
self.branch_proj = nn.AvgPool2d(kernel_size=3, stride=2, pad_mode='same')
def construct(self, old_x):
left = old_x
right = old_x
out = old_x
right = self.branch_main_1(right)
if self.group > 1:
right = self.channel_shuffle(right)
right = self.branch_main_2(right)
if self.stride == 1:
out = self.relu(left + right)
elif self.stride == 2:
left = self.branch_proj(left)
out = ops.cat((left, right), 1)
out = self.relu(out)
return out
def channel_shuffle(self, x):
batchsize, num_channels, height, width = ops.shape(x)
group_channels = num_channels // self.group
x = ops.reshape(x, (batchsize, group_channels, self.group, height, width))
x = ops.transpose(x, (0, 2, 1, 3, 4))
x = ops.reshape(x, (batchsize, num_channels, height, width))
return x
class ShuffleNetV1(nn.Cell):
def __init__(self, n_class=1000, model_size='2.0x', group=3):
super(ShuffleNetV1, self).__init__()
print('model size is ', model_size)
self.stage_repeats = [4, 8, 4]
self.model_size = model_size
if group == 3:
if model_size == '0.5x':
self.stage_out_channels = [-1, 12, 120, 240, 480]
elif model_size == '1.0x':
self.stage_out_channels = [-1, 24, 240, 480, 960]
elif model_size == '1.5x':
self.stage_out_channels = [-1, 24, 360, 720, 1440]
elif model_size == '2.0x':
self.stage_out_channels = [-1, 48, 480, 960, 1920]
else:
raise NotImplementedError
elif group == 8:
if model_size == '0.5x':
self.stage_out_channels = [-1, 16, 192, 384, 768]
elif model_size == '1.0x':
self.stage_out_channels = [-1, 24, 384, 768, 1536]
elif model_size == '1.5x':
self.stage_out_channels = [-1, 24, 576, 1152, 2304]
elif model_size == '2.0x':
self.stage_out_channels = [-1, 48, 768, 1536, 3072]
else:
raise NotImplementedError
input_channel = self.stage_out_channels[1]
self.first_conv = nn.SequentialCell(
nn.Conv2d(3, input_channel, 3, 2, 'pad', 1, weight_init='xavier_uniform', has_bias=False),
nn.BatchNorm2d(input_channel),
nn.ReLU(),
)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, pad_mode='same')
features = []
for idxstage in range(len(self.stage_repeats)):
numrepeat = self.stage_repeats[idxstage]
output_channel = self.stage_out_channels[idxstage + 2]
for i in range(numrepeat):
stride = 2 if i == 0 else 1
first_group = idxstage == 0 and i == 0
features.append(ShuffleV1Block(input_channel, output_channel,
group=group, first_group=first_group,
mid_channels=output_channel // 4, ksize=3, stride=stride))
input_channel = output_channel
self.features = nn.SequentialCell(features)
self.globalpool = nn.AvgPool2d(7)
self.classifier = nn.Dense(self.stage_out_channels[-1], n_class)
def construct(self, x):
x = self.first_conv(x)
x = self.maxpool(x)
x = self.features(x)
x = self.globalpool(x)
x = ops.reshape(x, (-1, self.stage_out_channels[-1]))
x = self.classifier(x)
return x
其中shufflent模型基于轻量化模块设计,模型整体结构如下:
ShuffleNet网络结构如下图所示,以输入图像224×224,组数3(g = 3)为例,首先通过数量24,卷积核大小为3×3,stride为2的卷积层,输出特征图大小为112×112,channel为24;然后通过stride为2的最大池化层,输出特征图大小为56×56,channel数不变;再堆叠3个ShuffleNet模块(Stage2, Stage3, Stage4),三个模块分别重复4次、8次、4次,其中每个模块开始先经过一次下采样模块(上图(c)),使特征图长宽减半,channel翻倍(Stage2的下采样模块除外,将channel数从24变为240);随后经过全局平均池化,输出大小为1×1×960
,再经过全连接层和softmax,得到分类概率。
模型训练
import time
import mindspore
import numpy as np
from mindspore import Tensor, nn
from mindspore.train import ModelCheckpoint, CheckpointConfig, TimeMonitor, LossMonitor, Model, Top1CategoricalAccuracy, Top5CategoricalAccuracy
def train():
mindspore.set_context(mode=mindspore.PYNATIVE_MODE, device_target="Ascend")
net = ShuffleNetV1(model_size="2.0x", n_class=10)
loss = nn.CrossEntropyLoss(weight=None, reduction='mean', label_smoothing=0.1)
min_lr = 0.0005
base_lr = 0.05
lr_scheduler = mindspore.nn.cosine_decay_lr(min_lr,
base_lr,
batches_per_epoch*250,
batches_per_epoch,
decay_epoch=250)
lr = Tensor(lr_scheduler[-1])
optimizer = nn.Momentum(params=net.trainable_params(), learning_rate=lr, momentum=0.9, weight_decay=0.00004, loss_scale=1024)
loss_scale_manager = ms.amp.FixedLossScaleManager(1024, drop_overflow_update=False)
model = Model(net, loss_fn=loss, optimizer=optimizer, amp_level="O3", loss_scale_manager=loss_scale_manager)
callback = [TimeMonitor(), LossMonitor()]
save_ckpt_path = "./"
config_ckpt = CheckpointConfig(save_checkpoint_steps=batches_per_epoch, keep_checkpoint_max=5)
ckpt_callback = ModelCheckpoint("shufflenetv1", directory=save_ckpt_path, config=config_ckpt)
callback += [ckpt_callback]
print("============== Starting Training ==============")
start_time = time.time()
# 由于时间原因,epoch = 5,可根据需求进行调整
model.train(5, dataset, callbacks=callback)
use_time = time.time() - start_time
hour = str(int(use_time // 60 // 60))
minute = str(int(use_time // 60 % 60))
second = str(int(use_time % 60))
print("total time:" + hour + "h " + minute + "m " + second + "s")
print("============== Train Success ==============")
if __name__ == '__main__':
train()
训练结果如下:
上面为训练后的loss
对模型进行测试
from mindspore import load_checkpoint, load_param_into_net
def test():
mindspore.set_context(mode=mindspore.GRAPH_MODE, device_target="Ascend")
dataset = get_dataset("./dataset/cifar-10-batches-bin", 128, "test")
net = ShuffleNetV1(model_size="2.0x", n_class=10)
param_dict = load_checkpoint("shufflenetv1-5_390.ckpt")
load_param_into_net(net, param_dict)
net.set_train(False)
loss = nn.CrossEntropyLoss(weight=None, reduction='mean', label_smoothing=0.1)
eval_metrics = {'Loss': nn.Loss(), 'Top_1_Acc': Top1CategoricalAccuracy(),
'Top_5_Acc': Top5CategoricalAccuracy()}
model = Model(net, loss_fn=loss, metrics=eval_metrics)
start_time = time.time()
res = model.eval(dataset, dataset_sink_mode=False)
use_time = time.time() - start_time
hour = str(int(use_time // 60 // 60))
minute = str(int(use_time // 60 % 60))
second = str(int(use_time % 60))
log = "result:" + str(res) + ", ckpt:'" + "./shufflenetv1-5_390.ckpt" \
+ "', time: " + hour + "h " + minute + "m " + second + "s"
print(log)
filename = './eval_log.txt'
with open(filename, 'a') as file_object:
file_object.write(log + '\n')
if __name__ == '__main__':
test()
测试效果如下,代码会报错但是不影响输出结果
教程总结
本次教程是基于轻量化模型来训练一个图像识别深度学习模型,shufflent模型作为轻量化模型的代表,其他的轻量化模型也可以考虑mobilenet,ghostnet等,如果考虑模型性能,也可以使用一个resnet50模型结合量化技术来获得一个精度和推理性能相对较好的图像分类模型。