昇思25天学习打卡营第14天 | ShuffleNet图像分类

文章目录

昇思25天学习打卡营第14天 | ShuffleNet图像分类

ShuffleNet

ShuffleNetV1是旷世科技提出的一种计算高效的CNN模型，这种模型利用有限的计算资源来达到最好的模型精度，主要应用在移动端。

ShuffleNetV1的核心是引入了两种操作：

Pointwise Group Convolution
Channel Shuffle
这两种操作在保持精度的同时大大降低了模型的计算量。

Pointwise Group Convolution

Group Convolution（分组卷积）相对于普通卷积，每一组的卷积核大小为 $in_channels / g ∗ k ∗ k \text{in\_channels} / g * k *k$ ，一共有 $g$ 组，所有组共有 $in_channels / g ∗ k ∗ k ) ∗ out_channels (\text{in\_channels}/g*k*k)*\text{out\_channels}$ 个参数，是正常卷积参数的 $1/ g$ 。
分组卷积的每个卷积核只处理特征图的一部分通道，但输出通道数仍等于卷积核的数量。
shufflenet2

图片来源：Huang G, Liu S, Van der Maaten L, et al. Condensenet: An efficient densenet using learned group convolutions[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 2752-2761.

Depthwise Convolution（深度可分离卷积）将输入特征图的每个通道分开，分别使用一个卷积核进行卷积，假设卷积核大小为 $1\times k\times k$ ，其中 $1$ 表示只对一个通道进行卷积。由于有in_channels个卷积核，故有 $in_channels × k × k \text{in\_channels}\times k \times k$ 个参数，得到的特征图通道数与输入相同。

Pointwise Group Convolution（逐点分组卷积）在分组卷积的基础上，令每一组卷积核大小为 $1\times 1$ ，故共有 $in_channels / g × 1 × 1 ) × out_channels (\text{in\_channels}/g\times1\times1)\times \text{out\_channels}$ 个参数。

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

Channel Shuffle

Group Convolution只能保证组内的特征提取，而不同组之间的特征是不通信的，这就降低了网络的特征提取能力。
为了解决这个问题，ShuffleNet引入了Channel Shuffle机制，将不同分组通道均匀分散重组，使得网络在下一层能处理不同组别通道的信息。
shufflenet3
对于 $g$ 组，每组有 $n$ 个通道的特征图：

reshape为 $g\times n$ 的矩阵；
转置为 $n\times g$ 的矩阵；
通过flatten操作得到新的排列。

ShuffleNet模块

ShuffleNet对ResNet中Bottleneck结构进行由(a)到(b), (c)的更改：
shufflenet5

将开始和最后的 $1\times 1$ 卷积模块改成Pointwise Group Convolution;
在降维后进行Channel Shuffle;
降采样模块中， $3\times 3$ Depthwise Convolution 的步长设置为2，特征图大小减半，因此shortcuts中采用步长为2的 $3\times 3$ 平均池化，并把相加改成拼接。

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

网络构建

shufflenet6

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

模型训练与评估

数据集

采用CIFAR-10数据集进行预训练。


![shufflenet6](https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/website-images/r2.3/tutorials/application/source_zh_cn/cv/images/shufflenet_6.png)

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()

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()

模型评估

调用model.eval()接口对模型进行评估。

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()

模型预测

import mindspore
import matplotlib.pyplot as plt
import mindspore.dataset as ds

net = ShuffleNetV1(model_size="2.0x", n_class=10)
show_lst = []
param_dict = load_checkpoint("shufflenetv1-5_390.ckpt")
load_param_into_net(net, param_dict)
model = Model(net)
dataset_predict = ds.Cifar10Dataset(dataset_dir="./dataset/cifar-10-batches-bin", shuffle=False, usage="train")
dataset_show = ds.Cifar10Dataset(dataset_dir="./dataset/cifar-10-batches-bin", shuffle=False, usage="train")
dataset_show = dataset_show.batch(16)
show_images_lst = next(dataset_show.create_dict_iterator())["image"].asnumpy()
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()
        ]
dataset_predict = dataset_predict.map(image_trans, 'image')
dataset_predict = dataset_predict.batch(16)
class_dict = {0:"airplane", 1:"automobile", 2:"bird", 3:"cat", 4:"deer", 5:"dog", 6:"frog", 7:"horse", 8:"ship", 9:"truck"}
# 推理效果展示(上方为预测的结果，下方为推理效果图片)
plt.figure(figsize=(16, 5))
predict_data = next(dataset_predict.create_dict_iterator())
output = model.predict(ms.Tensor(predict_data['image']))
pred = np.argmax(output.asnumpy(), axis=1)
index = 0
for image in show_images_lst:
    plt.subplot(2, 8, index+1)
    plt.title('{}'.format(class_dict[pred[index]]))
    index += 1
    plt.imshow(image)
    plt.axis("off")
plt.show()

总结

这一节介绍了ShuffleNet的基本结构，为了在移动设备这样的有限资源上进行训练，ShuffleNet提出了Pointwise Group Convolution操作以大幅减少参数量，使用Channel Shuffle来确保网络的特征提取能力。通过在ResNet的Bottleneck结构中应用上面的两种操作，得到ShuffleNet的基本网络模块。