摘要：
记录MindSpore AI框架使用ShuffleNet网络对CIFAR-10数据集进行分类的过程、步骤和方法。包括环境准备、下载数据集、数据集加载和预处理、构建模型、模型训练、模型评估、模型测试等。
一、概念
1.ShuffleNet网络
旷视科技提出的CNN模型
应用在移动端
通过设计更高效的网络结构来实现模型的压缩和加速。
2.模型架构
ShuffleNet最显著的特点
Pointwise Group Convolution
Group Convolution（分组卷积）原理图
分组卷积
Depthwise Convolution（深度可分离卷积）
Pointwise Group Convolution（逐点分组卷积）
3.Channel Shuffle
通道重排
对于g组
二、环境准备
%%capture captured_output
# 实验环境已经预装了mindspore==2.2.14，如需更换mindspore版本，可更改下面mindspore的版本号
!pip uninstall mindspore -y
!pip install -i https://pypi.mirrors.ustc.edu.cn/simple mindspore==2.2.14
# 查看当前 mindspore 版本
!pip show mindspore输出：
Name: mindspore
Version: 2.2.14
Summary: MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.
Home-page: https://www.mindspore.cn
Author: The MindSpore Authors
Author-email: contact@mindspore.cn
License: Apache 2.0
Location: /home/nginx/miniconda/envs/jupyter/lib/python3.9/site-packages
Requires: asttokens, astunparse, numpy, packaging, pillow, protobuf, psutil, scipy
Required-by: 分组卷积类
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三、ShuffleNet模块
ShuffleNet的改进，从(a)->(b)->(c)
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四、构建ShuffleNet网络
ShuffleNet网络结构图
输入图像224×224，组数3（g = 3）为例
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五、模型训练和评估
采用CIFAR-10数据集对ShuffleNet进行预训练。
1.训练集准备与加载
CIFAR-10
mindspore.dataset.Cifar10Dataset接口
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)输出：
Creating data folder...
Downloading data from https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/notebook/datasets/cifar-10-binary.tar.gz (162.2 MB)
file_sizes: 100%|█████████████████████████████| 170M/170M [00:00<00:00, 177MB/s]
Extracting tar.gz file...
Successfully downloaded / unzipped to ./dataset
[6]:
'./dataset'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()2.模型训练
随机初始化参数做预训练。
调用ShuffleNetV1定义网络
train.model.Model接口封装
model.train()训练
传入回调函数
打印
保存ckpt文件在当前目录下
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()输出：
model size is 2.0x
============== Starting Training ==============
epoch: 1 step: 1, loss is 2.702430248260498
epoch: 1 step: 2, loss is 2.5544934272766113
epoch: 1 step: 3, loss is 2.3527920246124268
epoch: 1 step: 4, loss is 2.432495355606079
epoch: 1 step: 5, loss is 2.442847490310669
......
epoch: 1 step: 386, loss is 1.8315027952194214
epoch: 1 step: 387, loss is 1.9081732034683228
epoch: 1 step: 388, loss is 1.8965389728546143
epoch: 1 step: 389, loss is 1.8942060470581055
epoch: 1 step: 390, loss is 1.8646998405456543
Train epoch time: 439745.086 ms, per step time: 1127.552 ms
epoch: 2 step: 1, loss is 1.9022231101989746
epoch: 2 step: 2, loss is 1.8828961849212646
epoch: 2 step: 3, loss is 1.8220021724700928
epoch: 2 step: 4, loss is 2.003005027770996
epoch: 2 step: 5, loss is 1.8657888174057007
......
epoch: 2 step: 386, loss is 1.754606008529663
epoch: 2 step: 387, loss is 1.73811674118042
epoch: 2 step: 388, loss is 1.5935282707214355
epoch: 2 step: 389, loss is 1.7022861242294312
epoch: 2 step: 390, loss is 1.7202574014663696
Train epoch time: 121300.859 ms, per step time: 311.028 ms
epoch: 3 step: 1, loss is 1.6813828945159912
epoch: 3 step: 2, loss is 1.7341467142105103
epoch: 3 step: 3, loss is 1.8423044681549072
epoch: 3 step: 4, loss is 1.8151057958602905
epoch: 3 step: 5, loss is 1.727158784866333
......
epoch: 3 step: 386, loss is 1.6009197235107422
epoch: 3 step: 387, loss is 1.7389277219772339
epoch: 3 step: 388, loss is 1.6847612857818604
epoch: 3 step: 389, loss is 1.7618985176086426
epoch: 3 step: 390, loss is 1.719774842262268
Train epoch time: 121936.621 ms, per step time: 312.658 ms
epoch: 4 step: 1, loss is 1.6524462699890137
epoch: 4 step: 2, loss is 1.5743780136108398
epoch: 4 step: 3, loss is 1.7330453395843506
epoch: 4 step: 4, loss is 1.6160061359405518
epoch: 4 step: 5, loss is 1.6632086038589478
......
epoch: 4 step: 386, loss is 1.6585990190505981
epoch: 4 step: 387, loss is 1.6520838737487793
epoch: 4 step: 388, loss is 1.4504361152648926
epoch: 4 step: 389, loss is 1.8115458488464355
epoch: 4 step: 390, loss is 1.6291583776474
Train epoch time: 121944.082 ms, per step time: 312.677 ms
epoch: 5 step: 1, loss is 1.737457275390625
epoch: 5 step: 2, loss is 1.6314475536346436
epoch: 5 step: 3, loss is 1.6039154529571533
epoch: 5 step: 4, loss is 1.59605073928833
epoch: 5 step: 5, loss is 1.6140247583389282
......
epoch: 5 step: 386, loss is 1.599562406539917
epoch: 5 step: 387, loss is 1.486626148223877
epoch: 5 step: 388, loss is 1.6146260499954224
epoch: 5 step: 389, loss is 1.6220197677612305
epoch: 5 step: 390, loss is 1.610574722290039
Train epoch time: 121699.011 ms, per step time: 312.049 ms
total time:0h 15m 26s
============== Train Success ==============训练好的模型保存在当前目录的shufflenetv1-5_390.ckpt中，用作评估。
3.模型评估
在CIFAR-10的测试集上对模型进行评估。
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()输出：
model size is 2.0x
[ERROR] CORE(263,ffffa833e930,python):2024-07-07-15:29:24.418.000 [mindspore/core/utils/file_utils.cc:253] GetRealPath] Get realpath failed, path[/tmp/ipykernel_263/3162391481.py]
[ERROR] CORE(263,ffffa833e930,python):2024-07-07-15:29:24.418.539 [mindspore/core/utils/file_utils.cc:253] GetRealPath] Get realpath failed, path[/tmp/ipykernel_263/3162391481.py]
......
result:{'Loss': 1.6150915485162, 'Top_1_Acc': 0.4930889423076923, 'Top_5_Acc': 0.9283854166666666}, ckpt:'./shufflenetv1-5_390.ckpt', time: 0h 1m 26s4.模型预测
在CIFAR-10的测试集上对模型进行预测，并将预测结果可视化。
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()输出：
model size is 2.0x
[ERROR] CORE(263,ffffa833e930,python):2024-07-07-15:30:55.337.972 [mindspore/core/utils/file_utils.cc:253] GetRealPath] Get realpath failed, path[/tmp/ipykernel_263/1681751341.py]
[ERROR] CORE(263,ffffa833e930,python):2024-07-07-15:30:55.338.097 [mindspore/core/utils/file_utils.cc:253] GetRealPath] Get realpath failed, path[/tmp/ipykernel_263/1681751341.py]
......
