昇思25天学习打卡营第13天 | ShuffleNet图像分类
内容介绍:
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。
ShuffleNet最显著的特点在于对不同通道进行重排来解决Group Convolution带来的弊端。通过对ResNet的Bottleneck单元进行改进,在较小的计算量的情况下达到了较高的准确率。
Pointwise Group Convolution
Group Convolution(分组卷积)原理如下图所示,相比于普通的卷积操作,分组卷积的情况下,每一组的卷积核大小为in_channels/g*k*k,一共有g组,所有组共有(in_channels/g*k*k)*out_channels个参数,是正常卷积参数的1/g。分组卷积中,每个卷积核只处理输入特征图的一部分通道,其优点在于参数量会有所降低,但输出通道数仍等于卷积核的数量。
具体内容:
1. 导包
from mindspore import nn
import mindspore.ops as ops
from mindspore import Tensor
from download import download
import mindspore as ms
from mindspore.dataset import Cifar10Dataset
from mindspore.dataset import vision, transforms
import time
import mindspore
import numpy as np
from mindspore import Tensor, nn
from mindspore.train import ModelCheckpoint, CheckpointConfig, TimeMonitor, LossMonitor, Model, Top1CategoricalAccuracy, Top5CategoricalAccuracy
from mindspore import load_checkpoint, load_param_into_net
import mindspore
import matplotlib.pyplot as plt
import mindspore.dataset as ds
2. 模型
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
3. 数据处理
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()
4. 模型训练
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()
5. 模型评估
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()
6. 模型预测
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()
ShuffleNet作为一种轻量级的神经网络结构,其独特的数据重排和分组卷积设计,使得它在保持较高精度的同时,大大降低了模型的计算量和参数量。这种设计思路让我意识到,在追求模型性能的同时,也需要考虑模型的轻量化和效率问题。这对于我们来说是一个非常重要的启示,特别是在移动设备和嵌入式系统上的深度学习应用中。
在使用MindSpore和ShuffleNet进行图像分类的实践过程中,我也遇到了一些挑战和困难。例如,如何调整超参数以优化模型的性能、如何处理数据的不平衡问题等。
原文地址:https://blog.csdn.net/weixin_44144773/article/details/140075775
免责声明:本站文章内容转载自网络资源,如本站内容侵犯了原著者的合法权益,可联系本站删除。更多内容请关注自学内容网(zxcms.com)!