ResNet50迁移学习
在实际应用场景中,由于训练数据集不足,所以很少有人会从头开始训练整个网络。普遍的做法是,在一个非常大的基础数据集上训练得到一个预训练模型,然后使用该模型来初始化网络的权重参数或作为固定特征提取器应用于特定的任务中。
数据准备
下载数据集
使用狗和狼分类数据集
from download import download
dataset_url = "https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/notebook/datasets/intermediate/Canidae_data.zip"
download(dataset_url, "./datasets-Canidae", kind="zip", replace=True)
加载数据集
加载数据集,并进行图像增强操作
batch_size = 18 # 批量大小
image_size = 224 # 训练图像空间大小
num_epochs = 5 # 训练周期数
lr = 0.001 # 学习率
momentum = 0.9 # 动量
workers = 4 # 并行线程个数
import mindspore as ms
import mindspore.dataset as ds
import mindspore.dataset.vision as vision
# 数据集目录路径
data_path_train = "./datasets-Canidae/data/Canidae/train/"
data_path_val = "./datasets-Canidae/data/Canidae/val/"
# 创建训练数据集
def create_dataset_canidae(dataset_path, usage):
"""数据加载"""
data_set = ds.ImageFolderDataset(dataset_path,
num_parallel_workers=workers,
shuffle=True,)
# 数据增强操作
mean = [0.485 * 255, 0.456 * 255, 0.406 * 255]
std = [0.229 * 255, 0.224 * 255, 0.225 * 255]
scale = 32
if usage == "train":
# Define map operations for training dataset
trans = [
vision.RandomCropDecodeResize(size=image_size, scale=(0.08, 1.0), ratio=(0.75, 1.333)),
vision.RandomHorizontalFlip(prob=0.5),
vision.Normalize(mean=mean, std=std),
vision.HWC2CHW()
]
else:
# Define map operations for inference dataset
trans = [
vision.Decode(),
vision.Resize(image_size + scale),
vision.CenterCrop(image_size),
vision.Normalize(mean=mean, std=std),
vision.HWC2CHW()
]
# 数据映射操作
data_set = data_set.map(
operations=trans,
input_columns='image',
num_parallel_workers=workers)
# 批量操作
data_set = data_set.batch(batch_size)
return data_set
dataset_train = create_dataset_canidae(data_path_train, "train")
step_size_train = dataset_train.get_dataset_size()
dataset_val = create_dataset_canidae(data_path_val, "val")
step_size_val = dataset_val.get_dataset_size()
训练模型
构建ResNet50网络,并将预训练模型权重参数加载到网络中
构建ResNet50网络
from typing import Type, Union, List, Optional
from mindspore import nn, train
from mindspore.common.initializer import Normal
weight_init = Normal(mean=0, sigma=0.02)
gamma_init = Normal(mean=1, sigma=0.02)
class ResidualBlockBase(nn.Cell):
expansion: int = 1 # 最后一个卷积核数量与第一个卷积核数量相等
def __init__(self, in_channel: int, out_channel: int,
stride: int = 1, norm: Optional[nn.Cell] = None,
down_sample: Optional[nn.Cell] = None) -> None:
super(ResidualBlockBase, self).__init__()
if not norm:
self.norm = nn.BatchNorm2d(out_channel)
else:
self.norm = norm
self.conv1 = nn.Conv2d(in_channel, out_channel,
kernel_size=3, stride=stride,
weight_init=weight_init)
self.conv2 = nn.Conv2d(in_channel, out_channel,
kernel_size=3, weight_init=weight_init)
self.relu = nn.ReLU()
self.down_sample = down_sample
def construct(self, x):
"""ResidualBlockBase construct."""
identity = x # shortcuts分支
out = self.conv1(x) # 主分支第一层:3*3卷积层
out = self.norm(out)
out = self.relu(out)
out = self.conv2(out) # 主分支第二层:3*3卷积层
out = self.norm(out)
if self.down_sample is not None:
identity = self.down_sample(x)
out += identity # 输出为主分支与shortcuts之和
out = self.relu(out)
return out
class ResidualBlock(nn.Cell):
expansion = 4 # 最后一个卷积核的数量是第一个卷积核数量的4倍
def __init__(self, in_channel: int, out_channel: int,
stride: int = 1, down_sample: Optional[nn.Cell] = None) -> None:
super(ResidualBlock, self).__init__()
self.conv1 = nn.Conv2d(in_channel, out_channel,
kernel_size=1, weight_init=weight_init)
self.norm1 = nn.BatchNorm2d(out_channel)
self.conv2 = nn.Conv2d(out_channel, out_channel,
kernel_size=3, stride=stride,
weight_init=weight_init)
self.norm2 = nn.BatchNorm2d(out_channel)
self.conv3 = nn.Conv2d(out_channel, out_channel * self.expansion,
kernel_size=1, weight_init=weight_init)
self.norm3 = nn.BatchNorm2d(out_channel * self.expansion)
self.relu = nn.ReLU()
self.down_sample = down_sample
def construct(self, x):
identity = x # shortscuts分支
out = self.conv1(x) # 主分支第一层:1*1卷积层
out = self.norm1(out)
out = self.relu(out)
out = self.conv2(out) # 主分支第二层:3*3卷积层
out = self.norm2(out)
out = self.relu(out)
out = self.conv3(out) # 主分支第三层:1*1卷积层
out = self.norm3(out)
if self.down_sample is not None:
identity = self.down_sample(x)
out += identity # 输出为主分支与shortcuts之和
out = self.relu(out)
return out
def make_layer(last_out_channel, block: Type[Union[ResidualBlockBase, ResidualBlock]],
channel: int, block_nums: int, stride: int = 1):
down_sample = None # shortcuts分支
if stride != 1 or last_out_channel != channel * block.expansion:
down_sample = nn.SequentialCell([
nn.Conv2d(last_out_channel, channel * block.expansion,
kernel_size=1, stride=stride, weight_init=weight_init),
nn.BatchNorm2d(channel * block.expansion, gamma_init=gamma_init)
])
layers = []
layers.append(block(last_out_channel, channel, stride=stride, down_sample=down_sample))
in_channel = channel * block.expansion
# 堆叠残差网络
for _ in range(1, block_nums):
layers.append(block(in_channel, channel))
return nn.SequentialCell(layers)
from mindspore import load_checkpoint, load_param_into_net
class ResNet(nn.Cell):
def __init__(self, block: Type[Union[ResidualBlockBase, ResidualBlock]],
layer_nums: List[int], num_classes: int, input_channel: int) -> None:
super(ResNet, self).__init__()
self.relu = nn.ReLU()
# 第一个卷积层,输入channel为3(彩色图像),输出channel为64
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, weight_init=weight_init)
self.norm = nn.BatchNorm2d(64)
# 最大池化层,缩小图片的尺寸
self.max_pool = nn.MaxPool2d(kernel_size=3, stride=2, pad_mode='same')
# 各个残差网络结构块定义,
self.layer1 = make_layer(64, block, 64, layer_nums[0])
self.layer2 = make_layer(64 * block.expansion, block, 128, layer_nums[1], stride=2)
self.layer3 = make_layer(128 * block.expansion, block, 256, layer_nums[2], stride=2)
self.layer4 = make_layer(256 * block.expansion, block, 512, layer_nums[3], stride=2)
# 平均池化层
self.avg_pool = nn.AvgPool2d()
# flattern层
self.flatten = nn.Flatten()
# 全连接层
self.fc = nn.Dense(in_channels=input_channel, out_channels=num_classes)
def construct(self, x):
x = self.conv1(x)
x = self.norm(x)
x = self.relu(x)
x = self.max_pool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avg_pool(x)
x = self.flatten(x)
x = self.fc(x)
return x
def _resnet(model_url: str, block: Type[Union[ResidualBlockBase, ResidualBlock]],
layers: List[int], num_classes: int, pretrained: bool, pretrianed_ckpt: str,
input_channel: int):
model = ResNet(block, layers, num_classes, input_channel)
if pretrained:
# 加载预训练模型
download(url=model_url, path=pretrianed_ckpt, replace=True)
param_dict = load_checkpoint(pretrianed_ckpt)
load_param_into_net(model, param_dict)
return model
def resnet50(num_classes: int = 1000, pretrained: bool = False):
"ResNet50模型"
resnet50_url = "https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/notebook/models/application/resnet50_224_new.ckpt"
resnet50_ckpt = "./LoadPretrainedModel/resnet50_224_new.ckpt"
return _resnet(resnet50_url, ResidualBlock, [3, 4, 6, 3], num_classes,
pretrained, resnet50_ckpt, 2048)
固定特征进行训练
冻结除最后一层之外的所有网络层。
import mindspore as ms
import matplotlib.pyplot as plt
import os
import time
net_work = resnet50(pretrained=True)
# 全连接层输入层的大小
in_channels = net_work.fc.in_channels
# 输出通道数大小为狼狗分类数2
head = nn.Dense(in_channels, 2)
# 重置全连接层
net_work.fc = head
# 平均池化层kernel size为7
avg_pool = nn.AvgPool2d(kernel_size=7)
# 重置平均池化层
net_work.avg_pool = avg_pool
# 冻结除最后一层外的所有参数
for param in net_work.get_parameters():
if param.name not in ["fc.weight", "fc.bias"]:
param.requires_grad = False
# 定义优化器和损失函数
opt = nn.Momentum(params=net_work.trainable_params(), learning_rate=lr, momentum=0.5)
loss_fn = nn.SoftmaxCrossEntropyWithLogits(sparse=True, reduction='mean')
def forward_fn(inputs, targets):
logits = net_work(inputs)
loss = loss_fn(logits, targets)
return loss
grad_fn = ms.value_and_grad(forward_fn, None, opt.parameters)
def train_step(inputs, targets):
loss, grads = grad_fn(inputs, targets)
opt(grads)
return loss
# 实例化模型
model1 = train.Model(net_work, loss_fn, opt, metrics={"Accuracy": train.Accuracy()})
训练和评估
利用预训练模型,可以使训练时间大大缩短
import mindspore as ms
import matplotlib.pyplot as plt
import os
import time
dataset_train = create_dataset_canidae(data_path_train, "train")
step_size_train = dataset_train.get_dataset_size()
dataset_val = create_dataset_canidae(data_path_val, "val")
step_size_val = dataset_val.get_dataset_size()
num_epochs = 5
# 创建迭代器
data_loader_train = dataset_train.create_tuple_iterator(num_epochs=num_epochs)
data_loader_val = dataset_val.create_tuple_iterator(num_epochs=num_epochs)
best_ckpt_dir = "./BestCheckpoint"
best_ckpt_path = "./BestCheckpoint/resnet50-best-freezing-param.ckpt"
import mindspore as ms
import matplotlib.pyplot as plt
import os
import time
# 开始循环训练
print("Start Training Loop ...")
best_acc = 0
for epoch in range(num_epochs):
losses = []
net_work.set_train()
epoch_start = time.time()
# 为每轮训练读入数据
for i, (images, labels) in enumerate(data_loader_train):
labels = labels.astype(ms.int32)
loss = train_step(images, labels)
losses.append(loss)
# 每个epoch结束后,验证准确率
acc = model1.eval(dataset_val)['Accuracy']
epoch_end = time.time()
epoch_seconds = (epoch_end - epoch_start) * 1000
step_seconds = epoch_seconds/step_size_train
print("-" * 20)
print("Epoch: [%3d/%3d], Average Train Loss: [%5.3f], Accuracy: [%5.3f]" % (
epoch+1, num_epochs, sum(losses)/len(losses), acc
))
print("epoch time: %5.3f ms, per step time: %5.3f ms" % (
epoch_seconds, step_seconds
))
if acc > best_acc:
best_acc = acc
if not os.path.exists(best_ckpt_dir):
os.mkdir(best_ckpt_dir)
ms.save_checkpoint(net_work, best_ckpt_path)
print("=" * 80)
print(f"End of validation the best Accuracy is: {best_acc: 5.3f}, "
f"save the best ckpt file in {best_ckpt_path}", flush=True)
可视化模型预测
import matplotlib.pyplot as plt
import mindspore as ms
def visualize_model(best_ckpt_path, val_ds):
net = resnet50()
# 全连接层输入层的大小
in_channels = net.fc.in_channels
# 输出通道数大小为狼狗分类数2
head = nn.Dense(in_channels, 2)
# 重置全连接层
net.fc = head
# 平均池化层kernel size为7
avg_pool = nn.AvgPool2d(kernel_size=7)
# 重置平均池化层
net.avg_pool = avg_pool
# 加载模型参数
param_dict = ms.load_checkpoint(best_ckpt_path)
ms.load_param_into_net(net, param_dict)
model = train.Model(net)
# 加载验证集的数据进行验证
data = next(val_ds.create_dict_iterator())
images = data["image"].asnumpy()
labels = data["label"].asnumpy()
class_name = {0: "dogs", 1: "wolves"}
# 预测图像类别
output = model.predict(ms.Tensor(data['image']))
pred = np.argmax(output.asnumpy(), axis=1)
# 显示图像及图像的预测值
plt.figure(figsize=(5, 5))
for i in range(4):
plt.subplot(2, 2, i + 1)
# 若预测正确,显示为蓝色;若预测错误,显示为红色
color = 'blue' if pred[i] == labels[i] else 'red'
plt.title('predict:{}'.format(class_name[pred[i]]), color=color)
picture_show = np.transpose(images[i], (1, 2, 0))
mean = np.array([0.485, 0.456, 0.406])
std = np.array([0.229, 0.224, 0.225])
picture_show = std * picture_show + mean
picture_show = np.clip(picture_show, 0, 1)
plt.imshow(picture_show)
plt.axis('off')
plt.show()
ResNet50图像分类
在ResNet网络提出之前,传统的卷积神经网络都是将一系列的卷积层和池化层堆叠得到的,但当网络堆叠到一定深度时,就会出现退化问题,如下图所示,随着网络的加深,其误差并没有如预想的一样减小。
ResNet网络提出了残差网络结构(Residual Network)来减轻退化问题,使用ResNet网络可以实现搭建较深的网络结构(突破1000层)。ResNet网络层数越深,其训练误差和测试误差越小。
数据集准备与加载
使用CIFAR-10数据集
from download import download
url = "https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/notebook/datasets/cifar-10-binary.tar.gz"
download(url, "./datasets-cifar10-bin", kind="tar.gz", replace=True)
加载数据集
import mindspore as ms
import mindspore.dataset as ds
import mindspore.dataset.vision as vision
import mindspore.dataset.transforms as transforms
from mindspore import dtype as mstype
data_dir = "./datasets-cifar10-bin/cifar-10-batches-bin" # 数据集根目录
batch_size = 256 # 批量大小
image_size = 32 # 训练图像空间大小
workers = 4 # 并行线程个数
num_classes = 10 # 分类数量
def create_dataset_cifar10(dataset_dir, usage, resize, batch_size, workers):
data_set = ds.Cifar10Dataset(dataset_dir=dataset_dir,
usage=usage,
num_parallel_workers=workers,
shuffle=True)
trans = []
if usage == "train":
trans += [
vision.RandomCrop((32, 32), (4, 4, 4, 4)),
vision.RandomHorizontalFlip(prob=0.5)
]
trans += [
vision.Resize(resize),
vision.Rescale(1.0 / 255.0, 0.0),
vision.Normalize([0.4914, 0.4822, 0.4465], [0.2023, 0.1994, 0.2010]),
vision.HWC2CHW()
]
target_trans = transforms.TypeCast(mstype.int32)
# 数据映射操作
data_set = data_set.map(operations=trans,
input_columns='image',
num_parallel_workers=workers)
data_set = data_set.map(operations=target_trans,
input_columns='label',
num_parallel_workers=workers)
# 批量操作
data_set = data_set.batch(batch_size)
return data_set
# 获取处理后的训练与测试数据集
dataset_train = create_dataset_cifar10(dataset_dir=data_dir,
usage="train",
resize=image_size,
batch_size=batch_size,
workers=workers)
step_size_train = dataset_train.get_dataset_size()
dataset_val = create_dataset_cifar10(dataset_dir=data_dir,
usage="test",
resize=image_size,
batch_size=batch_size,
workers=workers)
step_size_val = dataset_val.get_dataset_size()
构建网络
构建残差网络结构
残差网络结构图如下图所示,残差网络由两个分支构成:一个主分支,一个shortcuts(图中弧线表示)。主分支通过堆叠一系列的卷积操作得到,shotcuts从输入直接到输出。
残差网络结构主要由两种,一种是Building Block,适用于较浅的ResNet网络,如ResNet18和ResNet34;另一种是Bottleneck,适用于层数较深的ResNet网络,如ResNet50、ResNet101和ResNet152。
Building Block
Building Block结构图如下图所示,主分支有两层卷积网络结构:
主分支第一层网络以输入channel为64为例,首先通过一个3×3的卷积层,然后通过Batch Normalization层,最后通过Relu激活函数层,输出channel为64;
主分支第二层网络的输入channel为64,首先通过一个3×3的卷积层,然后通过Batch Normalization层,输出channel为64
最后将主分支输出的特征矩阵与shortcuts输出的特征矩阵相加,通过Relu激活函数即为Building Block最后的输出。
代码实现
from typing import Type, Union, List, Optional
import mindspore.nn as nn
from mindspore.common.initializer import Normal
# 初始化卷积层与BatchNorm的参数
weight_init = Normal(mean=0, sigma=0.02)
gamma_init = Normal(mean=1, sigma=0.02)
class ResidualBlockBase(nn.Cell):
expansion: int = 1 # 最后一个卷积核数量与第一个卷积核数量相等
def __init__(self, in_channel: int, out_channel: int,
stride: int = 1, norm: Optional[nn.Cell] = None,
down_sample: Optional[nn.Cell] = None) -> None:
super(ResidualBlockBase, self).__init__()
if not norm:
self.norm = nn.BatchNorm2d(out_channel)
else:
self.norm = norm
self.conv1 = nn.Conv2d(in_channel, out_channel,
kernel_size=3, stride=stride,
weight_init=weight_init)
self.conv2 = nn.Conv2d(in_channel, out_channel,
kernel_size=3, weight_init=weight_init)
self.relu = nn.ReLU()
self.down_sample = down_sample
def construct(self, x):
"""ResidualBlockBase construct."""
identity = x # shortcuts分支
out = self.conv1(x) # 主分支第一层:3*3卷积层
out = self.norm(out)
out = self.relu(out)
out = self.conv2(out) # 主分支第二层:3*3卷积层
out = self.norm(out)
if self.down_sample is not None:
identity = self.down_sample(x)
out += identity # 输出为主分支与shortcuts之和
out = self.relu(out)
return out
Bottleneck
Bottleneck结构图如下图所示,在输入相同的情况下Bottleneck结构相对Building Block结构的参数数量更少,更适合层数较深的网络
主分支第一层网络以输入channel为256为例,首先通过数量为64,大小为1×1的卷积核进行降维,然后通过Batch Normalization层,最后通过Relu激活函数层,其输出channel为64;
主分支第二层网络通过数量为64,大小为3×3的卷积核提取特征,然后通过Batch Normalization层,最后通过Relu激活函数层,其输出channel为64;
主分支第三层通过数量为256,大小1×1的卷积核进行升维,然后通过Batch Normalization层,其输出channel为256。
最后将主分支输出的特征矩阵与shortcuts输出的特征矩阵相加,通过Relu激活函数即为Bottleneck最后的输出。
代码实现:
class ResidualBlock(nn.Cell):
expansion = 4 # 最后一个卷积核的数量是第一个卷积核数量的4倍
def __init__(self, in_channel: int, out_channel: int,
stride: int = 1, down_sample: Optional[nn.Cell] = None) -> None:
super(ResidualBlock, self).__init__()
self.conv1 = nn.Conv2d(in_channel, out_channel,
kernel_size=1, weight_init=weight_init)
self.norm1 = nn.BatchNorm2d(out_channel)
self.conv2 = nn.Conv2d(out_channel, out_channel,
kernel_size=3, stride=stride,
weight_init=weight_init)
self.norm2 = nn.BatchNorm2d(out_channel)
self.conv3 = nn.Conv2d(out_channel, out_channel * self.expansion,
kernel_size=1, weight_init=weight_init)
self.norm3 = nn.BatchNorm2d(out_channel * self.expansion)
self.relu = nn.ReLU()
self.down_sample = down_sample
def construct(self, x):
identity = x # shortscuts分支
out = self.conv1(x) # 主分支第一层:1*1卷积层
out = self.norm1(out)
out = self.relu(out)
out = self.conv2(out) # 主分支第二层:3*3卷积层
out = self.norm2(out)
out = self.relu(out)
out = self.conv3(out) # 主分支第三层:1*1卷积层
out = self.norm3(out)
if self.down_sample is not None:
identity = self.down_sample(x)
out += identity # 输出为主分支与shortcuts之和
out = self.relu(out)
return out
构建ResNet50网络
网络结构如图所示
构建残差块:
def make_layer(last_out_channel, block: Type[Union[ResidualBlockBase, ResidualBlock]],
channel: int, block_nums: int, stride: int = 1):
down_sample = None # shortcuts分支
if stride != 1 or last_out_channel != channel * block.expansion:
down_sample = nn.SequentialCell([
nn.Conv2d(last_out_channel, channel * block.expansion,
kernel_size=1, stride=stride, weight_init=weight_init),
nn.BatchNorm2d(channel * block.expansion, gamma_init=gamma_init)
])
layers = []
layers.append(block(last_out_channel, channel, stride=stride, down_sample=down_sample))
in_channel = channel * block.expansion
# 堆叠残差网络
for _ in range(1, block_nums):
layers.append(block(in_channel, channel))
return nn.SequentialCell(layers)
ResNet50模型构建:
from mindspore import load_checkpoint, load_param_into_net
class ResNet(nn.Cell):
def __init__(self, block: Type[Union[ResidualBlockBase, ResidualBlock]],
layer_nums: List[int], num_classes: int, input_channel: int) -> None:
super(ResNet, self).__init__()
self.relu = nn.ReLU()
# 第一个卷积层,输入channel为3(彩色图像),输出channel为64
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, weight_init=weight_init)
self.norm = nn.BatchNorm2d(64)
# 最大池化层,缩小图片的尺寸
self.max_pool = nn.MaxPool2d(kernel_size=3, stride=2, pad_mode='same')
# 各个残差网络结构块定义
self.layer1 = make_layer(64, block, 64, layer_nums[0])
self.layer2 = make_layer(64 * block.expansion, block, 128, layer_nums[1], stride=2)
self.layer3 = make_layer(128 * block.expansion, block, 256, layer_nums[2], stride=2)
self.layer4 = make_layer(256 * block.expansion, block, 512, layer_nums[3], stride=2)
# 平均池化层
self.avg_pool = nn.AvgPool2d()
# flattern层
self.flatten = nn.Flatten()
# 全连接层
self.fc = nn.Dense(in_channels=input_channel, out_channels=num_classes)
def construct(self, x):
x = self.conv1(x)
x = self.norm(x)
x = self.relu(x)
x = self.max_pool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avg_pool(x)
x = self.flatten(x)
x = self.fc(x)
return x
def _resnet(model_url: str, block: Type[Union[ResidualBlockBase, ResidualBlock]],
layers: List[int], num_classes: int, pretrained: bool, pretrained_ckpt: str,
input_channel: int):
model = ResNet(block, layers, num_classes, input_channel)
if pretrained:
# 加载预训练模型
download(url=model_url, path=pretrained_ckpt, replace=True)
param_dict = load_checkpoint(pretrained_ckpt)
load_param_into_net(model, param_dict)
return model
def resnet50(num_classes: int = 1000, pretrained: bool = False):
"""ResNet50模型"""
resnet50_url = "https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/notebook/models/application/resnet50_224_new.ckpt"
resnet50_ckpt = "./LoadPretrainedModel/resnet50_224_new.ckpt"
return _resnet(resnet50_url, ResidualBlock, [3, 4, 6, 3], num_classes,
pretrained, resnet50_ckpt, 2048)
模型训练与评估
将预训练模型全连接层的输出由1000个更改为10个
# 定义ResNet50网络
network = resnet50(pretrained=True)
# 全连接层输入层的大小
in_channel = network.fc.in_channels
fc = nn.Dense(in_channels=in_channel, out_channels=10)
# 重置全连接层
network.fc = fc
# 设置学习率
num_epochs = 80
lr = nn.cosine_decay_lr(min_lr=0.00001, max_lr=0.001, total_step=step_size_train * num_epochs,
step_per_epoch=step_size_train, decay_epoch=num_epochs)
# 定义优化器和损失函数
opt = nn.Momentum(params=network.trainable_params(), learning_rate=lr, momentum=0.9)
loss_fn = nn.SoftmaxCrossEntropyWithLogits(sparse=True, reduction='mean')
def forward_fn(inputs, targets):
logits = network(inputs)
loss = loss_fn(logits, targets)
return loss
grad_fn = ms.value_and_grad(forward_fn, None, opt.parameters)
def train_step(inputs, targets):
loss, grads = grad_fn(inputs, targets)
opt(grads)
return loss
import os
# 创建迭代器
data_loader_train = dataset_train.create_tuple_iterator(num_epochs=num_epochs)
data_loader_val = dataset_val.create_tuple_iterator(num_epochs=num_epochs)
# 最佳模型存储路径
best_acc = 0
best_ckpt_dir = "./BestCheckpoint"
best_ckpt_path = "./BestCheckpoint/resnet50-best.ckpt"
if not os.path.exists(best_ckpt_dir):
os.mkdir(best_ckpt_dir)
import mindspore.ops as ops
def train(data_loader, epoch):
"""模型训练"""
losses = []
network.set_train(True)
for i, (images, labels) in enumerate(data_loader):
loss = train_step(images, labels)
if i % 100 == 0 or i == step_size_train - 1:
print('Epoch: [%3d/%3d], Steps: [%3d/%3d], Train Loss: [%5.3f]' %
(epoch + 1, num_epochs, i + 1, step_size_train, loss))
losses.append(loss)
return sum(losses) / len(losses)
def evaluate(data_loader):
"""模型验证"""
network.set_train(False)
correct_num = 0.0 # 预测正确个数
total_num = 0.0 # 预测总数
for images, labels in data_loader:
logits = network(images)
pred = logits.argmax(axis=1) # 预测结果
correct = ops.equal(pred, labels).reshape((-1, ))
correct_num += correct.sum().asnumpy()
total_num += correct.shape[0]
acc = correct_num / total_num # 准确率
return acc
# 开始循环训练
print("Start Training Loop ...")
for epoch in range(num_epochs):
curr_loss = train(data_loader_train, epoch)
curr_acc = evaluate(data_loader_val)
print("-" * 50)
print("Epoch: [%3d/%3d], Average Train Loss: [%5.3f], Accuracy: [%5.3f]" % (
epoch+1, num_epochs, curr_loss, curr_acc
))
print("-" * 50)
# 保存当前预测准确率最高的模型
if curr_acc > best_acc:
best_acc = curr_acc
ms.save_checkpoint(network, best_ckpt_path)
print("=" * 80)
print(f"End of validation the best Accuracy is: {best_acc: 5.3f}, "
f"save the best ckpt file in {best_ckpt_path}", flush=True)
可视化模型预测
import matplotlib.pyplot as plt
def visualize_model(best_ckpt_path, dataset_val):
num_class = 10 # 对狼和狗图像进行二分类
net = resnet50(num_class)
# 加载模型参数
param_dict = ms.load_checkpoint(best_ckpt_path)
ms.load_param_into_net(net, param_dict)
# 加载验证集的数据进行验证
data = next(dataset_val.create_dict_iterator())
images = data["image"]
labels = data["label"]
# 预测图像类别
output = net(data['image'])
pred = np.argmax(output.asnumpy(), axis=1)
# 图像分类
classes = []
with open(data_dir + "/batches.meta.txt", "r") as f:
for line in f:
line = line.rstrip()
if line:
classes.append(line)
# 显示图像及图像的预测值
plt.figure()
for i in range(6):
plt.subplot(2, 3, i + 1)
# 若预测正确,显示为蓝色;若预测错误,显示为红色
color = 'blue' if pred[i] == labels.asnumpy()[i] else 'red'
plt.title('predict:{}'.format(classes[pred[i]]), color=color)
picture_show = np.transpose(images.asnumpy()[i], (1, 2, 0))
mean = np.array([0.4914, 0.4822, 0.4465])
std = np.array([0.2023, 0.1994, 0.2010])
picture_show = std * picture_show + mean
picture_show = np.clip(picture_show, 0, 1)
plt.imshow(picture_show)
plt.axis('off')
plt.show()
# 使用测试数据集进行验证
visualize_model(best_ckpt_path=best_ckpt_path, dataset_val=dataset_val)
输出结果:
模型训练准确率为84.7%。
总结
ResNet50作为一种极其有效的网络模型,被应用于很多领域。本文介绍了基于ResNet50的图像分类及其模型迁移。由于ResNet50复杂的网络结构,其训练往往相当消耗资源,因此往往采用预训练-微调手段进行模型构建,从而达到训练的目的。