基本介绍
今日的应用实践的模型是计算机实践领域中十分出名的模型----ResNet模型。ResNet是一种残差网络结构,它通过引入"残差学习"的概念来解决随着网络深度增加时训练困难的问题,从而能够训练更深的网络结构。现很多网络极深的模型或多或少都受此影响。今日的主要任务是使用ResNet50进行迁移学习,所谓的迁移学习是不从头到尾训练一个模型,而是在一个特别大的数据集上面训练得到一个预训练模型,然后使用该模型的权重作为初始化参数,最后应用于特定的任务。对特定的任务来说也可以对模型进行训练,但是需要冻结模型的某些参数,一般只训练模型的分类器部分,不会训练特征提取部分。下面我们详细讲讲今日的应用实践。
数据集准备
本次使用的数据集是来自ImageNet数据集中抽取出来的狼狗数据集,每个类别大概有120张训练图像与30张验证图像,数据集可通过华为云OBS和相关API直接下载,然后进行加载。可借助MindSpore提供的API对数据集进行加载,同时,因为数据集在送入模型之前需做些处理,这些可封装到一个函数内,具体代码如下:
python
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
通过上述操作后,我们可以很方便的调用数据集,无论是进行训练还是可视化,都可以。
模型搭建
准备好数据集后,自然就是进行模型搭建,ResNet50是一个非常常见的模型,具体模型结构和不同AI框架下的代码都很容易获取,MindSpore官方也有相关的实现代码,我们直接使用,模型的代码如下:
python
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)
训练模型
我们采用定特征进行训练,需要冻结除最后一层之外的所有网络层,最后一层其实就是一个分类层,前面是特征提取层,MindSpore可以通过设置 requires_grad == False
冻结参数,以便不在反向传播中计算梯度,具体代码如下:
python
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()})
一切准备妥当后,便可以进行训练,由于有预训练模型,模型的训练速度非常快,比从头到尾训练快了好几倍。训练了5轮,效果就非常好了:
模型可视化预测
有了训练好的模型,自然要看看训练得好不好,除了看评价指标,最直观的就是实际使用一下模型,由于这是图像分类任务,所以将其可视化。这一整个流程的代码如下:
python
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()
调用该函数后,可视化结果如下:可以看出还是很准的