目录
一、模型构建
1.1残差单元
1.2 残差网络的整体结构
二、统计模型的参数量和计算量
三、数据预处理
四、没有残差连接的ResNet18
五、带残差连接的ResNet18
附:完整的可运行代码
实验大体步骤:
先前说明:
上次LeNet实验用到的那个数据集最后的准确率只有92%,但是看学长们的代码和同班同学们的运行结果都是95%+,于是我就尝试换成老师群里的数据集和学长的代码试一试,发现那个数据集运行出来的准确率只有10%。看了看同学的博客,说是换个数据集就可以了。于是我把其替换掉,发现准确率到了95.5%。好用!于是我将其放在这里,需要的同学可以自行下载。
好用的数据集:
通过网盘分享的文件:mnist.gz
链接: https://pan.baidu.com/s/10zpKj-10JgXXLnGEA-AqdA?pwd=41wb 提取码: 41wb
一、模型构建
1.1残差单元
一个残差网络通常有很多个残差单元堆叠而成。
为了减少网络的参数量,在瓶颈结构中会先试用1×1的卷积核来减少通道数,经过3×3卷记得处理后,再使用1×1的卷积恢复通道数。
代码如下:
# 残差单元算子
class ResBlock(nn.Module):
def __init__(self, in_channels, out_channels, stride=1, use_residual=True):
super(ResBlock, self).__init__()
self.stride = stride
self.use_residual = use_residual
# 第一个卷积层,卷积核大小为3×3,可以设置不同输出通道数以及步长
self.conv1 = nn.Conv2d(in_channels, out_channels, 3, padding=1, stride=self.stride)
# 第二个卷积层,卷积核大小为3×3,不改变输入特征图的形状,步长为1
self.conv2 = nn.Conv2d(out_channels, out_channels, 3, padding=1)
# 如果conv2的输出和此残差块的输入数据形状不一致,则use_1x1conv = True
# 当use_1x1conv = True,添加1个1x1的卷积作用在输入数据上,使其形状变成跟conv2一致
if in_channels != out_channels or stride != 1:
self.use_1x1conv = True
else:
self.use_1x1conv = False
# 当残差单元包裹的非线性层输入和输出通道数不一致时,需要用1×1卷积调整通道数后再进行相加运算
if self.use_1x1conv:
self.shortcut = nn.Conv2d(in_channels, out_channels, 1, stride=self.stride)
# 每个卷积层后会接一个批量规范化层,批量规范化的内容在7.5.1中会进行详细介绍
self.bn1 = nn.BatchNorm2d(out_channels)
self.bn2 = nn.BatchNorm2d(out_channels)
if self.use_1x1conv:
self.bn3 = nn.BatchNorm2d(out_channels)
def forward(self, inputs):
y = F.relu(self.bn1(self.conv1(inputs)))
y = self.bn2(self.conv2(y))
if self.use_residual:
if self.use_1x1conv: # 如果为真,对inputs进行1×1卷积,将形状调整成跟conv2的输出y一致
shortcut = self.shortcut(inputs)
shortcut = self.bn3(shortcut)
else: # 否则直接将inputs和conv2的输出y相加
shortcut = inputs
y = torch.add(shortcut, y)
out = F.relu(y)
return out
1.2 残差网络的整体结构
将ResNet18网络划分为6个模块:
·第一模块:包含了一个步长为2,大小为7×7的卷积层,卷积层的输出通道数为64,卷积层的输出经过批量归一化、ReLU激活函数的处理后,接了一个步长为2的3×3的最大汇聚层;
·第二模块:包含了两个残差单元,经过运算后,输出通道数为64,特征图的尺寸保持不变;
·第三模块:包含了两个残差单元,经过运算后,输出通道数为128,特征图的尺寸缩小一半;
·第四模块:包含了两个残差单元,经过运算后,输出通道数为256,特征图的尺寸缩小一半;
·第五模块:包含了两个残差单元,经过运算后,输出通道数为512,特征图的尺寸缩小一半;
·第六模块:包含了一个全局平均汇聚层,将特征图变为1×1的大小,最终经过全连接层计算出最后的输出。
代码如下:
# 定义模块一
def make_first_module(in_channels):
# 模块一:7*7卷积、批量规范化、汇聚
m1 = nn.Sequential(nn.Conv2d(in_channels, 64, 7, stride=2, padding=3),
nn.BatchNorm2d(64), nn.ReLU(),
nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
return m1
# 模块二到模块五
def resnet_module(input_channels, out_channels, num_res_blocks, stride=1, use_residual=True):
blk = []
# 根据num_res_blocks,循环生成残差单元
for i in range(num_res_blocks):
if i == 0: # 创建模块中的第一个残差单元
blk.append(ResBlock(input_channels, out_channels,
stride=stride, use_residual=use_residual))
else: # 创建模块中的其他残差单元
blk.append(ResBlock(out_channels, out_channels, use_residual=use_residual))
return blk
# 封装模块二到模块五
def make_modules(use_residual):
# 模块二:包含两个残差单元,输入通道数为64,输出通道数为64,步长为1,特征图大小保持不变
m2 = nn.Sequential(*resnet_module(64, 64, 2, stride=1, use_residual=use_residual))
# 模块三:包含两个残差单元,输入通道数为64,输出通道数为128,步长为2,特征图大小缩小一半。
m3 = nn.Sequential(*resnet_module(64, 128, 2, stride=2, use_residual=use_residual))
# 模块四:包含两个残差单元,输入通道数为128,输出通道数为256,步长为2,特征图大小缩小一半。
m4 = nn.Sequential(*resnet_module(128, 256, 2, stride=2, use_residual=use_residual))
# 模块五:包含两个残差单元,输入通道数为256,输出通道数为512,步长为2,特征图大小缩小一半。
m5 = nn.Sequential(*resnet_module(256, 512, 2, stride=2, use_residual=use_residual))
return m2, m3, m4, m5
# 定义完整网络
class Model_ResNet18(nn.Module):
def __init__(self, in_channels=3, num_classes=10, use_residual=True):
super(Model_ResNet18, self).__init__()
m1 = make_first_module(in_channels)
m2, m3, m4, m5 = make_modules(use_residual)
# 封装模块一到模块6
self.net = nn.Sequential(m1, m2, m3, m4, m5,
# 模块六:汇聚层、全连接层
nn.AdaptiveAvgPool2d(1), nn.Flatten(), nn.Linear(512, num_classes))
def forward(self, x):
return self.net(x)
二、统计模型的参数量和计算量
代码如下:
# 参数量
from torchsummary import summary
device = torch.device("cuda" if torch.cuda.is_available() else "cpu") # PyTorch v0.4.0
model = Model_ResNet18(in_channels=1, num_classes=10, use_residual=True).to(device)
summary(model, (1, 32, 32))
# 计算量
from thop import profile
device = torch.device("cuda" if torch.cuda.is_available() else "cpu") # PyTorch v0.4.0
model = Model_ResNet18(in_channels=1, num_classes=10, use_residual=True).to(device)
dummy_input = torch.randn(1, 1, 32, 32).to(device)
flops, params = profile(model, (dummy_input,))
print(flops)
参数量:
计算量:
从输出可以看出,参数量和计算量比LeNet多的不是一点半点,LeNet的参数量是6万多,计算量是41万多,参数量上去了,运行时间肯定也就多了。
三、数据预处理
代码如下:
# 打印并观察数据集分布情况
train_set, dev_set, test_set = json.load(gzip.open('./mnist.gz'))
train_images, train_labels = train_set[0][:1000], train_set[1][:1000]
dev_images, dev_labels = dev_set[0][:200], dev_set[1][:200]
test_images, test_labels = test_set[0][:200], test_set[1][:200]
train_set, dev_set, test_set = [train_images, train_labels], [dev_images, dev_labels], [test_images, test_labels]
print('Length of train/dev/test set:{}/{}/{}'.format(len(train_set[0]), len(dev_set[0]), len(test_set[0])))
import numpy as np
import matplotlib.pyplot as plt
import PIL.Image as Image
image, label = train_set[0][0], train_set[1][0]
image, label = np.array(image).astype('float32'), int(label)
# 原始图像数据为长度784的行向量,需要调整为[28,28]大小的图像
image = np.reshape(image, [28, 28])
image = Image.fromarray(image.astype('uint8'), mode='L')
print("The number in the picture is {}".format(label))
plt.figure(figsize=(5, 5))
plt.imshow(image)
plt.savefig('conv-number5.pdf')
# # 定义训练集、验证集和测试集
# train_set = {"images": train_images, "labels": train_labels}
# dev_set = {"images": dev_images, "labels": dev_labels}
# test_set = {"images": test_images, "labels": test_labels}
# 数据预处理
transforms = transforms.Compose(
[transforms.Resize(32), transforms.ToTensor(), transforms.Normalize(mean=[0.5], std=[0.5])])
class MNIST_dataset(data.Dataset):
def __init__(self, dataset, transforms, mode='train'):
self.mode = mode
self.transforms = transforms
self.dataset = dataset
def __getitem__(self, idx):
# 从字典中获取图像和标签
# image, label = self.dataset["images"][idx], self.dataset["labels"][idx]
image, label = self.dataset[0][idx], self.dataset[1][idx]
image, label = np.array(image).astype('float32'), int(label)
image = np.reshape(image, [28, 28])
image = Image.fromarray(image.astype('uint8'), mode='L')
image = self.transforms(image)
return image, label
def __len__(self):
# 返回图像数量
# return len(self.dataset["images"])
return len(self.dataset[0])
# 加载 mnist 数据集
train_dataset = MNIST_dataset(dataset=train_set, transforms=transforms, mode='train')
test_dataset = MNIST_dataset(dataset=test_set, transforms=transforms, mode='test')
dev_dataset = MNIST_dataset(dataset=dev_set, transforms=transforms, mode='dev')
四、没有残差连接的ResNet18
代码如下:
time1 = time.time()
seed = 300
torch.manual_seed(seed)
torch.cuda.manual_seed(seed) # 如果使用 GPU,还可以设置 CUDA 的随机种子
torch.backends.cudnn.deterministic = True # 使得 CUDA 确定性计算
torch.backends.cudnn.benchmark = False # 防止优化导致不一致
# 学习率大小
lr = 0.005
# 批次大小
batch_size = 64
# 加载数据
train_loader = data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
dev_loader = data.DataLoader(dev_dataset, batch_size=batch_size)
test_loader = data.DataLoader(test_dataset, batch_size=batch_size)
# 定义网络,不使用残差结构的深层网络
model = Model_ResNet18(in_channels=1, num_classes=10, use_residual=False)
# 定义优化器
optimizer = opt.SGD(lr=lr, params=model.parameters())
# 定义损失函数
loss_fn = F.cross_entropy
# 定义评价指标
metric = Accuracy(is_logist=True)
# 实例化RunnerV3
runner = RunnerV3(model, optimizer, loss_fn, metric)
# 启动训练
log_steps = 15
eval_steps = 15
runner.train(train_loader, dev_loader, num_epochs=10, log_steps=log_steps,
eval_steps=eval_steps, save_path="best_model.pdparams")
time2 = time.time()
# 可视化观察训练集与验证集的Loss变化情况
plot(runner, 'cnn-loss2.pdf')
# 加载最优模型
runner.load_model('best_model.pdparams')
# 模型评价
score, loss = runner.evaluate(test_loader)
print("[Test] accuracy/loss: {:.4f}/{:.4f}".format(score, loss))
print("没有残差连接的ResNet18的运行时间:", time2-time1)
准确率只有66%。但是后面发现调一调参数准确率也是可以达到94.5%的,但是这里不做体现了
因为我们要确保参数一致,再去对比有误残差连接的准确率,这样对比才是有意义的,通过调参而再去对比,就少了一定的说服了,也没有意义。
五、带残差连接的ResNet18
代码如下:
time3 = time.time()
# 固定随机种子
seed = 300
torch.manual_seed(seed)
torch.cuda.manual_seed(seed) # 如果使用 GPU,还可以设置 CUDA 的随机种子
torch.backends.cudnn.deterministic = True # 使得 CUDA 确定性计算
torch.backends.cudnn.benchmark = False # 防止优化导致不一致
# 加载 mnist 数据集
train_dataset = MNIST_dataset(dataset=train_set, transforms=transforms, mode='train')
test_dataset = MNIST_dataset(dataset=test_set, transforms=transforms, mode='test')
dev_dataset = MNIST_dataset(dataset=dev_set, transforms=transforms, mode='dev')
# 学习率大小
lr = 0.005
# 批次大小
batch_size = 16
# 加载数据
train_loader = data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
dev_loader = data.DataLoader(dev_dataset, batch_size=batch_size)
test_loader = data.DataLoader(test_dataset, batch_size=batch_size)
# 定义网络,通过指定use_residual为True,使用残差结构的深层网络
model = Model_ResNet18(in_channels=1, num_classes=10, use_residual=True)
# 定义优化器
optimizer = opt.SGD(lr=lr, params=model.parameters())
# 定义损失函数
loss_fn = F.cross_entropy
# 定义评价指标
metric = Accuracy(is_logist=True)
# 实例化RunnerV3
runner = RunnerV3(model, optimizer, loss_fn, metric)
# 启动训练
log_steps = 15
eval_steps = 15
runner.train(train_loader, dev_loader, num_epochs=10, log_steps=log_steps,
eval_steps=eval_steps, save_path="best_model.pdparams")
time4 = time.time()
# 可视化观察训练集与验证集的Loss变化情况
plot(runner, 'cnn-loss3.pdf')
# 加载最优模型
runner.load_model('best_model.pdparams')
# 模型评价
score, loss = runner.evaluate(test_loader)
print("[Test] accuracy/loss: {:.4f}/{:.4f}".format(score, loss))
print("有残差连接的ResNet18的运行时间:", time4-time3)
有残差连接的网络比没有残差连接的网络准确率高很多,那么这是为什么呢?
ResNet的论文中提到,更深的网络有更高的训练误差,所以就会有更高的测试误差。
同时来说,随着网络深度的增加,会带来了许多优化相关的问题,比如梯度消散,梯度爆炸。也有人将其比做成一个传话游戏,就是越往后传,错误也就越高。再举一个栗子:
假如有一个网络,输入x=1,非残差网络为G,残差网络为H,其中H(x)=F(x)+x,假如有这样的输入关系:
因为两者各自是对G的参数和F的参数进行更新,可以看出变化对F的影响远远大于G,说明引入残差后的映射对输出的变化更敏感,这样是有利于网络进行传播的。从论文中的对比也可以看出,残差网络layer升高后,error并没有像普通网络一样也升高。
再对比运行时间:
两者虽然相差不大,但是却比LeNet5的时间长很多,LeNet5训练只需要3秒多。
附:完整的可运行代码
主代码:
time3 = time.time()
# 固定随机种子
seed = 300
torch.manual_seed(seed)
torch.cuda.manual_seed(seed) # 如果使用 GPU,还可以设置 CUDA 的随机种子
torch.backends.cudnn.deterministic = True # 使得 CUDA 确定性计算
torch.backends.cudnn.benchmark = False # 防止优化导致不一致
# 加载 mnist 数据集
train_dataset = MNIST_dataset(dataset=train_set, transforms=transforms, mode='train')
test_dataset = MNIST_dataset(dataset=test_set, transforms=transforms, mode='test')
dev_dataset = MNIST_dataset(dataset=dev_set, transforms=transforms, mode='dev')
# 学习率大小
lr = 0.005
# 批次大小
batch_size = 16
# 加载数据
train_loader = data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
dev_loader = data.DataLoader(dev_dataset, batch_size=batch_size)
test_loader = data.DataLoader(test_dataset, batch_size=batch_size)
# 定义网络,通过指定use_residual为True,使用残差结构的深层网络
model = Model_ResNet18(in_channels=1, num_classes=10, use_residual=True)
# 定义优化器
optimizer = opt.SGD(lr=lr, params=model.parameters())
# 定义损失函数
loss_fn = F.cross_entropy
# 定义评价指标
metric = Accuracy(is_logist=True)
# 实例化RunnerV3
runner = RunnerV3(model, optimizer, loss_fn, metric)
# 启动训练
log_steps = 15
eval_steps = 15
runner.train(train_loader, dev_loader, num_epochs=10, log_steps=log_steps,
eval_steps=eval_steps, save_path="best_model.pdparams")
time4 = time.time()
# 可视化观察训练集与验证集的Loss变化情况
plot(runner, 'cnn-loss3.pdf')
# 加载最优模型
runner.load_model('best_model.pdparams')
# 模型评价
score, loss = runner.evaluate(test_loader)
print("[Test] accuracy/loss: {:.4f}/{:.4f}".format(score, loss))
print("有残差连接的ResNet18的运行时间:", time4-time3)
nndl_3代码:
import torch
from matplotlib import pyplot as plt
from torch import nn
class Op(object):
def __init__(self):
pass
def __call__(self, inputs):
return self.forward(inputs)
def forward(self, inputs):
raise NotImplementedError
def backward(self, inputs):
raise NotImplementedError
# 实现一个两层前馈神经网络
class Model_MLP_L2_V3(torch.nn.Module):
def __init__(self, input_size, hidden_size, output_size):
super(Model_MLP_L2_V3, self).__init__()
self.fc1 = torch.nn.Linear(input_size, hidden_size)
w_ = torch.normal(0, 0.01, size=(hidden_size, input_size), requires_grad=True)
self.fc1.weight = torch.nn.Parameter(w_)
self.fc1.bias = torch.nn.init.constant_(self.fc1.bias, val=1.0)
self.fc2 = torch.nn.Linear(hidden_size, output_size)
w2 = torch.normal(0, 0.01, size=(output_size, hidden_size), requires_grad=True)
self.fc2.weight = nn.Parameter(w2)
self.fc2.bias = torch.nn.init.constant_(self.fc2.bias, val=1.0)
self.act = torch.sigmoid
def forward(self, inputs):
outputs = self.fc1(inputs)
outputs = self.act(outputs)
outputs = self.fc2(outputs)
return outputs
class RunnerV3(object):
def __init__(self, model, optimizer, loss_fn, metric, **kwargs):
self.model = model
self.optimizer = optimizer
self.loss_fn = loss_fn
self.metric = metric # 只用于计算评价指标
# 记录训练过程中的评价指标变化情况
self.dev_scores = []
# 记录训练过程中的损失函数变化情况
self.train_epoch_losses = [] # 一个epoch记录一次loss
self.train_step_losses = [] # 一个step记录一次loss
self.dev_losses = []
# 记录全局最优指标
self.best_score = 0
def train(self, train_loader, dev_loader=None, **kwargs):
# 将模型切换为训练模式
self.model.train()
# 传入训练轮数,如果没有传入值则默认为0
num_epochs = kwargs.get("num_epochs", 0)
# 传入log打印频率,如果没有传入值则默认为100
log_steps = kwargs.get("log_steps", 100)
# 评价频率
eval_steps = kwargs.get("eval_steps", 0)
# 传入模型保存路径,如果没有传入值则默认为"best_model.pdparams"
save_path = kwargs.get("save_path", "best_model.pdparams")
custom_print_log = kwargs.get("custom_print_log", None)
# 训练总的步数
num_training_steps = num_epochs * len(train_loader)
if eval_steps:
if self.metric is None:
raise RuntimeError('Error: Metric can not be None!')
if dev_loader is None:
raise RuntimeError('Error: dev_loader can not be None!')
# 运行的step数目
global_step = 0
# 进行num_epochs轮训练
for epoch in range(num_epochs):
# 用于统计训练集的损失
total_loss = 0
for step, data in enumerate(train_loader):
X, y = data
# 获取模型预测
logits = self.model(X)
loss = self.loss_fn(logits, y) # 默认求mean
total_loss += loss
# 训练过程中,每个step的loss进行保存
self.train_step_losses.append((global_step, loss.item()))
if log_steps and global_step % log_steps == 0:
print(
f"[Train] epoch: {epoch}/{num_epochs}, step: {global_step}/{num_training_steps}, loss: {loss.item():.5f}")
# 梯度反向传播,计算每个参数的梯度值
loss.backward()
if custom_print_log:
custom_print_log(self)
# 小批量梯度下降进行参数更新
self.optimizer.step()
# 梯度归零
self.optimizer.zero_grad()
# 判断是否需要评价
if eval_steps > 0 and global_step > 0 and \
(global_step % eval_steps == 0 or global_step == (num_training_steps - 1)):
dev_score, dev_loss = self.evaluate(dev_loader, global_step=global_step)
print(f"[Evaluate] dev score: {dev_score:.5f}, dev loss: {dev_loss:.5f}")
# 将模型切换为训练模式
self.model.train()
# 如果当前指标为最优指标,保存该模型
if dev_score > self.best_score:
self.save_model(save_path)
print(
f"[Evaluate] best accuracy performence has been updated: {self.best_score:.5f} --> {dev_score:.5f}")
self.best_score = dev_score
global_step += 1
# 当前epoch 训练loss累计值
trn_loss = (total_loss / len(train_loader)).item()
# epoch粒度的训练loss保存
self.train_epoch_losses.append(trn_loss)
print("[Train] Training done!")
# 模型评估阶段,使用'torch.no_grad()'控制不计算和存储梯度
@torch.no_grad()
def evaluate(self, dev_loader, **kwargs):
assert self.metric is not None
# 将模型设置为评估模式
self.model.eval()
global_step = kwargs.get("global_step", -1)
# 用于统计训练集的损失
total_loss = 0
# 重置评价
self.metric.reset()
# 遍历验证集每个批次
for batch_id, data in enumerate(dev_loader):
X, y = data
# 计算模型输出
logits = self.model(X)
# 计算损失函数
loss = self.loss_fn(logits, y).item()
# 累积损失
total_loss += loss
# 累积评价
self.metric.update(logits, y)
dev_loss = (total_loss / len(dev_loader))
dev_score = self.metric.accumulate()
# 记录验证集loss
if global_step != -1:
self.dev_losses.append((global_step, dev_loss))
self.dev_scores.append(dev_score)
return dev_score, dev_loss
# 模型评估阶段,使用'torch.no_grad()'控制不计算和存储梯度
@torch.no_grad()
def predict(self, x, **kwargs):
# 将模型设置为评估模式
self.model.eval()
# 运行模型前向计算,得到预测值
logits = self.model(x)
return logits
def save_model(self, save_path):
torch.save(self.model.state_dict(), save_path)
def load_model(self, model_path):
model_state_dict = torch.load(model_path)
self.model.load_state_dict(model_state_dict)
class Accuracy():
def __init__(self, is_logist=True):
# 用于统计正确的样本个数
self.num_correct = 0
# 用于统计样本的总数
self.num_count = 0
self.is_logist = is_logist
def update(self, outputs, labels):
if outputs.shape[1] == 1: # 二分类
outputs = torch.squeeze(outputs, dim=-1)
if self.is_logist:
# logist判断是否大于0
preds = torch.tensor((outputs >= 0), dtype=torch.float32)
else:
# 如果不是logist,判断每个概率值是否大于0.5,当大于0.5时,类别为1,否则类别为0
preds = torch.tensor((outputs >= 0.5), dtype=torch.float32)
else:
# 多分类时,使用'torch.argmax'计算最大元素索引作为类别
preds = torch.argmax(outputs, dim=1)
# 获取本批数据中预测正确的样本个数
labels = torch.squeeze(labels, dim=-1)
batch_correct = torch.sum(torch.tensor(preds == labels, dtype=torch.float32)).numpy()
batch_count = len(labels)
# 更新num_correct 和 num_count
self.num_correct += batch_correct
self.num_count += batch_count
def accumulate(self):
# 使用累计的数据,计算总的指标
if self.num_count == 0:
return 0
return self.num_correct / self.num_count
def reset(self):
# 重置正确的数目和总数
self.num_correct = 0
self.num_count = 0
def name(self):
return "Accuracy"
# 可视化
def plot(runner, fig_name):
plt.figure(figsize=(10, 5))
plt.subplot(1, 2, 1)
train_items = runner.train_step_losses[::30]
train_steps = [x[0] for x in train_items]
train_losses = [x[1] for x in train_items]
plt.plot(train_steps, train_losses, color='#8E004D', label="Train loss")
if runner.dev_losses[0][0] != -1:
dev_steps = [x[0] for x in runner.dev_losses]
dev_losses = [x[1] for x in runner.dev_losses]
plt.plot(dev_steps, dev_losses, color='#E20079', linestyle='--', label="Dev loss")
# 绘制坐标轴和图例
plt.ylabel("loss", fontsize='x-large')
plt.xlabel("step", fontsize='x-large')
plt.legend(loc='upper right', fontsize='x-large')
plt.subplot(1, 2, 2)
# 绘制评价准确率变化曲线
if runner.dev_losses[0][0] != -1:
plt.plot(dev_steps, runner.dev_scores,
color='#E20079', linestyle="--", label="Dev accuracy")
else:
plt.plot(list(range(len(runner.dev_scores))), runner.dev_scores,
color='#E20079', linestyle="--", label="Dev accuracy")
# 绘制坐标轴和图例
plt.ylabel("score", fontsize='x-large')
plt.xlabel("step", fontsize='x-large')
plt.legend(loc='lower right', fontsize='x-large')
plt.savefig(fig_name)
plt.show()
这次的分享就到这里,下次再见~