Pytorch没有官方的高阶API。一般通过nn.Module来构建模型并编写自定义训练循环。
为了更加方便地训练模型，作者编写了仿keras的Pytorch模型接口：torchkeras， 作为Pytorch的高阶API。
本章我们主要详细介绍Pytorch的高阶API如下相关的内容。
- 构建模型的3种方法(继承nn.Module基类，使用nn.Sequential，辅助应用模型容器)
- 训练模型的3种方法(脚本风格，函数风格，torchkeras.Model类风格)
- 使用GPU训练模型(单GPU训练，多GPU训练)
本篇我们介绍训练模型的3种方法。
pytorch通常需要用户编写自定义训练循环，训练循环的代码风格因人而异。
有3类典型的训练循环代码风格：脚本形式训练循环，函数形式训练循环，类形式训练循环。
下面以minist数据集的分类模型的训练为例，演示这3种训练模型的风格。
〇，准备数据
代码语言：javascript复制import torch
from torch import nn
from torchkeras import summary,Model
import torchvision
from torchvision import transforms
transform = transforms.Compose([transforms.ToTensor()])
ds_train = torchvision.datasets.MNIST(root="./data/minist/",train=True,download=True,transform=transform)
ds_valid = torchvision.datasets.MNIST(root="./data/minist/",train=False,download=True,transform=transform)
dl_train = torch.utils.data.DataLoader(ds_train, batch_size=128, shuffle=True, num_workers=4)
dl_valid = torch.utils.data.DataLoader(ds_valid, batch_size=128, shuffle=False, num_workers=4)
print(len(ds_train))
print(len(ds_valid))
60000
10000
%matplotlib inline
%config InlineBackend.figure_format = 'svg'
#查看部分样本
from matplotlib import pyplot as plt
plt.figure(figsize=(8,8))
for i in range(9):
img,label = ds_train[i]
img = torch.squeeze(img)
ax=plt.subplot(3,3,i 1)
ax.imshow(img.numpy())
ax.set_title("label = %d"%label)
ax.set_xticks([])
ax.set_yticks([])
plt.show()
一，脚本风格
脚本风格的训练循环最为常见。
代码语言：javascript复制net = nn.Sequential()
net.add_module("conv1",nn.Conv2d(in_channels=1,out_channels=32,kernel_size = 3))
net.add_module("pool1",nn.MaxPool2d(kernel_size = 2,stride = 2))
net.add_module("conv2",nn.Conv2d(in_channels=32,out_channels=64,kernel_size = 5))
net.add_module("pool2",nn.MaxPool2d(kernel_size = 2,stride = 2))
net.add_module("dropout",nn.Dropout2d(p = 0.1))
net.add_module("adaptive_pool",nn.AdaptiveMaxPool2d((1,1)))
net.add_module("flatten",nn.Flatten())
net.add_module("linear1",nn.Linear(64,32))
net.add_module("relu",nn.ReLU())
net.add_module("linear2",nn.Linear(32,10))
print(net)
Sequential(
(conv1): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1))
(pool1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(conv2): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1))
(pool2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(dropout): Dropout2d(p=0.1, inplace=False)
(adaptive_pool): AdaptiveMaxPool2d(output_size=(1, 1))
(flatten): Flatten()
(linear1): Linear(in_features=64, out_features=32, bias=True)
(relu): ReLU()
(linear2): Linear(in_features=32, out_features=10, bias=True)
)
summary(net,input_shape=(1,32,32))
----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 32, 30, 30] 320
MaxPool2d-2 [-1, 32, 15, 15] 0
Conv2d-3 [-1, 64, 11, 11] 51,264
MaxPool2d-4 [-1, 64, 5, 5] 0
Dropout2d-5 [-1, 64, 5, 5] 0
AdaptiveMaxPool2d-6 [-1, 64, 1, 1] 0
Flatten-7 [-1, 64] 0
Linear-8 [-1, 32] 2,080
ReLU-9 [-1, 32] 0
Linear-10 [-1, 10] 330
================================================================
Total params: 53,994
Trainable params: 53,994
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.003906
Forward/backward pass size (MB): 0.359695
Params size (MB): 0.205971
Estimated Total Size (MB): 0.569572
----------------------------------------------------------------
import datetime
import numpy as np
import pandas as pd
from sklearn.metrics import accuracy_score
def accuracy(y_pred,y_true):
y_pred_cls = torch.argmax(nn.Softmax(dim=1)(y_pred),dim=1).data
return accuracy_score(y_true,y_pred_cls)
loss_func = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(params=net.parameters(),lr = 0.01)
metric_func = accuracy
metric_name = "accuracy"
epochs = 3
log_step_freq = 100
dfhistory = pd.DataFrame(columns = ["epoch","loss",metric_name,"val_loss","val_" metric_name])
print("Start Training...")
nowtime = datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')
print("=========="*8 "%s"%nowtime)
for epoch in range(1,epochs 1):
# 1，训练循环-------------------------------------------------
net.train()
loss_sum = 0.0
metric_sum = 0.0
step = 1
for step, (features,labels) in enumerate(dl_train, 1):
# 梯度清零
optimizer.zero_grad()
# 正向传播求损失
predictions = net(features)
loss = loss_func(predictions,labels)
metric = metric_func(predictions,labels)
# 反向传播求梯度
loss.backward()
optimizer.step()
# 打印batch级别日志
loss_sum = loss.item()
metric_sum = metric.item()
if step%log_step_freq == 0:
print(("[step = %d] loss: %.3f, " metric_name ": %.3f") %
(step, loss_sum/step, metric_sum/step))
# 2，验证循环-------------------------------------------------
net.eval()
val_loss_sum = 0.0
val_metric_sum = 0.0
val_step = 1
for val_step, (features,labels) in enumerate(dl_valid, 1):
predictions = net(features)
val_loss = loss_func(predictions,labels)
val_metric = metric_func(predictions,labels)
val_loss_sum = val_loss.item()
val_metric_sum = val_metric.item()
# 3，记录日志-------------------------------------------------
info = (epoch, loss_sum/step, metric_sum/step,
val_loss_sum/val_step, val_metric_sum/val_step)
dfhistory.loc[epoch-1] = info
# 打印epoch级别日志
print(("nEPOCH = %d, loss = %.3f," metric_name
" = %.3f, val_loss = %.3f, " "val_" metric_name " = %.3f")
%info)
nowtime = datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')
print("n" "=========="*8 "%s"%nowtime)
print('Finished Training...')
Start Training...
================================================================================2020-06-26 12:49:16
[step = 100] loss: 0.742, accuracy: 0.745
[step = 200] loss: 0.466, accuracy: 0.843
[step = 300] loss: 0.363, accuracy: 0.880
[step = 400] loss: 0.310, accuracy: 0.898
EPOCH = 1, loss = 0.281,accuracy = 0.908, val_loss = 0.087, val_accuracy = 0.972
================================================================================2020-06-26 12:50:32
[step = 100] loss: 0.103, accuracy: 0.970
[step = 200] loss: 0.114, accuracy: 0.966
[step = 300] loss: 0.112, accuracy: 0.967
[step = 400] loss: 0.108, accuracy: 0.968
EPOCH = 2, loss = 0.111,accuracy = 0.967, val_loss = 0.082, val_accuracy = 0.976
================================================================================2020-06-26 12:51:47
[step = 100] loss: 0.093, accuracy: 0.972
[step = 200] loss: 0.095, accuracy: 0.971
[step = 300] loss: 0.092, accuracy: 0.972
[step = 400] loss: 0.093, accuracy: 0.972
EPOCH = 3, loss = 0.098,accuracy = 0.971, val_loss = 0.113, val_accuracy = 0.970
================================================================================2020-06-26 12:53:09
Finished Training...二，函数风格
该风格在脚本形式上作了简单的函数封装。
代码语言：javascript复制class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.layers = nn.ModuleList([
nn.Conv2d(in_channels=1,out_channels=32,kernel_size = 3),
nn.MaxPool2d(kernel_size = 2,stride = 2),
nn.Conv2d(in_channels=32,out_channels=64,kernel_size = 5),
nn.MaxPool2d(kernel_size = 2,stride = 2),
nn.Dropout2d(p = 0.1),
nn.AdaptiveMaxPool2d((1,1)),
nn.Flatten(),
nn.Linear(64,32),
nn.ReLU(),
nn.Linear(32,10)]
)
def forward(self,x):
for layer in self.layers:
x = layer(x)
return x
net = Net()
print(net)
Net(
(layers): ModuleList(
(0): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1))
(1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(2): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1))
(3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(4): Dropout2d(p=0.1, inplace=False)
(5): AdaptiveMaxPool2d(output_size=(1, 1))
(6): Flatten()
(7): Linear(in_features=64, out_features=32, bias=True)
(8): ReLU()
(9): Linear(in_features=32, out_features=10, bias=True)
)
)
summary(net,input_shape=(1,32,32))
----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 32, 30, 30] 320
MaxPool2d-2 [-1, 32, 15, 15] 0
Conv2d-3 [-1, 64, 11, 11] 51,264
MaxPool2d-4 [-1, 64, 5, 5] 0
Dropout2d-5 [-1, 64, 5, 5] 0
AdaptiveMaxPool2d-6 [-1, 64, 1, 1] 0
Flatten-7 [-1, 64] 0
Linear-8 [-1, 32] 2,080
ReLU-9 [-1, 32] 0
Linear-10 [-1, 10] 330
================================================================
Total params: 53,994
Trainable params: 53,994
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.003906
Forward/backward pass size (MB): 0.359695
Params size (MB): 0.205971
Estimated Total Size (MB): 0.569572
----------------------------------------------------------------
import datetime
import numpy as np
import pandas as pd
from sklearn.metrics import accuracy_score
def accuracy(y_pred,y_true):
y_pred_cls = torch.argmax(nn.Softmax(dim=1)(y_pred),dim=1).data
return accuracy_score(y_true,y_pred_cls)
model = net
model.optimizer = torch.optim.SGD(model.parameters(),lr = 0.01)
model.loss_func = nn.CrossEntropyLoss()
model.metric_func = accuracy
model.metric_name = "accuracy"
def train_step(model,features,labels):
# 训练模式，dropout层发生作用
model.train()
# 梯度清零
model.optimizer.zero_grad()
# 正向传播求损失
predictions = model(features)
loss = model.loss_func(predictions,labels)
metric = model.metric_func(predictions,labels)
# 反向传播求梯度
loss.backward()
model.optimizer.step()
return loss.item(),metric.item()
def valid_step(model,features,labels):
# 预测模式，dropout层不发生作用
model.eval()
predictions = model(features)
loss = model.loss_func(predictions,labels)
metric = model.metric_func(predictions,labels)
return loss.item(), metric.item()
# 测试train_step效果
features,labels = next(iter(dl_train))
train_step(model,features,labels)
(2.32741117477417, 0.1015625)
def train_model(model,epochs,dl_train,dl_valid,log_step_freq):
metric_name = model.metric_name
dfhistory = pd.DataFrame(columns = ["epoch","loss",metric_name,"val_loss","val_" metric_name])
print("Start Training...")
nowtime = datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')
print("=========="*8 "%s"%nowtime)
for epoch in range(1,epochs 1):
# 1，训练循环-------------------------------------------------
loss_sum = 0.0
metric_sum = 0.0
step = 1
for step, (features,labels) in enumerate(dl_train, 1):
loss,metric = train_step(model,features,labels)
# 打印batch级别日志
loss_sum = loss
metric_sum = metric
if step%log_step_freq == 0:
print(("[step = %d] loss: %.3f, " metric_name ": %.3f") %
(step, loss_sum/step, metric_sum/step))
# 2，验证循环-------------------------------------------------
val_loss_sum = 0.0
val_metric_sum = 0.0
val_step = 1
for val_step, (features,labels) in enumerate(dl_valid, 1):
val_loss,val_metric = valid_step(model,features,labels)
val_loss_sum = val_loss
val_metric_sum = val_metric
# 3，记录日志-------------------------------------------------
info = (epoch, loss_sum/step, metric_sum/step,
val_loss_sum/val_step, val_metric_sum/val_step)
dfhistory.loc[epoch-1] = info
# 打印epoch级别日志
print(("nEPOCH = %d, loss = %.3f," metric_name
" = %.3f, val_loss = %.3f, " "val_" metric_name " = %.3f")
%info)
nowtime = datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')
print("n" "=========="*8 "%s"%nowtime)
print('Finished Training...')
return dfhistory
epochs = 3
dfhistory = train_model(model,epochs,dl_train,dl_valid,log_step_freq = 100)
Start Training...
================================================================================2020-06-26 13:10:00
[step = 100] loss: 2.298, accuracy: 0.137
[step = 200] loss: 2.288, accuracy: 0.145
[step = 300] loss: 2.278, accuracy: 0.165
[step = 400] loss: 2.265, accuracy: 0.183
EPOCH = 1, loss = 2.254,accuracy = 0.195, val_loss = 2.158, val_accuracy = 0.301
================================================================================2020-06-26 13:11:23
[step = 100] loss: 2.127, accuracy: 0.302
[step = 200] loss: 2.080, accuracy: 0.338
[step = 300] loss: 2.025, accuracy: 0.374
[step = 400] loss: 1.957, accuracy: 0.411
EPOCH = 2, loss = 1.905,accuracy = 0.435, val_loss = 1.469, val_accuracy = 0.710
================================================================================2020-06-26 13:12:43
[step = 100] loss: 1.435, accuracy: 0.615
[step = 200] loss: 1.324, accuracy: 0.647
[step = 300] loss: 1.221, accuracy: 0.672
[step = 400] loss: 1.132, accuracy: 0.696
EPOCH = 3, loss = 1.074,accuracy = 0.711, val_loss = 0.582, val_accuracy = 0.878
================================================================================2020-06-26 13:13:59
Finished Training...
三，类风格
此处使用torchkeras中定义的模型接口构建模型，并调用compile方法和fit方法训练模型。
使用该形式训练模型非常简洁明了。推荐使用该形式。
代码语言：javascript复制class CnnModel(nn.Module):
def __init__(self):
super().__init__()
self.layers = nn.ModuleList([
nn.Conv2d(in_channels=1,out_channels=32,kernel_size = 3),
nn.MaxPool2d(kernel_size = 2,stride = 2),
nn.Conv2d(in_channels=32,out_channels=64,kernel_size = 5),
nn.MaxPool2d(kernel_size = 2,stride = 2),
nn.Dropout2d(p = 0.1),
nn.AdaptiveMaxPool2d((1,1)),
nn.Flatten(),
nn.Linear(64,32),
nn.ReLU(),
nn.Linear(32,10)]
)
def forward(self,x):
for layer in self.layers:
x = layer(x)
return x
model = torchkeras.Model(CnnModel())
print(model)
CnnModel(
(layers): ModuleList(
(0): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1))
(1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(2): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1))
(3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(4): Dropout2d(p=0.1, inplace=False)
(5): AdaptiveMaxPool2d(output_size=(1, 1))
(6): Flatten()
(7): Linear(in_features=64, out_features=32, bias=True)
(8): ReLU()
(9): Linear(in_features=32, out_features=10, bias=True)
)
)
model.summary(input_shape=(1,32,32))
----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 32, 30, 30] 320
MaxPool2d-2 [-1, 32, 15, 15] 0
Conv2d-3 [-1, 64, 11, 11] 51,264
MaxPool2d-4 [-1, 64, 5, 5] 0
Dropout2d-5 [-1, 64, 5, 5] 0
AdaptiveMaxPool2d-6 [-1, 64, 1, 1] 0
Flatten-7 [-1, 64] 0
Linear-8 [-1, 32] 2,080
ReLU-9 [-1, 32] 0
Linear-10 [-1, 10] 330
================================================================
Total params: 53,994
Trainable params: 53,994
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.003906
Forward/backward pass size (MB): 0.359695
Params size (MB): 0.205971
Estimated Total Size (MB): 0.569572
----------------------------------------------------------------
from sklearn.metrics import accuracy_score
def accuracy(y_pred,y_true):
y_pred_cls = torch.argmax(nn.Softmax(dim=1)(y_pred),dim=1).data
return accuracy_score(y_true.numpy(),y_pred_cls.numpy())
model.compile(loss_func = nn.CrossEntropyLoss(),
optimizer= torch.optim.Adam(model.parameters(),lr = 0.02),
metrics_dict={"accuracy":accuracy})
dfhistory = model.fit(3,dl_train = dl_train, dl_val=dl_valid, log_step_freq=100)
Start Training ...
================================================================================2020-06-26 13:22:39
{'step': 100, 'loss': 0.976, 'accuracy': 0.664}
{'step': 200, 'loss': 0.611, 'accuracy': 0.795}
{'step': 300, 'loss': 0.478, 'accuracy': 0.841}
{'step': 400, 'loss': 0.403, 'accuracy': 0.868}
------- ------- ---------- ---------- --------------
| epoch | loss | accuracy | val_loss | val_accuracy |
------- ------- ---------- ---------- --------------
| 1 | 0.371 | 0.879 | 0.087 | 0.972 |
------- ------- ---------- ---------- --------------
================================================================================2020-06-26 13:23:59
{'step': 100, 'loss': 0.182, 'accuracy': 0.948}
{'step': 200, 'loss': 0.176, 'accuracy': 0.949}
{'step': 300, 'loss': 0.173, 'accuracy': 0.95}
{'step': 400, 'loss': 0.174, 'accuracy': 0.951}
------- ------- ---------- ---------- --------------
| epoch | loss | accuracy | val_loss | val_accuracy |
------- ------- ---------- ---------- --------------
| 2 | 0.175 | 0.951 | 0.152 | 0.958 |
------- ------- ---------- ---------- --------------
================================================================================2020-06-26 13:25:22
{'step': 100, 'loss': 0.143, 'accuracy': 0.961}
{'step': 200, 'loss': 0.151, 'accuracy': 0.959}
{'step': 300, 'loss': 0.149, 'accuracy': 0.96}
{'step': 400, 'loss': 0.152, 'accuracy': 0.959}
------- ------- ---------- ---------- --------------
| epoch | loss | accuracy | val_loss | val_accuracy |
------- ------- ---------- ---------- --------------
| 3 | 0.153 | 0.959 | 0.086 | 0.975 |
------- ------- ---------- ---------- --------------
================================================================================2020-06-26 13:26:48
Finished Training...
