本文参加新星计划人工智能(Pytorch)赛道：https://bbs.csdn.net/topics/613989052

从零开始网格上的深度学习-4:训练测试篇

• 引言
• 一、概述
• 二、核心代码
• • 2.1 网格上的Transformer
  • 2.2 模型初始化、学习率动态调整
  • 2.3 随机种子设定、使用tensorboardX可视化
• 三、网格分类实验
• • 3.1 分类结果
  • 3.2 全部代码

引言

本文主要内容如下：

• 对上一篇Transformer网络进行改进
• 加入模型初始化、学习率动态调整
• 设定随机种子、打印训练时间、使用tensorboardX可视化(上图)

一、概述

• 前三篇主要讲述了网格的输入特征以及网络框架部分，包括了基于面元素的二面角特征计算、卷积网络、Transformer网络，以及隐含网络中的激活函数、归一化函数、损失函数等等。

除了以上内容，还有一些知识点是深度学习的重要组成部分：如何训练一个网络… 如：网络的初始化-Kaiming初始化、学习率的调整-模拟退火、训练loss的可视化以调整网络框架 or 微调参数-tensorboardX、优化器-Adam等等 本文对以上内容进行简述

二、核心代码

2.1 网格上的Transformer

• 将sum求和形式的位置嵌入，改为了concat拼接，然后统一经过两个面卷积层
• 最后增加了一个线性层

Transformer.py

class TriTransNet(nn.Module):def __init__(self, classes_n=30):super().__init__()self.conv_1 = FaceConv(9, 128, 4)self.conv_2 = FaceConv(128, 128, 4)self.bn_1 = nn.BatchNorm1d(128)self.bn_2 = nn.BatchNorm1d(128)self.sa1 = SA(128)self.sa2 = SA(128)self.gp = nn.AdaptiveAvgPool1d(1)self.linear1 = nn.Linear(256, 128, bias=False)self.bn1 = nn.BatchNorm1d(128)self.linear2 = nn.Linear(128, 64)self.bn2 = nn.BatchNorm1d(64)self.linear3 = nn.Linear(64, classes_n)self.act = nn.GELU()def forward(self, x, mesh):x = x.permute(0, 2, 1).contiguous()# 位置编码 放到DataLoader中比较好pos = [m.xyz for m in mesh]pos = np.array(pos)pos = torch.from_numpy(pos).float().to(x.device).requires_grad_(True)batch_size, _, N = x.size()x = torch.cat((x, pos), dim=1)        # 拼接 Not sumx = self.act(self.bn_1(self.conv_1(x, mesh).squeeze(-1)))x = self.act(self.bn_2(self.conv_2(x, mesh).squeeze(-1)))x1 = self.sa1(x)x2 = self.sa2(x1)x = torch.cat((x1, x2), dim=1)x = self.gp(x)x = x.view(batch_size, -1)x = self.act(self.bn1(self.linear1(x)))x = self.act(self.bn2(self.linear2(x)))x = self.linear3(x)return x

2.2 模型初始化、学习率动态调整

• 网络模型初始化策略有很多：预训练、随机、固定…等初始化

可参考¹:pytorch nn.init 中实现的初始化函数 uniform, normal, const, Xavier, He initialization

def init_func(m):className = m.__class__.__name__if hasattr(m, 'weight') and (className.find('Conv') != -1 or className.find('Linear') != -1):torch.nn.init.normal_(m.weight.data, 0.0, 0.02)

以上进行对线性层和卷积层中的参数进行normal_初始化，均值=0 标准差=0.02

• 学习率的调整为训练一定轮次后线性衰减，使用Adam优化器

可参考²:史上最全学习率调整策略lr_scheduler

def get_scheduler(optimizer, epoch_max):def lambda_rule(epoch):lr_l = 1.0 - max(0, epoch + 1 + 1 - epoch_max/2) / float(epoch_max/2 + 1)return lr_lscheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lambda_rule)return scheduler

optimizer = torch.optim.Adam(self.net.parameters(), lr=0.001, betas=(0.9, 0.999))

2.3 随机种子设定、使用tensorboardX可视化

• 设定随机种子，方便实验复现 但很难进行一丝不差的进行复现

详情可参考³:【pytorch】结果无法复现

	import numpy as npimport randomimport torchrandom.seed(0)np.random.seed(0)torch.manual_seed(0)torch.cuda.manual_seed(0)torch.cuda.manual_seed_all(0)

• 使用tensorboardX可视化

# 先进行创建
SW = SummaryWriter(log_dir='runs', comment='cls')  

# 然后add相关数据 绘制曲线即可
SW.add_scalar('data/train_loss', loss, epoch)
SW.add_scalar('data/test_acc', acc, epoch)

然后在控制台中输入tensorboard --logdir [path]即可 [path]就是SummaryWriter创建log_dir路径runs下生成的events开头的文件，如下图：

三、网格分类实验

数据集是SHREC’11 可参考三角网格(Triangular Mesh)分类数据集

3.1 分类结果

相比⁴:从零开始网格上的深度学习-3:Transformer篇
准确率提升约十个百分点 84% -> 94%

3.2 全部代码

DataLoader代码请参考⁵:从零开始网格上的深度学习-1:输入篇(Pytorch)
FaceConv代码请参考⁶:从零开始网格上的深度学习-2:卷积网络CNN篇

• Model.py

from torch.optim import lr_scheduler
import torch
from Transformer import TriTransNetdef init_func(m):className = m.__class__.__name__if hasattr(m, 'weight') and (className.find('Conv') != -1 or className.find('Linear') != -1):torch.nn.init.normal_(m.weight.data, 0.0, 0.02)def get_scheduler(optimizer, epoch_max):def lambda_rule(epoch):lr_l = 1.0 - max(0, epoch + 1 + 1 - epoch_max/2) / float(epoch_max/2 + 1)return lr_lscheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lambda_rule)return schedulerclass Model:def __init__(self):self.device = torch.device('cuda:0')  # torch.device('cpu')self.loss_fun = torch.nn.CrossEntropyLoss(ignore_index=-1)self.loss = None# 网络self.net = TriTransNet()self.optimizer = torch.optim.Adam(self.net.parameters(), lr=0.001, betas=(0.9, 0.999))self.scheduler = get_scheduler(self.optimizer, epoch_max=200)# 自定义初始化self.net = self.net.cuda(0)self.net.apply(init_func)# 打印网络参数量num_params = 0for param in self.net.parameters():num_params += param.numel()print('[Network] Total number of parameters : %.3f M' % (num_params / 1e6))print('-----------------------------------------------')def train(self, data):self.net.train(True)self.optimizer.zero_grad()  # 梯度清零# 前向传播face_features = torch.from_numpy(data['face_features']).float()face_features = face_features.to(self.device).requires_grad_(True)labels = torch.from_numpy(data['label']).long().to(self.device)mesh = data['mesh']out = self.net(face_features, mesh)# 反向传播loss = self.loss_fun(out, labels)loss.backward()self.loss = float(loss)  # 只要值self.optimizer.step()    # 参数更新def test(self, data):self.net.eval()with torch.no_grad():# 前向传播face_features = torch.from_numpy(data['face_features']).float()face_features = face_features.to(self.device).requires_grad_(False)labels = torch.from_numpy(data['label']).long().to(self.device)mesh = data['mesh']out = self.net(face_features, mesh)# 计算准确率pred_class = out.data.max(1)[1]correct = pred_class.eq(labels).sum().float()return correctdef update_learning_rate(self):self.scheduler.step()lr = self.optimizer.param_groups[0]['lr']print('learning rate = %.7f' % lr)

• Train_shrec11.py

import sys
import os
import time
sys.path.append(os.path.join(os.path.dirname(__file__), "../../"))
from DataLoader_shrec11 import DataLoader
from Model import Model
from tensorboardX import SummaryWriter
from DataLoader_shrec11 import Meshif __name__ == '__main__':# 0.设定seed 尽量可复现import numpy as npimport randomimport torchrandom.seed(0)np.random.seed(0)torch.manual_seed(0)torch.cuda.manual_seed(0)torch.cuda.manual_seed_all(0)# 1.数据读取data_train = DataLoader(phase='train')         # 通过参数 获取数据data_test = DataLoader(phase='test')           # 通过参数 获取数据print('#train meshes = %d' % len(data_train))  # 输出训练模型个数print('#test  meshes = %d' % len(data_test))   # 输出测试模型个数# 2.开始训练model = Model()                                      # 创建模型SW = SummaryWriter(log_dir='runs', comment='cls')    # 保存训练曲线for epoch in range(1, 201):print('---------------- Epoch: %d -------------' % epoch)epoch_start_time = time.time()epoch_iter = 0loss = 0for i, data in enumerate(data_train):model.train(data)loss += model.lossprint('Time Taken: %.3f sec, loss_sum: %.6f' % ((time.time() - epoch_start_time), loss))model.update_learning_rate()# 测试新的模型准确率acc = 0for i, data in enumerate(data_test):acc += model.test(data)acc = acc / len(data_test)print('epoch: %d, TEST ACC: %0.2f' % (epoch, acc * 100))# 绘制曲线SW.add_scalar('data/train_loss', loss, epoch)SW.add_scalar('data/test_acc', acc, epoch)