复现PointNet++（语义分割网络）：Windows + PyTorch + S3DIS语义分割 + 代码

一、平台

Windows 10

GPU RTX 3090 + CUDA 11.1 + cudnn 8.9.6

Python 3.9

Torch 1.9.1 + cu111

所用的原始代码：https://github.com/yanx27/Pointnet_Pointnet2_pytorch

二、数据

Stanford3dDataset_v1.2_Aligned_Version

三、代码

分享给有需要的人，代码质量勿喷。

对源代码进行了简化和注释。

分割结果保存成txt，或者利用 laspy 生成点云。

别问为啥在C盘，问就是2T的三星980Pro

3.1 文件组织结构

3.2 数据预处理

3.2.1 run_collect_indoor3d_data.py 生成*.npy文件

改了路径

3.2.2 indoor3d_util.py

改了路径

3.2.3 S3DISDataLoader.py

改了路径

3.3 训练 train_SematicSegmentation.py

# 参考
# https://github.com/yanx27/Pointnet_Pointnet2_pytorch
# 先在Terminal运行：python -m visdom.server
# 再运行本文件import argparse
import os
# import datetime
import logging
import importlib
import shutil
from tqdm import tqdm
import numpy as np
import time
import visdom
import torch
import warnings
warnings.filterwarnings('ignore')from dataset.S3DISDataLoader import S3DISDataset
from PointNet2 import dataProcess# PointNet
from PointNet2.pointnet_sem_seg import get_model as PNss
from PointNet2.pointnet_sem_seg import get_loss as PNloss# PointNet++
from PointNet2.pointnet2_sem_seg import get_model as PN2SS
from PointNet2.pointnet2_sem_seg import get_loss as PN2loss# True为PointNet++
PN2bool = True
# PN2bool = False# 当前文件的路径
ROOT_DIR = os.path.dirname(os.path.abspath(__file__))# 训练输出模型的路径: PointNet
dirModel1 = ROOT_DIR + '/trainModel/pointnet_model'
if not os.path.exists(dirModel1):os.makedirs(dirModel1)
# 训练输出模型的路径
dirModel2 = ROOT_DIR + '/trainModel/PointNet2_model'
if not os.path.exists(dirModel2):os.makedirs(dirModel2)# 日志的路径
pathLog = os.path.join(ROOT_DIR, 'LOG_train.txt')# 数据集的路径
pathDataset = os.path.join(ROOT_DIR, 'dataset/stanford_indoor3d/')# 分类的类别
classNumber = 13
classes = ['ceiling', 'floor', 'wall', 'beam', 'column', 'window', 'door', 'table', 'chair', 'sofa', 'bookcase','board', 'clutter']
class2label = {cls: i for i, cls in enumerate(classes)}
seg_classes = class2label
seg_label_to_cat = {}
for i, cat in enumerate(seg_classes.keys()):seg_label_to_cat[i] = cat# 日志和输出
def log_string(str):logger.info(str)print(str)def inplace_relu(m):classname = m.__class__.__name__if classname.find('ReLU') != -1:m.inplace=Truedef parse_args():parser = argparse.ArgumentParser('Model')parser.add_argument('--pnModel', type=bool, default=True, help='True = PointNet++；False = PointNet')parser.add_argument('--batch_size', type=int, default=32, help='Batch Size during training [default: 32]')parser.add_argument('--epoch', default=320, type=int, help='Epoch to run [default: 32]')parser.add_argument('--learning_rate', default=0.001, type=float, help='Initial learning rate [default: 0.001]')parser.add_argument('--GPU', type=str, default='0', help='GPU to use [default: GPU 0]')parser.add_argument('--optimizer', type=str, default='Adam', help='Adam or SGD [default: Adam]')parser.add_argument('--decay_rate', type=float, default=1e-4, help='weight decay [default: 1e-4]')parser.add_argument('--npoint', type=int, default=4096, help='Point Number [default: 4096]')parser.add_argument('--step_size', type=int, default=10, help='Decay step for lr decay [default: every 10 epochs]')parser.add_argument('--lr_decay', type=float, default=0.7, help='Decay rate for lr decay [default: 0.7]')parser.add_argument('--test_area', type=int, default=5, help='Which area to use for test, option: 1-6 [default: 5]')return parser.parse_args()if __name__ == '__main__':# python -m visdom.servervisdomTL = visdom.Visdom()visdomTLwindow = visdomTL.line([0], [0], opts=dict(title='train_loss'))visdomVL = visdom.Visdom()visdomVLwindow = visdomVL.line([0], [0], opts=dict(title='validate_loss'))visdomTVL = visdom.Visdom(env='PointNet++')# region 创建日志文件logger = logging.getLogger("train")logger.setLevel(logging.INFO)formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')file_handler = logging.FileHandler(pathLog)file_handler.setLevel(logging.INFO)file_handler.setFormatter(formatter)logger.addHandler(file_handler)#endregion#region 超参数args = parse_args()args.pnModel = PN2boollog_string('------------ hyper-parameter ------------')log_string(args)# 指定GPUos.environ["CUDA_VISIBLE_DEVICES"] = args.GPUpointNumber = args.npointbatchSize = args.batch_size#endregion# region dataset# train datatrainData = S3DISDataset(split='train',data_root=pathDataset, num_point=pointNumber,test_area=args.test_area, block_size=1.0, sample_rate=1.0, transform=None)trainDataLoader = torch.utils.data.DataLoader(trainData, batch_size=batchSize, shuffle=True, num_workers=0,pin_memory=True, drop_last=True,worker_init_fn=lambda x: np.random.seed(x + int(time.time())))# Validation datatestData = S3DISDataset(split='test',data_root=pathDataset, num_point=pointNumber,test_area=args.test_area, block_size=1.0, sample_rate=1.0, transform=None)testDataLoader = torch.utils.data.DataLoader(testData, batch_size=batchSize, shuffle=False, num_workers=0,pin_memory=True, drop_last=True)log_string("The number of training data is: %d" % len(trainData))log_string("The number of validation data is: %d" % len(testData))weights = torch.Tensor(trainData.labelweights).cuda()#endregion# region loading model：使用预训练模型或新训练modelSS = ''criterion = ''if PN2bool:modelSS = PN2SS(classNumber).cuda()criterion = PN2loss().cuda()modelSS.apply(inplace_relu)else:modelSS = PNss(classNumber).cuda()criterion = PNloss().cuda()modelSS.apply(inplace_relu)# 权重初始化def weights_init(m):classname = m.__class__.__name__if classname.find('Conv2d') != -1:torch.nn.init.xavier_normal_(m.weight.data)torch.nn.init.constant_(m.bias.data, 0.0)elif classname.find('Linear') != -1:torch.nn.init.xavier_normal_(m.weight.data)torch.nn.init.constant_(m.bias.data, 0.0)try:path_premodel = ''if PN2bool:path_premodel = os.path.join(dirModel2, 'best_model_S3DIS.pth')else:path_premodel = os.path.join(dirModel1, 'best_model_S3DIS.pth')checkpoint = torch.load(path_premodel)start_epoch = checkpoint['epoch']# print('pretrain epoch = '+str(start_epoch))modelSS.load_state_dict(checkpoint['model_state_dict'])log_string('!!!!!!!!!! Use pretrain model')except:log_string('...... starting new training ......')start_epoch = 0modelSS = modelSS.apply(weights_init)#endregion# start_epoch = 0# modelSS = modelSS.apply(weights_init)#region 训练的参数和选项if args.optimizer == 'Adam':optimizer = torch.optim.Adam(modelSS.parameters(),lr=args.learning_rate,betas=(0.9, 0.999),eps=1e-08,weight_decay=args.decay_rate)else:optimizer = torch.optim.SGD(modelSS.parameters(), lr=args.learning_rate, momentum=0.9)def bn_momentum_adjust(m, momentum):if isinstance(m, torch.nn.BatchNorm2d) or isinstance(m, torch.nn.BatchNorm1d):m.momentum = momentumLEARNING_RATE_CLIP = 1e-5MOMENTUM_ORIGINAL = 0.1MOMENTUM_DECCAY = 0.5MOMENTUM_DECCAY_STEP = args.step_sizeglobal_epoch = 0best_iou = 0#endregionfor epoch in range(start_epoch, args.epoch):# region Train on chopped sceneslog_string('****** Epoch %d (%d/%s) ******' % (global_epoch + 1, epoch + 1, args.epoch))lr = max(args.learning_rate * (args.lr_decay ** (epoch // args.step_size)), LEARNING_RATE_CLIP)log_string('Learning rate:%f' % lr)for param_group in optimizer.param_groups:param_group['lr'] = lrmomentum = MOMENTUM_ORIGINAL * (MOMENTUM_DECCAY ** (epoch // MOMENTUM_DECCAY_STEP))if momentum < 0.01:momentum = 0.01log_string('BN momentum updated to: %f' % momentum)modelSS = modelSS.apply(lambda x: bn_momentum_adjust(x, momentum))modelSS = modelSS.train()#endregion# region 训练num_batches = len(trainDataLoader)total_correct = 0total_seen = 0loss_sum = 0for i, (points, target) in tqdm(enumerate(trainDataLoader), total=len(trainDataLoader), smoothing=0.9):# 梯度归零optimizer.zero_grad()# xyzLpoints = points.data.numpy() # ndarray = bs,4096,9(xyz rgb nxnynz)points[:, :, :3] = dataProcess.rotate_point_cloud_z(points[:, :, :3]) ## 数据处理的操作points = torch.Tensor(points) # tensor = bs,4096,9points, target = points.float().cuda(), target.long().cuda()points = points.transpose(2, 1) # tensor = bs,9,4096# 预测结果seg_pred, trans_feat = modelSS(points) # tensor = bs,4096,13  # tensor = bs,512,16seg_pred = seg_pred.contiguous().view(-1, classNumber) # tensor = (bs*4096=)点数量,13# 真实标签batch_label = target.view(-1, 1)[:, 0].cpu().data.numpy() # ndarray = (bs*4096=)点数量target = target.view(-1, 1)[:, 0] # tensor = (bs*4096=)点数量# lossloss = criterion(seg_pred, target, trans_feat, weights)loss.backward()# 优化器来更新模型的参数optimizer.step()pred_choice = seg_pred.cpu().data.max(1)[1].numpy() # ndarray = (bs*4096=)点数量correct = np.sum(pred_choice == batch_label) # 预测正确的点数量total_correct += correcttotal_seen += (batchSize * pointNumber)loss_sum += losslog_string('Training mean loss: %f' % (loss_sum / num_batches))log_string('Training accuracy: %f' % (total_correct / float(total_seen)))# drawtrainLoss = (loss_sum.item()) / num_batchesvisdomTL.line([trainLoss], [epoch+1], win=visdomTLwindow, update='append')#endregion# region 保存模型if epoch % 1 == 0:modelpath=''if PN2bool:modelpath = os.path.join(dirModel2, 'model' + str(epoch + 1) + '_S3DIS.pth')else:modelpath = os.path.join(dirModel1, 'model' + str(epoch + 1) + '_S3DIS.pth')state = {'epoch': epoch,'model_state_dict': modelSS.state_dict(),'optimizer_state_dict': optimizer.state_dict(),}torch.save(state, modelpath)logger.info('Save model...'+modelpath)#endregion# region Evaluate on chopped sceneswith torch.no_grad():num_batches = len(testDataLoader)total_correct = 0total_seen = 0loss_sum = 0labelweights = np.zeros(classNumber)total_seen_class = [0 for _ in range(classNumber)]total_correct_class = [0 for _ in range(classNumber)]total_iou_deno_class = [0 for _ in range(classNumber)]modelSS = modelSS.eval()log_string('****** Epoch Evaluation %d (%d/%s) ******' % (global_epoch + 1, epoch + 1, args.epoch))for i, (points, target) in tqdm(enumerate(testDataLoader), total=len(testDataLoader), smoothing=0.9):points = points.data.numpy() # ndarray = bs,4096,9points = torch.Tensor(points) # tensor = bs,4096,9points, target = points.float().cuda(), target.long().cuda() # tensor = bs,4096,9 # tensor = bs,4096points = points.transpose(2, 1) # tensor = bs,9,4096seg_pred, trans_feat = modelSS(points) # tensor = bs,4096,13 # tensor = bs,512,16pred_val = seg_pred.contiguous().cpu().data.numpy() # ndarray = bs,4096,13seg_pred = seg_pred.contiguous().view(-1, classNumber) # tensor = bs*4096,13batch_label = target.cpu().data.numpy() # ndarray = bs,4096target = target.view(-1, 1)[:, 0] # tensor = bs*4096loss = criterion(seg_pred, target, trans_feat, weights)loss_sum += losspred_val = np.argmax(pred_val, 2) # ndarray = bs,4096correct = np.sum((pred_val == batch_label))total_correct += correcttotal_seen += (batchSize * pointNumber)tmp, _ = np.histogram(batch_label, range(classNumber + 1))labelweights += tmpfor l in range(classNumber):total_seen_class[l] += np.sum((batch_label == l))total_correct_class[l] += np.sum((pred_val == l) & (batch_label == l))total_iou_deno_class[l] += np.sum(((pred_val == l) | (batch_label == l)))labelweights = labelweights.astype(np.float32) / np.sum(labelweights.astype(np.float32))mIoU = np.mean(np.array(total_correct_class) / (np.array(total_iou_deno_class, dtype=np.float64) + 1e-6))log_string('eval mean loss: %f' % (loss_sum / float(num_batches)))log_string('eval point avg class IoU: %f' % (mIoU))log_string('eval point accuracy: %f' % (total_correct / float(total_seen)))log_string('eval point avg class acc: %f' % (np.mean(np.array(total_correct_class) / (np.array(total_seen_class, dtype=np.float64) + 1e-6))))iou_per_class_str = '------- IoU --------\n'for l in range(classNumber):iou_per_class_str += 'class %s weight: %.3f, IoU: %.3f \n' % (seg_label_to_cat[l] + ' ' * (14 - len(seg_label_to_cat[l])), labelweights[l - 1],total_correct_class[l] / float(total_iou_deno_class[l]))log_string(iou_per_class_str)log_string('Eval mean loss: %f' % (loss_sum / num_batches))log_string('Eval accuracy: %f' % (total_correct / float(total_seen)))# drawvalLoss = (loss_sum.item()) / num_batchesvisdomVL.line([valLoss], [epoch+1], win=visdomVLwindow, update='append')# region 根据 mIoU确定最佳模型if mIoU >= best_iou:best_iou = mIoUbestmodelpath = ''if PN2bool:bestmodelpath = os.path.join(dirModel2, 'best_model_S3DIS.pth')else:bestmodelpath = os.path.join(dirModel1, 'best_model_S3DIS.pth')state = {'epoch': epoch,'class_avg_iou': mIoU,'model_state_dict': modelSS.state_dict(),'optimizer_state_dict': optimizer.state_dict(),}torch.save(state, bestmodelpath)logger.info('Save best model......'+bestmodelpath)log_string('Best mIoU: %f' % best_iou)#endregion#endregionglobal_epoch += 1# drawvisdomTVL.line(X=[epoch+1], Y=[trainLoss],name="train loss", win='line', update='append',opts=dict(showlegend=True, markers=False,title='PointNet++ train validate loss',xlabel='epoch', ylabel='loss'))visdomTVL.line(X=[epoch+1], Y=[valLoss], name="train loss", win='line', update='append')log_string('-------------------------------------------------\n\n')

3.4 预测测试 test_SematicSegmentation.py

# 参考
# https://github.com/yanx27/Pointnet_Pointnet2_pytorchimport argparse
import sys
import os
import numpy as np
import logging
from pathlib import Path
import importlib
from tqdm import tqdm
import torch
import warnings
warnings.filterwarnings('ignore')from dataset.S3DISDataLoader import ScannetDatasetWholeScene
from dataset.indoor3d_util import g_label2color# PointNet
from PointNet2.pointnet_sem_seg import get_model as PNss
# PointNet++
from PointNet2.pointnet2_sem_seg import get_model as PN2SSPN2bool = True
# PN2bool = False# region 函数：投票；日志输出；保存结果为las。
# 投票决定结果
def add_vote(vote_label_pool, point_idx, pred_label, weight):B = pred_label.shape[0]N = pred_label.shape[1]for b in range(B):for n in range(N):if weight[b, n] != 0 and not np.isinf(weight[b, n]):vote_label_pool[int(point_idx[b, n]), int(pred_label[b, n])] += 1return vote_label_pool# 日志
def log_string(str):logger.info(str)print(str)# save to LAS
import laspy
def SaveResultLAS(newLasPath, point_np, rgb_np, label1, label2):# datanewx = point_np[:, 0]newy = point_np[:, 1]newz = point_np[:, 2]newred = rgb_np[:, 0]newgreen = rgb_np[:, 1]newblue = rgb_np[:, 2]newclassification = label1newuserdata = label2minx = min(newx)miny = min(newy)minz = min(newz)# create a new headernewheader = laspy.LasHeader(point_format=3, version="1.2")newheader.scales = np.array([0.0001, 0.0001, 0.0001])newheader.offsets = np.array([minx, miny, minz])newheader.add_extra_dim(laspy.ExtraBytesParams(name="Classification", type=np.uint8))newheader.add_extra_dim(laspy.ExtraBytesParams(name="UserData", type=np.uint8))# create a Lasnewlas = laspy.LasData(newheader)newlas.x = newxnewlas.y = newynewlas.z = newznewlas.red = newrednewlas.green = newgreennewlas.blue = newbluenewlas.Classification = newclassificationnewlas.UserData = newuserdata# writenewlas.write(newLasPath)# 超参数
def parse_args():parser = argparse.ArgumentParser('Model')parser.add_argument('--pnModel', type=bool, default=True, help='True = PointNet++；False = PointNet')parser.add_argument('--batch_size', type=int, default=32, help='batch size in testing [default: 32]')parser.add_argument('--GPU', type=str, default='0', help='specify GPU device')parser.add_argument('--num_point', type=int, default=4096, help='point number [default: 4096]')parser.add_argument('--test_area', type=int, default=5, help='area for testing, option: 1-6 [default: 5]')parser.add_argument('--num_votes', type=int, default=1,help='aggregate segmentation scores with voting [default: 1]')return parser.parse_args()#endregion# 当前文件的路径
ROOT_DIR = os.path.dirname(os.path.abspath(__file__))# 模型的路径
pathTrainModel = os.path.join(ROOT_DIR, 'trainModel/pointnet_model')
if PN2bool:pathTrainModel = os.path.join(ROOT_DIR, 'trainModel/PointNet2_model')# 结果路径
visual_dir = ROOT_DIR + '/testResultPN/'
if PN2bool:visual_dir = ROOT_DIR + '/testResultPN2/'
visual_dir = Path(visual_dir)
visual_dir.mkdir(exist_ok=True)# 日志的路径
pathLog = os.path.join(ROOT_DIR, 'LOG_test_eval.txt')# 数据集的路径
pathDataset = os.path.join(ROOT_DIR, 'dataset/stanford_indoor3d/')# 分割类别排序
classNumber = 13
classes = ['ceiling', 'floor', 'wall', 'beam', 'column', 'window', 'door', 'table', 'chair', 'sofa', 'bookcase','board', 'clutter']
class2label = {cls: i for i, cls in enumerate(classes)}
seg_classes = class2label
seg_label_to_cat = {}
for i, cat in enumerate(seg_classes.keys()):seg_label_to_cat[i] = catif __name__ == '__main__':#region LOG infologger = logging.getLogger("test_eval")logger.setLevel(logging.INFO) #日志级别：DEBUG, INFO, WARNING, ERROR, 和 CRITICALfile_handler = logging.FileHandler(pathLog)file_handler.setLevel(logging.INFO)formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')file_handler.setFormatter(formatter)logger.addHandler(file_handler)#endregion#region 超参数args = parse_args()args.pnModel = PN2boollog_string('--- hyper-parameter ---')log_string(args)os.environ["CUDA_VISIBLE_DEVICES"] = args.GPUbatchSize = args.batch_sizepointNumber = args.num_pointtestArea = args.test_areavoteNumber = args.num_votes#endregion#region ---------- 加载语义分割的模型 ----------log_string("---------- Loading sematic segmentation model ----------")ssModel = ''if PN2bool:ssModel = PN2SS(classNumber).cuda()else:ssModel = PNss(classNumber).cuda()path_model = os.path.join(pathTrainModel, 'best_model_S3DIS.pth')checkpoint = torch.load(path_model)ssModel.load_state_dict(checkpoint['model_state_dict'])ssModel = ssModel.eval()#endregion# 模型推断（inference）或评估（evaluation）阶段，不需要计算梯度，而且关闭梯度计算可以显著减少内存占用，加速计算。log_string('--- Evaluation whole scene')with torch.no_grad():# IOU 结果total_seen_class = [0 for _ in range(classNumber)]total_correct_class = [0 for _ in range(classNumber)]total_iou_deno_class = [0 for _ in range(classNumber)]# 测试区域的所有文件testDataset = ScannetDatasetWholeScene(pathDataset, split='test', test_area=testArea, block_points=pointNumber)scene_id_name = testDataset.file_listscene_id_name = [x[:-4] for x in scene_id_name] # 名称（无扩展名）testCount = len(scene_id_name)testCount = 1# 遍历需要预测的物体for batch_idx in range(testCount):log_string("Inference [%d/%d] %s ..." % (batch_idx + 1, testCount, scene_id_name[batch_idx]))# 数据whole_scene_data = testDataset.scene_points_list[batch_idx]# 真值whole_scene_label = testDataset.semantic_labels_list[batch_idx]whole_scene_labelR = np.reshape(whole_scene_label, (whole_scene_label.size, 1))# 预测标签vote_label_pool = np.zeros((whole_scene_label.shape[0], classNumber))# 同一物体多次预测for _ in tqdm(range(voteNumber), total=voteNumber):scene_data, scene_label, scene_smpw, scene_point_index = testDataset[batch_idx]num_blocks = scene_data.shape[0]s_batch_num = (num_blocks + batchSize - 1) // batchSizebatch_data = np.zeros((batchSize, pointNumber, 9))batch_label = np.zeros((batchSize, pointNumber))batch_point_index = np.zeros((batchSize, pointNumber))batch_smpw = np.zeros((batchSize, pointNumber))for sbatch in range(s_batch_num):start_idx = sbatch * batchSizeend_idx = min((sbatch + 1) * batchSize, num_blocks)real_batch_size = end_idx - start_idxbatch_data[0:real_batch_size, ...] = scene_data[start_idx:end_idx, ...]batch_label[0:real_batch_size, ...] = scene_label[start_idx:end_idx, ...]batch_point_index[0:real_batch_size, ...] = scene_point_index[start_idx:end_idx, ...]batch_smpw[0:real_batch_size, ...] = scene_smpw[start_idx:end_idx, ...]batch_data[:, :, 3:6] /= 1.0torch_data = torch.Tensor(batch_data)torch_data = torch_data.float().cuda()torch_data = torch_data.transpose(2, 1)seg_pred, _ = ssModel(torch_data)batch_pred_label = seg_pred.contiguous().cpu().data.max(2)[1].numpy()# 投票产生预测标签vote_label_pool = add_vote(vote_label_pool, batch_point_index[0:real_batch_size, ...],batch_pred_label[0:real_batch_size, ...],batch_smpw[0:real_batch_size, ...])# region  保存预测的结果# 预测标签pred_label = np.argmax(vote_label_pool, 1)pred_labelR = np.reshape(pred_label, (pred_label.size, 1))# 点云-真值-预测标签pcrgb_ll = np.hstack((whole_scene_data, whole_scene_labelR, pred_labelR))# ---------- 保存成 txt ----------pathTXT = os.path.join(visual_dir, scene_id_name[batch_idx] + '.txt')np.savetxt(pathTXT, pcrgb_ll, fmt='%f', delimiter='\t')log_string('save:' + pathTXT)# ---------- 保存成 las ----------pathLAS = os.path.join(visual_dir, scene_id_name[batch_idx] + '.las')SaveResultLAS(pathLAS, pcrgb_ll[:,0:3], pcrgb_ll[:,3:6], pcrgb_ll[:,6], pcrgb_ll[:,7])log_string('save:' + pathLAS)# endregion# IOU 临时结果total_seen_class_tmp = [0 for _ in range(classNumber)]total_correct_class_tmp = [0 for _ in range(classNumber)]total_iou_deno_class_tmp = [0 for _ in range(classNumber)]for l in range(classNumber):total_seen_class_tmp[l] += np.sum((whole_scene_label == l))total_correct_class_tmp[l] += np.sum((pred_label == l) & (whole_scene_label == l))total_iou_deno_class_tmp[l] += np.sum(((pred_label == l) | (whole_scene_label == l)))total_seen_class[l] += total_seen_class_tmp[l]total_correct_class[l] += total_correct_class_tmp[l]total_iou_deno_class[l] += total_iou_deno_class_tmp[l]iou_map = np.array(total_correct_class_tmp) / (np.array(total_iou_deno_class_tmp, dtype=np.float64) + 1e-6)print(iou_map)arr = np.array(total_seen_class_tmp)tmp_iou = np.mean(iou_map[arr != 0])log_string('Mean IoU of %s: %.4f' % (scene_id_name[batch_idx], tmp_iou))IoU = np.array(total_correct_class) / (np.array(total_iou_deno_class, dtype=np.float64) + 1e-6)iou_per_class_str = '----- IoU -----\n'for l in range(classNumber):iou_per_class_str += 'class %s, IoU: %.3f \n' % (seg_label_to_cat[l] + ' ' * (14 - len(seg_label_to_cat[l])),total_correct_class[l] / float(total_iou_deno_class[l]))log_string(iou_per_class_str)log_string('eval point avg class IoU: %f' % np.mean(IoU))log_string('eval whole scene point avg class acc: %f' % (np.mean(np.array(total_correct_class) / (np.array(total_seen_class, dtype=np.float64) + 1e-6))))log_string('eval whole scene point accuracy: %f' % (np.sum(total_correct_class) / float(np.sum(total_seen_class) + 1e-6)))log_string('--------------------------------------\n\n')