HDMapNet

HDMapNet copied to clipboard

Is there any wrong with eval_iou()?

6

Hi, thx for your nice work! When I train the model, I find a problem. In train dataset, IOU can achieve about[0.8 0.6 0.8], while its eval IOU is only...

ppbangKGT

关于测试地图分割结果的问题

1

按我看代码的理解，在运行vis_pred.py时相当于是使用训练得到的model.pt对数据集进行推理以及可视化了吧？但是这里在读取数据集时使用的仍是data/dataset.py里的semantic_dataset函数，在这个python脚本里我注意到有读取nuscenes数据集的map和Lidar的数据。这个是用来做什么的呢？在推理阶段不可以直接输入六张图片得到地图分割的结果吗？ 希望能解答一下

azxcdewq123

Hi, great work! I wonder how to reproduce mAP of HDMapNet. Can you give some codes or commands? The mAP in HDMapNet paper is marked in yellow.  Thanks in...

weimengchuan

trouble installing torch==1.10.2+cu113 torchaudio==0.10.2+cu113 torchvision==0.11.3+cu113

1

I am working with NVIDIA Orion AGX production board and I have jetpack 5 installed on it which has cuda 11.4 installed. Every other libraries installed smoothly except these ones...

Venkat-1405

whether the trained weights has been released?

1

Hi, first thanks for your great job! I wonder whether you will release your trained weights? thanks.

LadissonLai

How to predict new Data set

2

Hello I have a Data set, how to predict my data and detect its lane and how to visualize it? if we want to get visualize all of the sample...

sajedehfzh

result visualization

2

in which folder predicted result save?

AdrawCode27

In vectorize process, what dose the **sort_points_by_dist** function do?

taylover-pei

i'm trying to use my own dataset to train hdmapnet, and my cameras are not horizontal（differ from nusenes)，so i want to know that is the plane generated from z_pitch_yaw better...

rangerToby

Added distributed training logic for HDMapNet and does not affect precision

Bin-ze