Deephome

the [overview](https://github.com/Autoware-AI/autoware.ai/wiki/Overview) introduce the fusion_detector module (with MV3D), but I cannot find the source code.

Can't run eval.py using provided model & Training using default settings get bad results

3

T have some problems, can you give me some advice, thanks! 1)run eval.py ,get errors as follows: /home/yang/Software/anaconda3/lib/python3.5/site-packages/torch/serialization.py:316: SourceChangeWarning: source code of class 'torch.nn.parallel.data_parallel.DataParallel' has changed. you can retrieve the...

Sample data on BaiduPan is unavailable

1

Thank you for your great work! Sample data on BaiduPan is unavailable now, I'll appreciate it if you would like to update the link, so I can download the sample...

PoseLocalParameterization中四元数更新代码错误？

4

在pose_local_parameterization.cpp的deltaQ函数中： `Eigen::Quaterniond deltaQ(const Eigen::Vector3d &theta) { Eigen::Quaterniond dq; Eigen::Vector3d half_theta = theta; // theta： so(3) 旋转向量 half_theta /= static_cast(2.0); // half_theta: 四元数向量部分 dq.w() = static_cast(1.0); dq.x() = half_theta.x(); dq.y() =...

Can‘t compiled on Win10_64？

14

platform: win10 64, python 3.6, pytorch 1.0.0 I met the following error, can you give me some advice? D:\YX\python\pytorch_projects\C_Extension\DCNv2-master_1.0\DCNv2-master>python setup.py install running install running bdist_egg running egg_info creating DCNv2.egg-info writing...

Error when replacing torchpack.distributed with torch.distributed.launch

6

Hi, I tried to use torch.distributed.launch instead of torchpack.distributed for multi-gpu test. I modified the tools/test.py (according to mmdetection3d) and create a dist_test.sh as follows: ``` CONFIG=$1 CHECKPOINT=$2 GPUS=$3 PORT=${PORT:-29500}...

Make Large Models Great Again!

1

good good study, day day up!

Questions about location tokens

4

Hi, your work is great! But I am confused about the location tokens you used in Decoder, could you provide more details it?

 As shown in above image, the depth map generated by nerf suffers from artifacts /erros in sky area. How to solve this problem?

Large performance gap between pytorch model and onnx model

15

Thank for your excellent work! I just exported the pytorch model to onnx model without nms, and used deploy/onnx_demo.py for detecting facial features in images. However I found that the...