Li Jiaxin

According to Tensorflow's official SSIM code `https://www.tensorflow.org/api_docs/python/tf/image/ssim`, there isn't the average pooling when image size > 256. So I wonder whether the SSIM proposed here `https://github.com/photosynthesis-team/piq` should be adopted especially...

Do you mean that the `pytorch-ssim` is identitcal with TF official SSIM, and both of them are lack of the downsample implementation?

@precyon 1. The calibration process involves only the anchors. The anchors are fixed and we estimate their positions according to the relative distance between any pair of anchors. 2. The...

@goldenminerlmg In our implementation, calibration (involved uncalibrated anchors) and localization (between calibrated anchors and the UAVs) are separate. That is: 1. Fix the position of anchors. 2. Perform calibration of...

Currently the only documentation is the paper: Accurate 3D Localization for MAV Swarms by UWB and IMU Fusion. Probably later one of my colleague will include this work into his...

We have VICON ground truth, which is available in our dataset. Tran Quang Minh 于2021年2月2日周二 下午4:58写道： > Hi, > I see that you reported in the paper that the errors...

Don't be so apologetic. I should have made the shrec16/test.py better. I have updated the codes just now, at least it works on my desktop without any problem now.

It is simple a way to get a integer id for each category.

Please make sure that the cuda environment is configured properly. For example, proper environment variables. For example, you may consider adding these lines to `~/.bashrc` ``` # cuda-10.1 export CUDA_HOME=/usr/local/cuda-10.1...

For the speed. An alternative implementation is to run for loop in pytorch, to get a max-pooling for each node. In the case that node number is small, e.g.,