Dávid Komorowicz

I used my own colmap reconstruction available here: https://drive.google.com/file/d/1dgfQIomKb2AAV5asaWhRcgtyl--ABsgW/view?usp=sharing

I did, here it is [epoch=19.ckpt.zip](https://github.com/kwea123/nerf_pl/files/6376490/epoch.19.ckpt.zip) 

There is an unofficial **opendr** (https://github.com/polmorenoc/opendr) port for Python 3 and I'm working on porting the mesh lib... It's definitely more work but sooner or later it has to be...

Upon further inspection I came to the conclusion that the `BETA_PLUS_PLUS` vehicles have a 64-beam lidar, but no front lidars. This was not clearly articulated. I think, out of these...

> Another question about parameter of num_nodes,I have no idea that what it does.I have never used pytorch_lightning. In distributed training the number of nodes correspond to the number of...

The val_check_interval error means that your epoch (9636) is smaller than when you would like to run the validation (10000). To fix this, change the `VAL_FREQ: 10000.0` in the config...

I've been trying to compile this but I get the following error: ``` -- Caffe2: CUDA detected: 11.2 -- Caffe2: CUDA nvcc is: /usr/local/cuda/bin/nvcc -- Caffe2: CUDA toolkit directory: /usr/local/cuda...

I'll try it out on Ubuntu and let you know. One problem for me was that cmake found the mkl.cmake from cgal which was installed on my machine, maybe we...

Now it compiles and runs fine, no additional cmake config needed for mkl. However the model file seems to be corrupted. I get the following error at: `torch::jit::load(options_.mvs_module_path, kDevIn);` ```...

With PyTorch 1.7.1 I can read the model file properly. I think the problem is that libtorch tries to open the file as a text file, not binary, that was...