WhaSuk Lee

Results 14 issues of WhaSuk Lee

Thank you for such a great work! I'm currently trying to register a projective distorted picture, but I couldn't find the very transformation. May I ask for `projective2D.m` for Parametric...

## How to reproduce Running on `nvcr.io/nvidia/cuda:11.7.1-devel-ubuntu20.04` container ```sh python scripts/demo_inference.py \ --cfg downloaded/multi_domain_model/256x192_res50_lr1e-3_2x-regression.yaml \ --checkpoint downloaded/multi_domain_model/multi_domain_fast50_regression_256x192.pth \ --video downloaded/serve_test_13.mp4 \ --detbatch 1 \ --posebatch 1 \ --save_video \ --pose_track...

[Colab](https://colab.research.google.com/drive/1c7xb_7U61HmeJp55xjXs24hf1GUtHmPs?usp=sharing) is available where you can check out the full process of the project. ```sh ... ! mkdir /content/data file_id = '1D47msNOOiJKvPOXlnpyzdKA3k6E97NTC' downloaded = drive.CreateFile({'id': file_id}) downloaded.GetContentFile('/content/data/yolov3-spp.weights') ! mkdir /content/data...

Tested on `nvcr.io/nvidia/cuda:11.2.0-cudnn8-devel-ubuntu20.04` ![nvidia-smi](https://github.com/Hzzone/pytorch-openpose/assets/40482558/b78e8d87-2563-4823-b090-b236c8458c3b) ```sh $ conda create -n pytorch-openpose-py38 python=3.8 $ conda activate pytorch-openpose-py38 $ conda install -y pytorch">=1.6.0" torchvision cudatoolkit">=9.2" -c pytorch $ pip3 install -r requirements.txt $...

The length of `serve_test_13.mp4` is 4 seconds long, (1920 x 1080). I've noticed the inference speed reaches about 3000, but it takes 4~6 seconds to process the entire video. Does...

## Steps ```sh $ git clone $ cd onnx-tensorrt $ git submodule update --init --recursive $ mkdir build $ cmake .. -DTENSORRT_ROOT=/usr/src/tensorrt/ -DCMAKE_CXX_STANDARD=14 $ make -j$(nproc) ``` ## Error ```...

I went through [Register/localize new images into an existing reconstruction](https://colmap.github.io/faq.html#register-localize-new-images-into-an-existing-reconstruction) Here's a full script: ```sh PROJECT_PATH=/root/Developments/20240414/colmap_proj/1 IMAGES=/root/Developments/20240414/dataset/frames IMAGE_LIST_PATH=/root/Developments/20240414/dataset/image_list.txt # STEP - 1 $ colmap feature_extractor \ --database_path $PROJECT_PATH/database.db \ --image_path...

**Describe the bug** - I am trying to register new images into my existing reconstruction **To Reproduce** Steps to reproduce the behavior: 1. `$ colmap gui` 2. Create new directory...

Has anyone made it to retrieve proper frames using AR0234 in Jetson Nano? I only get greenish frames.

Hello JetsonHacks! I really appreciate your work, and it has been a great help to my project. I'm planning to use a SPI screen with touch functionality. I don't have...