Salvador BLANCO

I am wondering the same! Did you solve it @makeitraina ?

I also want to use my own data set, I wonder if there is a tool to create a COCO like dataset/annotations? @Gzzgz @oujieww @Ai-is-light were you able to find...

@SimonPrPr @FengyangZhang Could you explain how you solved the folders: ``` directory = 'COCO_exp_caffe/pose56/exp22/' # directory = 'COCO_exp_caffe/pose56/exp22/' serverFolder = 'COCO_kpt/pose56/exp22' # serverFolder = '/home/zhecao/COCO_kpt/pose56/exp22' base_folder = 'arch/'+directory+'model' # base_folder...

@yw155 Thank you for the response, indeed in the "train_pose.sh" there is a path to the `VGG_ILSVRC_19_layers.caffemodel` file: `/home/gtk/m_HDD/caffe_train/build/tools/caffe train --solver=pose_solver.prototxt --gpu=$1 --weights=../../../model/vgg/VGG_ILSVRC_19_layers.caffemodel 2>&1 | tee ./output.txt` But in the...

https://patrickwasp.com/create-your-own-coco-style-dataset/

I updated to hyperpose-2.1.0 When I anazyze the `sh scripts/download-test-data.sh` data with: `/hyperpose-cli --source ../data/media --model ../data/models/lopps-resnet50-V2-HW=368x432.onnx --w 368 --h 432` I get: Terminal Log: ``` ./hyperpose-cli --source ../data/media --model...

When I analyze the sh scripts/download-test-data.sh data with: `./hyperpose-cli --source ../data/media --model ../data/models/openpose-thin-V2-HW=368x432.onnx --w 432 --h 368 --max_batch_size 1` The model is able to analyze only two images: [IMG 1](https://ibb.co/cbjrR0T)...

@stubbb The issue happens with all the models. Am I the only one having this issue ? Could you check if you can replicate the results ?

@stubbb GeForce RTX 2080 Ti Ubuntu 20.04.1 LTS TensorRT 7.0.0-1 + cuda10.2 @ganler I will try the gdb command Thank you

@ganler ``` gdb --args ./hyperpose-cli --source ../data/media --model ../data/models/openpose-thin-V2-HW=368x432.onnx --w 432 --h 368 --max_batch_size 1 GNU gdb (Ubuntu 9.1-0ubuntu1) 9.1 Copyright (C) 2020 Free Software Foundation, Inc. License GPLv3+: GNU...