@@ -62,16 +62,17 @@ The pose estimation work is based on the C++ code from [the ECCV 2016 demo](http
## Contents
1.[Installation, Reinstallation and Uninstallation](#installation-reinstallation-and-uninstallation)
2.[Quick Start](#quick-start)
2.[Custom Caffe](#custom-caffe)
3.[Quick Start](#quick-start)
1.[Demo](#demo)
2.[OpenPose Wrapper](#openpose-wrapper)
3.[OpenPose Library](#openpose-library)
3.[Output](#output)
4.[Output](#output)
1.[Output Format](#output-format)
2.[Reading Saved Results](#reading-saved-results)
4.[OpenPose Benchmark](#openpose-benchmark)
5.[Send Us Your Feedback!](#send-us-your-feedback)
6.[Citation](#citation)
5.[OpenPose Benchmark](#openpose-benchmark)
6.[Send Us Your Feedback!](#send-us-your-feedback)
7.[Citation](#citation)
...
...
@@ -80,6 +81,19 @@ You can find the installation, reinstallation and uninstallation steps on: [doc/
## Custom Caffe
We only modified some Caffe compilation flags and minor details. You can use use your own Caffe distribution, these are the files we added and modified:
1. Added files: `install_caffe.sh`; as well as `Makefile.config.Ubuntu14.example`, `Makefile.config.Ubuntu16.example`, `Makefile.config.Ubuntu14_cuda_7.example` and `Makefile.config.Ubuntu16_cuda_7.example` (extracted from `Makefile.config.example`). Basically, you must enable cuDNN.
2. Edited file: Makefile. Search for "# OpenPose: " to find the edited code. We basically added the C++11 flag to avoid issues in some old computers.
1. Run `make all && make distribute` in your Caffe version.
2. Open the OpenPose Makefile config file: `./Makefile.config.UbuntuX.example` (where X depends on your OS and CUDA version).
3. Modify the Caffe folder directory variable (`CAFFE_DIR`) to your custom Caffe `distribute` folder location in the previous OpenPose Makefile config file.
## Quick Start
Most users cases should not need to dive deep into the library, they might just be able to use the [Demo](#demo) or the simple [OpenPose Wrapper](#openpose-wrapper). So you can most probably skip the library details in [OpenPose Library](#openpose-library).
...
...
@@ -168,16 +182,6 @@ We use standard formats (JSON, XML, PNG, JPG, ...) to save our results, so there
## Custom Caffe
We only modified some Caffe compilation flags and minor details. You can use use your own Caffe distribution, these are the files we added and modified:
1. Added files: `install_caffe.sh`; as well as `Makefile.config.Ubuntu14.example`, `Makefile.config.Ubuntu16.example`, `Makefile.config.Ubuntu14_cuda_7.example` and `Makefile.config.Ubuntu16_cuda_7.example` (extracted from `Makefile.config.example`). Basically, you must enable cuDNN.
2. Edited file: Makefile. Search for "# OpenPose: " to find the edited code. We basically added the C++11 flag to avoid issues in some old computers.
4. Finally, run `make all && make distribute` in your Caffe version and modify the Caffe directory variable in our Makefile config file: `./Makefile.config.UbuntuX.example` (where X is 14 or 16 depending on your Ubuntu version), set the `CAFFE_DIR` parameter to the path where both the `include` and `lib` Caffe folders are located.
## OpenPose Benchmark
Initial library running time benchmark on [OpenPose Benchmark](https://docs.google.com/spreadsheets/d/1-DynFGvoScvfWDA1P4jDInCkbD4lg0IKOYbXgEq0sK0/edit#gid=0). You can comment in that document with your graphics card model and running time for that model, and we will add your results to the benchmark!