You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+3Lines changed: 3 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -104,13 +104,15 @@ Your case if you just want to process a folder of images or video or webcam and
104
104
105
105
Forget about the OpenPose library details and just read the [doc/demo_overview.md](doc/demo_overview.md) 1-page section.
106
106
107
+
107
108
#### OpenPose Wrapper
108
109
Your case if you want to read a specific format of image source and/or add a specific post-processing function and/or implement your own display/saving.
109
110
110
111
(Almost) forget about the library, just take a look to the `Wrapper` tutorial on [examples/tutorial_wrapper/](examples/tutorial_wrapper/).
111
112
112
113
Note: you should not need to modify the OpenPose source code nor examples. In this way, you are able to directly upgrade OpenPose anytime in the future without changing your code. You might create your custom code on [examples/user_code/](examples/user_code/) and compile it by using `make all` in the OpenPose folder.
113
114
115
+
114
116
#### OpenPose Library
115
117
Your case if you want to change internal functions and/or extend its functionality. First, take a look at the [Demo](#demo) and [OpenPose Wrapper](#openpose-wrapper). Second, read the 2 following subsections: OpenPose Overview and Extending Functionality.
116
118
@@ -120,6 +122,7 @@ Your case if you want to change internal functions and/or extend its functionali
120
122
121
123
3. Adding An Extra Module: Learn how to add an extra module in [doc/library_add_new_module.md](doc/library_add_new_module.md).
122
124
125
+
123
126
#### Doxygen Documentation Autogeneration
124
127
You can generate the documentation by running the following command. The documentation will be generated in `doc/doxygen/html/index.html`. You can simply open it with double-click (your default browser should automatically display it).
@@ -104,7 +102,7 @@ You just need to remove the OpenPose folder, by default called `openpose/`. E.g.
104
102
105
103
### Installation - Library
106
104
1. Install the pre-requisites:
107
-
1. Microsoft Visual Studio (VS) 2015 Enterprise Update 3. VS Enterprise Update 1 will give some compiler errors, while VS 2015 Community has not been tested.
105
+
1. Microsoft Visual Studio (VS) 2015 Enterprise Update 3. VS Enterprise Update 1 and VS 2017 will give some compiler errors, while VS 2015 Community has not been tested.
108
106
2. [CUDA 8](https://developer.nvidia.com/cuda-downloads): Install it on the default location, `C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v8.0`. Otherwise, modify the Visual Studio project solution accordingly. Install CUDA 8.0 after Visual Studio 2015 is installed to assure that the CUDA installation will generate all necessary files for VS. If CUDA was already installed, re-install it after installing VS!
109
107
3. [cuDNN 5.1](https://developer.nvidia.com/cudnn): Once you have downloaded it, just unzip it and copy (merge) the contents on the CUDA folder, `C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v8.0`.
110
108
2. Download the OpenPose dependencies and models (body, face and hand models) by double-clicking on `{openpose_path}\windows\download_3rdparty_and_models.bat`. Alternatively, you might prefer to download them manually:
@@ -129,7 +127,7 @@ You just need to remove the OpenPose folder, by default called `openpose/`. E.g.
129
127
3. Open the Windows cmd (Windows button + X, then A).
130
128
4. Go to the OpenPose directory, assuming OpenPose has been downloaded on `C:\openpose`: `cd C:\openpose\`.
131
129
5. Run the tutorial commands.
132
-
7. Check [Quick Start](#quick-start) to test video, webcam and a folder with images, in order to verify OpenPose was properly installed.
130
+
7. Check OpenPose was properly installed by running it on the default images, video or webcam: [doc/quick_start.md#quick-start](./quick_start.md#quick-start).
133
131
134
132
135
133
@@ -158,114 +156,6 @@ If you want to try our OpenPose 3-D reconstruction demo, see [doc/openpose_3d_re
158
156
159
157
160
158
161
-
## Quick Start
162
-
Check that the library is working properly by using any of the following commands. Note that `examples/media/video.avi` and `examples/media` exist, so you do not need to change the paths. In addition, the following commands assume your terminal (Ubuntu) or cmd (Windows) are located in the OpenPose folder.
This command provides the most accurate results we have been able to achieve for body, hand and face keypoint detection. However, this command will need around 8 GB of GPU memory and runs around 1 FPS on a Titan X.
The visual GUI should show the original image with the poses blended on it, similarly to the pose of this gif:
252
-
<p align="center">
253
-
<img src="media/shake.gif", width="720">
254
-
</p>
255
-
256
-
If you choose to visualize a body part or a PAF (Part Affinity Field) heat map with the command option `--part_to_show`, the result should be similar to one of the following images:
257
-
<p align="center">
258
-
<img src="media/body_heat_maps.png", width="720">
259
-
</p>
260
-
261
-
<p align="center">
262
-
<img src="media/paf_heat_maps.png", width="720">
263
-
</p>
264
-
265
-
266
-
267
-
268
-
269
159
## FAQ
270
160
**Q: Out of memory error** - I get an error similar to: `Check failed: error == cudaSuccess (2 vs. 0) out of memory`.
Copy file name to clipboardExpand all lines: doc/openpose_3d_reconstruction_demo.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -48,7 +48,7 @@ The program uses 3 cameras by default, but cameras can be added or removed from
48
48
49
49
50
50
### Windows
51
-
1.[Install the OpenPose library](installation.md#installation---library) and make sure the [OpenPose demo runs](installation.md#quick-start), so that the required OpenPose library was properly compiled.
51
+
1.[Install the OpenPose library](installation.md#installation---library) and make sure the [OpenPose demo runs](quick_start.md#quick-start), so that the required OpenPose library was properly compiled.
52
52
2. Open the OpenPose visual studio solution `windows\openpose.sln`.
53
53
3. Right-click on `Solution 'OpenPose'` of the `Solution Explorer` window, usually placed at the top-right part of the VS screen.
54
54
4. Click on `Properties`. Go to `Configuration Properties` -> `Configuration` and check `Build` for the `OpenPose3DReconstruction` project.
Check that the library is working properly by running any of the following commands. Make sure that you are in the **root directory of the project** (i.e. in the OpenPose folder, not inside `build/` nor `windows/` nor `bin/`). In addition, `examples/media/video.avi` and `examples/media` do exist, no need to change the paths.
This command provides the most accurate results we have been able to achieve for body, hand and face keypoint detection. However, this command will need around 8 GB of GPU memory and runs around 1 FPS on a Titan X.
The visual GUI should show the original image with the poses blended on it, similarly to the pose of this gif:
102
+
<palign="center">
103
+
<img src="media/shake.gif", width="720">
104
+
</p>
105
+
106
+
If you choose to visualize a body part or a PAF (Part Affinity Field) heat map with the command option `--part_to_show`, the result should be similar to one of the following images:
0 commit comments