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
+2-14Lines changed: 2 additions & 14 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -20,13 +20,9 @@ The GUI has been modernized and is now built with **PySide6 (Qt)** (replacing tk
20
20
21
21
The new interface supports **multi-camera preview** with a **tiled display**, PyTorch models, and features improved interactive workflows for experimental use.
22
22
23
-
---
24
-
25
23
## Documentation
26
24
27
-
> Full documentation is a work in progress and will be posted to DeepLabCut's official docs site when ready.
28
-
29
-
---
25
+
> Find the full documentation at the [DeepLabCut docs website](https://deeplabcut.github.io/DeepLabCut/docs/dlc-live/dlc-live-gui/index.html)
30
26
31
27
## System requirements (quick summary)
32
28
@@ -36,8 +32,6 @@ The new interface supports **multi-camera preview** with a **tiled display**, Py
36
32
-**TensorFlow***(for backwards compatibility with existing models; Windows installs are no longer available for Python > 3.10)*
37
33
- A supported camera backend (OpenCV webcams by default; additional backends supported)
38
34
39
-
---
40
-
41
35
## Installation
42
36
43
37
While the previous `deeplabcut-live-gui` is available on PyPI, the newest PySide6-based GUI and features **must be obtained by installing from source**.
@@ -109,8 +103,6 @@ pip install -e .[pytorch]
109
103
pip install -e .[tf]
110
104
```
111
105
112
-
---
113
-
114
106
## Run the application
115
107
116
108
> [!TIP]
@@ -128,8 +120,6 @@ uv run dlclivegui
128
120
> [!IMPORTANT]
129
121
> Activate your venv/conda environment before launching so the GUI can access installed dependencies.
130
122
131
-
---
132
-
133
123
## Typical workflow
134
124
135
125
The new GUI supports **one or more cameras**.
@@ -152,8 +142,6 @@ Typical workflow:
152
142
> For additional camera ecosystems (Basler, GenTL, Aravis, etc.), see the relevant documentation.
153
143
<!-- TODO @C-Achard add link to docs website once available -->
154
144
155
-
---
156
-
157
145
## Current limitations
158
146
159
147
- Pose inference runs on **one selected camera at a time** (even in multi-camera mode)
@@ -177,4 +165,4 @@ If you use this code, we kindly ask you to please cite:
177
165
178
166
This project is under active development — feedback from real experimental use is highly valued.
179
167
180
-
Please report issues, suggest features, or contribute on [GitHub](https://github.com/DeepLabCut/DeepLabCut-live-GUI).
168
+
Please report issues, suggest features, or contribute here on [GitHub](https://github.com/DeepLabCut/DeepLabCut-live-GUI/issues).
0 commit comments