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
+22-9Lines changed: 22 additions & 9 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -30,8 +30,17 @@ A complete documentation is provided [here](https://interdigitalinc.github.io/Co
30
30
31
31
## installation
32
32
33
+
The CompressAI library providing learned compresion modules is available as a submodule. It can be initilized by running:
34
+
```
35
+
git submodule update --init --recursive
36
+
```
37
+
Note: the installation scripts documented below installs compressai from source expects the submodule to be populated.
33
38
34
-
### initialization of the environment
39
+
CompressAI-Vision can be installed using a virtual environment and pip or using uv.
40
+
41
+
### 1. Using a virtual environment:
42
+
43
+
#### Initialization of the environment
35
44
To get started locally and install the development version of CompressAI-Vision, first create a [virtual environment](https://docs.python.org/3.8/library/venv.html) with python==3.8:
36
45
37
46
```
@@ -40,19 +49,13 @@ source ./venv/bin/activate
40
49
pip install -U pip
41
50
```
42
51
43
-
The CompressAI library providing learned compresion modules is available as a submodule. It can be initilized by running:
44
-
```
45
-
git submodule update --init --recursive
46
-
```
47
-
Note: the installation script documented below installs compressai from source expects the submodule to be populated.
48
-
49
-
### installation of compressai-vision and supported vision models:
52
+
#### 2. installation of compressai-vision and supported vision models:
50
53
51
54
First, if you want to manually export CUDA related paths, please source (e.g. for CUDA 11.8):
0 commit comments