Update README.md
Browse files
README.md
CHANGED
|
@@ -13,6 +13,15 @@ StreamFormer backbone model pre-trained on *Global*-, *Temporal*- and *Spatial*-
|
|
| 13 |
|
| 14 |
StreamFormer is a streaming video representation backbone that encodes a stream of video input. It is designed for multiple downstream applications like Online Action Detection, Online Video Instance Segmentation and Video Question Answering.
|
| 15 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
### How to use
|
| 17 |
|
| 18 |
How to get the multi-granularity feature:
|
|
|
|
| 13 |
|
| 14 |
StreamFormer is a streaming video representation backbone that encodes a stream of video input. It is designed for multiple downstream applications like Online Action Detection, Online Video Instance Segmentation and Video Question Answering.
|
| 15 |
|
| 16 |
+
### Installation
|
| 17 |
+
|
| 18 |
+
```bash
|
| 19 |
+
conda create -n streamformer python=3.10
|
| 20 |
+
conda activate streamformer
|
| 21 |
+
conda install pytorch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1 pytorch-cuda=12.4 -c pytorch -c nvidia
|
| 22 |
+
pip install -r requirements.txt
|
| 23 |
+
```
|
| 24 |
+
|
| 25 |
### How to use
|
| 26 |
|
| 27 |
How to get the multi-granularity feature:
|