Update README.md
Browse files
README.md
CHANGED
|
@@ -28,6 +28,14 @@ It is _**the largest open-source vision/vision-language foundation model (14B)**
|
|
| 28 |
- Image size: 224 x 224
|
| 29 |
- **Pretrain Dataset:** LAION-en, LAION-COCO, COYO, CC12M, CC3M, SBU, Wukong, LAION-multi
|
| 30 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
## Model Usage (Image Embeddings)
|
| 32 |
|
| 33 |
```python
|
|
|
|
| 28 |
- Image size: 224 x 224
|
| 29 |
- **Pretrain Dataset:** LAION-en, LAION-COCO, COYO, CC12M, CC3M, SBU, Wukong, LAION-multi
|
| 30 |
|
| 31 |
+
## Linear Probing Performance
|
| 32 |
+
|
| 33 |
+
See this [document](https://github.com/OpenGVLab/InternVL/tree/main/classification) for more details about the linear probing evaluation.
|
| 34 |
+
|
| 35 |
+
| IN-1K | IN-ReaL | IN-V2 | IN-A | IN-R | IN-Sketch |
|
| 36 |
+
| :---: | :-----: | :---: | :--: | :--: | :-------: |
|
| 37 |
+
| 88.2 | 90.4 | 79.9 | 77.5 | 89.8 | 69.1 |
|
| 38 |
+
|
| 39 |
## Model Usage (Image Embeddings)
|
| 40 |
|
| 41 |
```python
|