Update README.md
Browse files
README.md
CHANGED
@@ -3,7 +3,7 @@ license: apache-2.0
|
|
3 |
pipeline_tag: image-to-text
|
4 |
---
|
5 |
|
6 |
-
#
|
7 |
```python
|
8 |
from transformers import AutoTokenizer, VisionEncoderDecoderModel, AutoImageProcessor
|
9 |
from PIL import Image
|
@@ -18,6 +18,8 @@ imgen = Image.open(requests.get('https://cdn-uploads.huggingface.co/production/u
|
|
18 |
print(tokenizer.decode(model.generate(feature_extractor(imgen, return_tensors="pt").pixel_values)[0]).replace('\\[','\\begin{align*}').replace('\\]','\\end{align*}'))
|
19 |
```
|
20 |
|
|
|
|
|
21 |
# 补充:
|
22 |
建议图片尺寸:大约 (400, 500), (H, W)。
|
23 |
建议输出字数:大约100-300个tokens。
|
|
|
3 |
pipeline_tag: image-to-text
|
4 |
---
|
5 |
|
6 |
+
# 使用方法:
|
7 |
```python
|
8 |
from transformers import AutoTokenizer, VisionEncoderDecoderModel, AutoImageProcessor
|
9 |
from PIL import Image
|
|
|
18 |
print(tokenizer.decode(model.generate(feature_extractor(imgen, return_tensors="pt").pixel_values)[0]).replace('\\[','\\begin{align*}').replace('\\]','\\end{align*}'))
|
19 |
```
|
20 |
|
21 |
+
colab: https://colab.research.google.com/drive/1vj3GKTmHcVor7FRKyk254nXEi9Lu_dhL?usp=sharing
|
22 |
+
|
23 |
# 补充:
|
24 |
建议图片尺寸:大约 (400, 500), (H, W)。
|
25 |
建议输出字数:大约100-300个tokens。
|