Instructions to use nlpconnect/vit-gpt2-image-captioning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nlpconnect/vit-gpt2-image-captioning with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning") model = AutoModelForMultimodalLM.from_pretrained("nlpconnect/vit-gpt2-image-captioning", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
496b5b1
1
Parent(s): 0e334c7
Updates README.md sample running code to remove FutureWarning deprecation error for `ViTFeatureExtractor`.
Browse filesChanges `ViTFeatureExtractor` to `ViTFeatureExtractor` in sample running code to resolve FutureWarning error: 'FutureWarning: The class ViTFeatureExtractor is deprecated and will be removed in version 5 of Transformers. Please use ViTImageProcessor instead.'
README.md
CHANGED
|
@@ -28,12 +28,12 @@ This is an image captioning model trained by @ydshieh in [flax ](https://github.
|
|
| 28 |
|
| 29 |
```python
|
| 30 |
|
| 31 |
-
from transformers import VisionEncoderDecoderModel,
|
| 32 |
import torch
|
| 33 |
from PIL import Image
|
| 34 |
|
| 35 |
model = VisionEncoderDecoderModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
|
| 36 |
-
feature_extractor =
|
| 37 |
tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
|
| 38 |
|
| 39 |
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
|
|
|
| 28 |
|
| 29 |
```python
|
| 30 |
|
| 31 |
+
from transformers import VisionEncoderDecoderModel, ViTImageProcessor, AutoTokenizer
|
| 32 |
import torch
|
| 33 |
from PIL import Image
|
| 34 |
|
| 35 |
model = VisionEncoderDecoderModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
|
| 36 |
+
feature_extractor = ViTImageProcessor.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
|
| 37 |
tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
|
| 38 |
|
| 39 |
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|