Commit
•
5fcaacd
1
Parent(s):
74406c3
Update README.md
Browse files
README.md
CHANGED
@@ -1,5 +1,35 @@
|
|
1 |
# Hindi Image Captioning Model
|
2 |
|
3 |
-
This is an encoder-decoder image captioning model made with VIT encoder and GPT2-Hindi as a decoder.
|
4 |
|
5 |
-
This model was trained using HuggingFace course community week, organized by Huggingface. Training were done on Kaggle Notebooks
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
# Hindi Image Captioning Model
|
2 |
|
3 |
+
This is an encoder-decoder image captioning model made with VIT encoder and GPT2-Hindi as a decoder. This is a first attempt at using ViT + GPT2-Hindi for image captioning task. We used the Flickr8k Hindi Dataset, which is the translated version of the original Flickr8k Dataset, available on kaggle to train the model.
|
4 |
|
5 |
+
This model was trained using HuggingFace course community week, organized by Huggingface. Training were done on Kaggle Notebooks.
|
6 |
+
|
7 |
+
## How to use
|
8 |
+
|
9 |
+
Here is how to use this model to caption an image of the Flickr8k dataset:
|
10 |
+
```python
|
11 |
+
import torch
|
12 |
+
import requests
|
13 |
+
from PIL import Image
|
14 |
+
from transformers import ViTFeatureExtractor, AutoTokenizer, VisionEncoderDecoderModel
|
15 |
+
|
16 |
+
if torch.cuda.is_available():
|
17 |
+
device = 'cuda'
|
18 |
+
else:
|
19 |
+
device = 'cpu'
|
20 |
+
|
21 |
+
url = 'https://shorturl.at/fvxEQ'
|
22 |
+
image = Image.open(requests.get(url, stream=True).raw)
|
23 |
+
|
24 |
+
feature_extractor = ViTFeatureExtractor.from_pretrained('google/vit-base-patch16-224')
|
25 |
+
tokenizer = AutoTokenizer.from_pretrained('surajp/gpt2-hindi')
|
26 |
+
model = VisionEncoderDecoderModel.from_pretrained('team-indain-image-caption/hindi-image-captioning').to(device)
|
27 |
+
|
28 |
+
#Inference
|
29 |
+
sample = feature_extractor(image, return_tensors="pt").pixel_values.to(device)
|
30 |
+
clean_text = lambda x: x.replace('<|endoftext|>','').split('\n')[0]
|
31 |
+
|
32 |
+
caption_ids = model.generate(sample, max_length = 50)[0]
|
33 |
+
caption_text = clean_text(tokenizer.decode(caption_ids))
|
34 |
+
print(caption_text)
|
35 |
+
```
|