|
--- |
|
license: apache-2.0 |
|
language: |
|
- en |
|
base_model: |
|
- WinKawaks/vit-small-patch16-224 |
|
- google/bert_uncased_L-2_H-128_A-2 |
|
pipeline_tag: image-to-text |
|
library_name: transformers |
|
tags: |
|
- vit |
|
- bert |
|
- vision |
|
- caption |
|
- captioning |
|
- image |
|
--- |
|
An image captioning model, based on bert-tiny and vit-small, weighing only 100mb! |
|
|
|
Works very fast on CPU. |
|
|
|
```python |
|
from transformers import AutoTokenizer, AutoImageProcessor, VisionEncoderDecoderModel |
|
import requests, time |
|
from PIL import Image |
|
|
|
model_path = "cnmoro/tiny-image-captioning" |
|
|
|
# load the image captioning model and corresponding tokenizer and image processor |
|
model = VisionEncoderDecoderModel.from_pretrained(model_path) |
|
tokenizer = AutoTokenizer.from_pretrained(model_path) |
|
image_processor = AutoImageProcessor.from_pretrained(model_path) |
|
|
|
# preprocess an image |
|
url = "https://upload.wikimedia.org/wikipedia/commons/thumb/4/47/New_york_times_square-terabass.jpg/800px-New_york_times_square-terabass.jpg" |
|
image = Image.open(requests.get(url, stream=True).raw) |
|
pixel_values = image_processor(image, return_tensors="pt").pixel_values |
|
|
|
start = time.time() |
|
|
|
# generate caption - suggested settings |
|
generated_ids = model.generate( |
|
pixel_values, |
|
temperature=0.7, |
|
top_p=0.8, |
|
top_k=50, |
|
num_beams=3 # you can use 1 for even faster inference with a small drop in quality |
|
) |
|
generated_text = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] |
|
|
|
end = time.time() |
|
|
|
print(generated_text) |
|
# a group of people walking in the middle of a city. |
|
|
|
print(f"Time taken: {end - start} seconds") |
|
# Time taken: 0.11215853691101074 seconds |
|
# on CPU ! |
|
``` |
