|
--- |
|
tags: |
|
- image-to-text |
|
- image-captioning |
|
license: apache-2.0 |
|
--- |
|
|
|
# Sample running code |
|
|
|
```python |
|
|
|
from transformers import VisionEncoderDecoderModel, ViTFeatureExtractor, AutoTokenizer |
|
import torch |
|
from PIL import Image |
|
|
|
model = VisionEncoderDecoderModel.from_pretrained("jaimin/image_caption") |
|
feature_extractor = ViTFeatureExtractor.from_pretrained("jaimin/image_caption") |
|
tokenizer = AutoTokenizer.from_pretrained("jaimin/image_caption") |
|
|
|
device = torch.device("cuda" if torch.cuda.is_available() else "cpu") |
|
model.to(device) |
|
|
|
|
|
|
|
max_length = 16 |
|
num_beams = 4 |
|
gen_kwargs = {"max_length": max_length, "num_beams": num_beams} |
|
def predict_step(image_paths): |
|
images = [] |
|
for image_path in image_paths: |
|
i_image = Image.open(image_path) |
|
if i_image.mode != "RGB": |
|
i_image = i_image.convert(mode="RGB") |
|
|
|
images.append(i_image) |
|
|
|
pixel_values = feature_extractor(images=images, return_tensors="pt").pixel_values |
|
pixel_values = pixel_values.to(device) |
|
|
|
output_ids = model.generate(pixel_values, **gen_kwargs) |
|
|
|
preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True) |
|
preds = [pred.strip() for pred in preds] |
|
return preds |
|
|
|
|
|
``` |
|
|
|
# Sample running code using transformers pipeline |
|
|
|
```python |
|
|
|
from transformers import pipeline |
|
|
|
image_to_text = pipeline("image-to-text", model="jaimin/image_caption") |
|
|
|
|
|
|
|
|
|
``` |
