| --- |
| license: mit |
| library_name: transformers |
| pipeline_tag: image-to-text |
| --- |
| |
| # Load model |
| from transformers import AutoProcessor, BlipForConditionalGeneration |
|
|
| processor = AutoProcessor.from_pretrained("trunks/blip-image-captioning-base") |
| |
| model = BlipForConditionalGeneration.from_pretrained("trunks/blip-image-captioning-base") |
|
|
|
|
| # prepare image for model |
| from PIL import Image |
| from IPython.display import display |
|
|
| img1 = Image.open("imagepath/img.jpeg") |
|
|
| width, height = img1.size |
|
|
| img1_resized = img1.resize((int(0.3 * width), int(0.3 * height)) |
| |
| display(img1_resized) |
|
|
| # testing image |
| inputs = processor(images=img1, return_tensors="pt") |
| |
| pixel_values = inputs.pixel_values |
| |
| generated_ids = model.generate(pixel_values=pixel_values, max_length=50) |
| |
| generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True)[0] |
|
|
| print(generated_caption) |
| |
