--- license: apache-2.0 tags: - image-captioning languages: - en pipeline_tag: image-to-text datasets: - michelecafagna26/hl language: - en metrics: - sacrebleu - rouge library_name: transformers --- ## BLIP-base fine-tuned for Image Captioning on High-Level descriptions of Actions [BLIP](https://arxiv.org/abs/2201.12086) base trained on the [HL dataset](https://huggingface.co/datasets/michelecafagna26/hl) for **action generation of images** ## Model fine-tuning ๐Ÿ‹๏ธโ€ - Trained for 6 epochs - lr: 5eโˆ’5, - Adam optimizer, - half-precision (fp16) ## Test set metrics ๐Ÿงพ | Cider | SacreBLEU | Rouge-L| |--------|------------|--------| | 123.07 | 17.16 | 32.16 | ## Model in Action ๐Ÿš€ ```python import requests from PIL import Image from transformers import BlipProcessor, BlipForConditionalGeneration processor = BlipProcessor.from_pretrained("michelecafagna26/blip-base-captioning-ft-hl-actions") model = BlipForConditionalGeneration.from_pretrained("michelecafagna26/blip-base-captioning-ft-hl-actions").to("cuda") img_url = 'https://datasets-server.huggingface.co/assets/michelecafagna26/hl/--/default/train/0/image/image.jpg' raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB') inputs = processor(raw_image, return_tensors="pt").to("cuda") pixel_values = inputs.pixel_values generated_ids = model.generate(pixel_values=pixel_values, max_length=50, do_sample=True, top_k=120, top_p=0.9, early_stopping=True, num_return_sequences=1) processor.batch_decode(generated_ids, skip_special_tokens=True) >>> "she is holding an umbrella." ``` ## BibTex and citation info ```BibTeX @inproceedings{cafagna2023hl, title={{HL} {D}ataset: {V}isually-grounded {D}escription of {S}cenes, {A}ctions and {R}ationales}, author={Cafagna, Michele and van Deemter, Kees and Gatt, Albert}, booktitle={Proceedings of the 16th International Natural Language Generation Conference (INLG'23)}, address = {Prague, Czech Republic}, year={2023} } ```