Instructions to use michelecafagna26/blip-base-captioning-ft-hl-narratives with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use michelecafagna26/blip-base-captioning-ft-hl-narratives with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="michelecafagna26/blip-base-captioning-ft-hl-narratives")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("michelecafagna26/blip-base-captioning-ft-hl-narratives") model = AutoModelForMultimodalLM.from_pretrained("michelecafagna26/blip-base-captioning-ft-hl-narratives", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| license: apache-2.0 | |
| tags: | |
| - image-captioning | |
| languages: | |
| - en | |
| pipeline_tag: image-to-text | |
| datasets: | |
| - michelecafagna26/hl-narratives | |
| language: | |
| - en | |
| metrics: | |
| - sacrebleu | |
| - rouge | |
| library_name: transformers | |
| ## BLIP-base fine-tuned for Narrative Image Captioning | |
| [BLIP](https://arxiv.org/abs/2201.12086) base trained on the [HL Narratives](https://huggingface.co/datasets/michelecafagna26/hl-narratives) for **high-level narrative descriptions generation** | |
| ## Model fine-tuning ๐๏ธโ | |
| - Trained for a 3 epochs | |
| - lr: 5eโ5 | |
| - Adam optimizer | |
| - half-precision (fp16) | |
| ## Test set metrics ๐งพ | |
| | Cider | SacreBLEU | Rouge-L| | |
| |--------|------------|--------| | |
| | 79.39 | 11.70 | 26.17 | | |
| ## Model in Action ๐ | |
| ```python | |
| import requests | |
| from PIL import Image | |
| from transformers import BlipProcessor, BlipForConditionalGeneration | |
| processor = BlipProcessor.from_pretrained("blip-base-captioning-ft-hl-narratives") | |
| model = BlipForConditionalGeneration.from_pretrained("blip-base-captioning-ft-hl-narratives").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 near a lake and is on vacation." | |
| ``` | |
| ## 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} | |
| } | |
| ``` |