{}
Model Card for SDSU AI Club Image Captioning Model
Model Details
Model Description
This image captioning model uses the transformers, datasets, and pytorch libraries to fine tune a pre-trained BLIP model with a subset of the Flickr 30k image dataset. The model then generates a new caption for the image.
- Developed by: Charisma Meyer, Daniel Aguilar, Erica Lee, Evan Tardiff, Steven Trujillo, Vincent Huynh
- Funded by [optional]: [More Information Needed]
- Shared by [optional]: [More Information Needed]
- Model type: Image Captioning
- Language(s) (NLP): [More Information Needed]
- License: [More Information Needed]
- Finetuned from model [optional]: Salesforce/blip-image-captioning-base
Model Sources [optional]
- Repository: [More Information Needed]
- Paper: "BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation" by Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi
- Demo [optional]: [More Information Needed]
Uses
Direct Use
[More Information Needed]
Downstream Use [optional]
[More Information Needed]
Out-of-Scope Use
[More Information Needed]
Bias, Risks, and Limitations
[More Information Needed]
Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
Training Details
Training Data
[More Information Needed]
Training Procedure
The training procedure was a process where we took a significant Dataset on hugging face and trained a model, also from hugging face we were able to find a model that performs the image captioning function on this dataset and be able to generate a tailored caption from this image. The biggest problem was that our computers could not train a model with the big datasets as it took to much RAM and it crashed our computers. So we had to figure out to be able to train this model using the datasets given. We came up with the solution that we could create a subset of the dataset, while manipulating the batch size to see how many images are being read at a time and train the model with this new dataset. This allowed us to be able to successfully train the model in a reasonable amount of time.
Preprocessing [optional]
[More Information Needed]
Training Hyperparameters
- Training regime: [More Information Needed]
Speeds, Sizes, Times [optional]
[More Information Needed]
Evaluation
Testing Data, Factors & Metrics
Testing Data
[More Information Needed]
Factors
[More Information Needed]
Metrics
[More Information Needed]
Results
[More Information Needed]
Summary
Model Examination [optional]
[More Information Needed]
Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type: [More Information Needed]
- Hours used: [More Information Needed]
- Cloud Provider: [More Information Needed]
- Compute Region: [More Information Needed]
- Carbon Emitted: [More Information Needed]
Technical Specifications [optional]
Model Architecture and Objective
[More Information Needed]
Compute Infrastructure
[More Information Needed]
Hardware
[More Information Needed]
Software
[More Information Needed]
Citation
@misc{li2022blip, title={BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation}, author={Junnan Li and Dongxu Li and Caiming Xiong and Steven Hoi}, year={2022}, eprint={2201.12086}, archivePrefix={arXiv}, primaryClass={cs.CV} }
@misc{, author={younesbelkada, RocketKnight1}, title={Fine-tune BLIP using Hugging Face transformers and datasets}, year={2023}, url={\url{https://github.com/huggingface/notebooks/blob/main/examples/image_captioning_blip.ipynb}} }
Glossary [optional]
[More Information Needed]
More Information [optional]
[More Information Needed]
Model Card Authors [optional]
[More Information Needed]
Model Card Contact
[More Information Needed]