Downloads · 30 days
0
Thomas1010/image-caption-flickr8k
image-caption-flickr8k is a machine learning model from Thomas1010. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Trained model + vocabulary for an Image Caption Generator (ResNet50 features + LSTM decoder).
Downloads · 30 days
0
Access
Public
Updated Aug 29, 2026
Repo size
24.9 MB
Likes
0
Public
Click a slice to open those files.
.pt24.8 MB · 100%
From the Hugging Face model README
Trained model + vocabulary for an Image Caption Generator (ResNet50 features + LSTM decoder).
Trained as part of Task 1.2 (AI Training '27). See the full project code and instructions on GitHub:
https://huggingface.co/Thomas1010/image-caption-flickr8k
best_model.pt — trained model checkpointvocab.pkl — vocabulary used for tokenizing captionsDownload both files and place them in models_store/ and data/processed/
respectively in the project repo above, then run the Streamlit app.