Hugging Face's logo

Seungjun
/
image_captioner

Image-to-Text
Transformers
Safetensors
pytorch_model_hub_mixin
model_hub_mixin
Inference Endpoints
Model card Files Community
Edit model card

This model has been pushed to the Hub using the PytorchModelHubMixin integration:

  • Library: [More Information Needed]
  • Docs: [More Information Needed]

About the project

This is a decoder of image captioning model. The image will be first preprocessed and resized to (224, 224) and then passed to ViT_b_32(with no classification layer), and then this will output (N, 768). Then this will be repeated 32(max_length) times and will be passed to K, V to CrossMultiHeadAttention block in decoder. This model was trained with Microsoft COCO2017 dataset and acheived 0.54 of masked_accuracy on validation set.

Sample Code

To use this model, first you need to download ViT_b_32 which will be used as encoder and download decoder from this repo.

Downloads last month
7
Safetensors
Model size
44.3M params
Tensor type
F32
·
Inference Examples
Image-to-Text
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.