metadata
language:
- en
metrics:
- Bleu_1 0.604
- Bleu_2 0.415
- Bleu_3 0.273
- Bleu_4 0.179
- METEOR 0.188
- ROUGE_L 0.445
- CIDEr 0.526
- SPICE 0.113
datasets:
- MSCOCO2014
license: mit
Model Card for Model ID
This modelcard aims to be a base template for new models. It has been generated using this raw template.
Model Details
Model Description
- Developed by: Pasindu Akalpa
- Model type: CNN(ENCODER)-RNN(DECODER)
- Language(s) (NLP): ENGLISH(US)
- License: [MIT]
Evaluation
Metrics
- Bleu_1 = 0.604
- Bleu_2 = 0.415
- Bleu_3 = 0.273
- Bleu_4 = 0.179
- METEOR = 0.188
- ROUGE_L = 0.445
- CIDEr = 0.526
- SPICE = 0.113
Model Architecture and Objective
- Encoder-Decoder Architecture
Compute Infrastructure
Hardware
- GPU = Google Colab V100 GPU
- RAM = 12GB
Software
- python
- pytorch
- jupyter-notebook