A simple Python API (built on top of TensorFlow) for neural image captioning with MSCOCO data.
-
Updated
Aug 30, 2021 - Python
A simple Python API (built on top of TensorFlow) for neural image captioning with MSCOCO data.
COCOA: Semantic Amodal Segmentation for huggingface datasets
Microsoft COCO: Common Objects in Context for huggingface datasets
Encoder-Decoder CNN-LSTM Model with an attention mechanism for image captioning. Trained using the Microsoft COCO Dataset.
COCO-Stuff dataset for huggingface datasets
PyTorch implementation of SSD: Single Shot MultiBox Detector.
The Jakarnotator is an annotation tool to create your own database for instance segmentation problem.
A deep-learning object detection project pre-trained on COCO dataset
Trident Pyramid Networks for Object Detection (BMVC 2022)
FQDet: Fast-converging Query-based Detector
Object Detection Dataset Format Converter
Implementation of models in our EMNLP 2019 paper: A Logic-Driven Framework for Consistency of Neural Models
MSCOCO data format details and how to evaluate mAP with pycocotools
Show, Attend, and Tell. Modified to use on UIT-ViIC dataset.
Image Caption Generator using a Pretrained ResNet-50 and an LSTM architecture. Trained on COCO 2017 dataset, it's accessible via a Streamlit app.
MS COCO captions in Arabic
Add a description, image, and links to the mscoco topic page so that developers can more easily learn about it.
To associate your repository with the mscoco topic, visit your repo's landing page and select "manage topics."