Streamlit tool to explore coco datasets

Last update: Dec 16, 2022

Overview

What is this

This tool given a COCO annotations file and COCO predictions file will let you explore your dataset, visualize results and calculate important metrics.

Running the explorer on example data

You can use the predictions I prepared and explore the results on the COCO validation dataset. The predictions are coming from a Mask R-CNN model trained with mmdetection.

Download (and extract in project directory) the labels, annotations and images:

https://drive.google.com/open?id=1wxIagenNdCt_qphEe8gZYK7H2_to9QXl

Setup using docker

sudo docker run -p 8501:8501 -it -v "$PWD"/coco_data:/coco_data i008/cocoexp:latest  \
    --coco_train /coco_data/ground_truth_annotations.json \
    --coco_predictions /coco_data/predictions.json  \
    --images_path /coco_data/images/

Setup using conda

conda env update
conda activate cocoexplorer
streamlit run coco_explorer.py -- --coco_train ./coco_data/ground_truth_annotations.json --coco_predictions ./coco_data/predictions.json  --images_path ./coco_data/val2017/

Setup using pip

python3 -m venv .venv
. .venv/bin/activate
pip install -r requirements.txt
streamlit run coco_explorer.py -- --coco_train ./coco_data/ground_truth_annotations.json --coco_predictions ./coco_data/predictions.json  --images_path ./coco_data/val2017/

go to http://localhost:8501

Running on your own data

In the same way you can explore your own results. Just follow the official COCO dataset format for annotations and predictions.

Streamlit tool to explore coco datasets

Related tags

Overview

What is this

Running the explorer on example data

Running on your own data

Examples

Owner

Jakub Cieslik

Unofficial PyTorch implementation of the Adaptive Convolution architecture for image style transfer

Unsupervised Image to Image Translation with Generative Adversarial Networks

Ansible Automation Example: JSNAPY PRE/POST Upgrade Validation

TargetAllDomainObjects - A python wrapper to run a command on against all users/computers/DCs of a Windows Domain

TensorFlow-based implementation of "ICNet for Real-Time Semantic Segmentation on High-Resolution Images".

DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

Model Agnostic Interpretability for Multiple Instance Learning

Social Fabric: Tubelet Compositions for Video Relation Detection

An SMPC companion library for Syft

A simple, fast, and efficient object detector without FPN

The codes and related files to reproduce the results for Image Similarity Challenge Track 2.

A PyTorch library for Vision Transformers

Extracts data from the database for a graph-node and stores it in parquet files

DeOldify - A Deep Learning based project for colorizing and restoring old images (and video!)

AI4Good project for detecting waste in the environment

Implementation of "Bidirectional Projection Network for Cross Dimension Scene Understanding" CVPR 2021 (Oral)

FMA: A Dataset For Music Analysis

ISTR: End-to-End Instance Segmentation with Transformers (https://arxiv.org/abs/2105.00637)

Data labels and scripts for fastMRI.org

3DMV jointly combines RGB color and geometric information to perform 3D semantic segmentation of RGB-D scans.