ashkamath

mdetr

TRICD

nlp-data-loading-framework-

Here we implement a data pre-processing pipeline (which we built to use as part of a larger codebase) that abstracts over the different types of embeddings and downstream task data sets and provides easy-to-call functions which can be used while building and training models. We hope it will be useful to you as well!

ashkamath.github.io

multimodal

A collection of multimodal datasets, and visual features for VQA and captionning in pytorch. Just run "pip install multimodal"

text_nn

Text classification models. Used a submodule for other projects.

AMMI2021

baby-vqa

Some (baby) Keras deep neural networks for the Visual Question Answering task.

cider

python codes for CIDEr - Consensus-based Image Caption Evaluation

cluster-support

cocoapi

COCO API - Dataset @ http://cocodataset.org/

COMPSCI590S

Systems for Data Science repo

flickr30k_entities

Flickr30K Entities Dataset

image-feature-extractors

Feature extraction and visualization scripts for nocaps baselines.

llama

Inference code for LLaMA models

pytorch-Deep-Learning

Deep Learning (with PyTorch)

pytorch-PPUU

Code for Prediction and Planning Under Uncertainty (PPUU)

sim-eval

A tool for evaluation of semantic similarity measures.

yolov5

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite