kamalm8 Goto Github PK

caption-anything

Caption-Anything is a versatile tool combining image segmentation, visual captioning, and ChatGPT, generating tailored captions with diverse controls for user preferences.

deeplabel

A cross-platform image annotation tool for machine learning

detectron

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

dotfiles

Configurations and dotfiles for my development machine.

few-shot-learning-fashion

This repository includes benchmark and training code for few shot learning algorithms on the Fashion product image classification dataset.

fots_tf

This an implementation of FOTS with tensorflow

frustum-pointnets

Frustum PointNets for 3D Object Detection from RGB-D Data

grpc

The C based gRPC (C++, Python, Ruby, Objective-C, PHP, C#)

keras-preprocessing

Utilities for working with image data, text data, and sequence data.

mask_rcnn

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

models

Models and examples built with TensorFlow

mymastersthesis

This is the final version of my masters thesis on blind multichannel speech dereverberation.

network_binarization_papers

This is my reading list of network binarization papers.

person-attribute-recognition-marketduke

A simple baseline implemented in PyTorch for pedestrian attribute recognition task, evaluating on Market-1501 and DukeMTMC-reID dataset.

vit-net