ashstuff Goto Github PK

ashstuff.github.io

ashwin_website

ashwin_website_new

awesome-resources

list of awesome resource that i came across

centermask2

CenterMask2 on top of detectron2, in CVPR 2020

clr

convnet.pytorch

ConvNet training using pytorch

dab-detr

[ICLR 2022] DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR

darknet

Convolutional Neural Networks

dcgan-tensorflow

A tensorflow implementation of Deep Convolutional Generative Adversarial Networks

deepdiva

Python Framework for Reproducible Deep Learning Experiments

detectron2

Detectron2 is FAIR's next-generation platform for object detection and segmentation.

detr

End-to-End Object Detection with Transformers

dino

[ICLR 2023] Official implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection"

dissm

dn-detr

[CVPR 2022 Oral]Official implementation of DN-DETR

faster-rcnn.torch

Experimental Torch7 implementation of RCNN for Object Detection with a Region Proposal Network

google-health

kaggle_statefarm

A simple baseline model set using MXNet for Kaggle StateFarm driver position identification

keras

Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on Theano or TensorFlow.

keras-dualpathnetworks

Dual Path Networks for Keras 2.0+

lvm-med

Release LMV-Med pre-trained models

mask_rcnn

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

mcat

Multimodal Co-Attention Transformer for Survival Prediction in Gigapixel Whole Slide Images - ICCV 2021

memory-efficient-attention

Memory Efficient Attention (O(sqrt(n)) for Jax and PyTorch

multimae

MultiMAE: Multi-modal Multi-task Masked Autoencoders, ECCV 2022

openselfsup

Self-Supervised Learning Toolbox and Benchmark

poojavarshini.github.io

poseur

[ECCV 2022] The official repo for the paper "Poseur: Direct Human Pose Regression with Transformers".

pytorch-faster-rcnn

I would appreciate if someone can retrain the model. The "finetune from scratch" result should be better because the training details have been changed. (And mobilenet training not supported yet.)