This is your work, valued

Shenzhen, China

Ren Tianhe

Elite
@rentainhe

PhD candidate @CVMI-Lab | Previous Senior Computer Vision Engineer in IDEA-CVR @IDEA-Research

rentainhe.github.io/

visualization. a collection of visualization function

448

pytorch-distributed-training. Simple tutorials on Pytorch DDP training

278

TRAR-VQA. [ICCV 2021] Official implementation of the paper "TRAR: Routing the Attention Spans in Transformers for Visual Question Answering"

68

pytorch-pooling. Test different pooling method used in CNN for Computer Vision Task

35

Learn-Detectron2-From-Scratch. Detectron2 Learning Notes Sharing

10

knowledge-graph-visualization. knowledge graph system based on Neo4j and Vue

9

ViT.pytorch. The Pytorch reimplementation of Vision Transformer

9

config-builder. a list of config-builder repo and tutorials which may help you to build your own config file

7

vision-mlp-oneflow. Vision MLP Models Based on OneFlow

7

x-classification. a framework for image classification based on pytorch

6

mini-classification. lightweight and efficient classification project based on pytorch-lightning

4

pytorch-models. Computer vision models on Pytorch

4

TRAR-Feature-Extraction. Grid features extraction for ICCV 2021 paper "TRAR: Routing the Attention Spans in Transformers for Visual Question Answering"

3

rentainhe.github.io. Personal homepage

3

vision-mlp. A collection of SOTA vision mlp models based on Pytorch

3

simple-imagenet-test. A simple test code on Imagenet

2

knowledge-graph-backend. the backend of knowledge graph system based on Springboot

2

MaskDINO. [CVPR 2023] Official implementation of the paper "Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation"

1

ViT-pytorch. Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)

1

T2T-ViT. ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

1

MambaOut. MambaOut: Do We Really Need Mamba for Vision?

1

sam2. The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

1

ConvNeXt. Code release for ConvNeXt model

1

Awesome-Anything. General AI methods for Anything: AnyObject, AnyGeneration, AnyModel, AnyTask, AnyX

1

rexnet. Official Pytorch implementation of ReXNet (Rank eXpansion Network) with pretrained models

1

transformers. 🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

1

what_I_have_read. Just for self-motivation

1

ollama. Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

1

deep-learning-knowledge. A collection of cv-interview problems and answers

1

paper-reading.

1