Kaihua Tang

Scene-Graph-Benchmark.pytorch. A new codebase for popular Scene Graph Generation methods (2020). Visualization & Scene Graph Extraction on custom images/datasets are provided. It's also a PyTorch implementation of paper “Unbiased Scene Graph Generation from Biased Training CVPR 2020”

Long-Tailed-Recognition.pytorch. [NeurIPS 2020] This project provides a strong single-stage baseline for Long-Tailed Classification, Detection, and Instance Segmentation (LVIS). It is also a PyTorch implementation of the NeurIPS 2020 paper 'Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect'.

Building-a-Small-LLM-from-Scratch. 该系列的目的是让读者可以在基础的pytorch上，不依赖任何其他现成的外部库，从零开始理解并实现一个大语言模型的所有组成部分，以及训练微调代码，因此读者仅需python，pytorch和最基础深度学习背景知识即可。

VQA2.0-Recent-Approachs-2018.pytorch. A pytroch reimplementation of "Bilinear Attention Network", "Intra- and Inter-modality Attention", "Learning Conditioned Graph Structures", "Learning to count object", "Bottom-up top-down" for Visual Question Answering 2.0

ResNet50-Pytorch-Face-Recognition. Using Pytorch to implement a ResNet50 for Cross-Age Face Recognition

Generalized-Long-Tailed-Benchmarks.pytorch. [ECCV 2022] A generalized long-tailed challenge that incorporates both the conventional class-wise imbalance and the overlooked attribute-wise imbalance within each class. The proposed IFL together with other baselines are also included.

VCTree-Scene-Graph-Generation. Code for the Scene Graph Generation part of CVPR 2019 oral paper: "Learning to Compose Dynamic Tree Structures for Visual Contexts"

GGNN-for-bAbI-dataset.pytorch.1.0. A Complete PyTorch 1.0 Implementation of Gated Graph Sequence Neural Networks (GGNN)

ResNet50-Tensorflow-Face-Recognition. Using Tensorflow to implement a ResNet50 for Cross-Age Face Recognition

Qwen-Tokenizer-Pruner. Due to the huge vocaburary size (151,936) of Qwen models, the Embedding and LM Head weights are excessively heavy. Therefore, this project provides a Tokenizer vocabulary shearing solution for Qwen and Qwen-VL.

VCTree-Visual-Question-Answering. Code for the Visual Question Answering (VQA) part of CVPR 2019 oral paper: "Learning to Compose Dynamic Tree Structures for Visual Contexts"

LLM-TP-Inference-on-910B. 本项目提供了基于910B的huggingface LLM模型的Tensor Parallel(TP)部署教程，同时也可以作为一份极简的TP学习代码。

Local-Disco-Diffusion-v5.2.jupyterNote. A custom Disco Diffusion v5.2 that runs on local GPUS.

CiiV-Adversarial-Robustness.pytorch. The official PyTorch Implementation of the Paper "Adversarial Visual Robustness by Causal Intervention"

LVIS-for-mmdetection. support Large Vocabulary Instance Segmentation (LVIS) dataset for mmdetection

Kinetics-Data-Preprocessing. An instruction to 1) download the Kinetics-400/Kinetics-600, 2) resize the videos, and 3) prepare annotations.

Describe-and-Guess-GAME-Using-GPT-3. A simple demo of how to use GPT-3 to play Describe-and-Guess in the specified topic and question type.

machine-learning-notes. My continuously updated Machine Learning, Probabilistic Models and Deep Learning notes and demos (1000+ slides) 我不间断更新的机器学习，概率模型和深度学习的讲义(1000+页)和视频链接

Minimalist-TinyLLaMA-to-Onnx. Export TinyLLaMA to Onnx and Conduct LLM inference using onnxruntime

bottom-up-attention-vqa. An efficient PyTorch implementation of the winning entry of the 2017 VQA Challenge.

stable-diffusion-webui. Stable Diffusion web UI

pytorch-grad-cam. PyTorch implementation of Grad-CAM

HowToTrainYourMAMLPytorch. The original code for the paper "How to train your MAML" along with a replication of the original "Model Agnostic Meta Learning" (MAML) paper in Pytorch.

Quick-Draw-Multimodal-Recognition. The Course Project of CE7454 (Team 13)

Interative-Story.agent. This project aims to create a new storytelling experience by allowing users to interact with AI to shape the story's direction.

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.)

CS-Notes. :books: Computer Science Learning Notes

faster-rcnn.pytorch. Python

SceneGraphParser. A python toolkit for parsing captions (in natural language) into scene graphs (as symbolic representations).

adversarial-attacks-pytorch. PyTorch implementations of Adversarial attacks and utils.

coding-interview-university. A complete computer science study plan to become a software engineer.