zhongyi-zhou

GestureIMT

Gesture-aware Interactive Machine Teaching with In-situ Object Annotations (UIST 22)

ControlNet

Let us control diffusion models!

DeepSeek-MoE

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

Dual-Reversed-RS

[ECCV2022 Oral] Bringing Rolling Shutter Images Alive with Dual Reversed Distortion

models

Models and examples built with TensorFlow

mywebtest

openpose

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

public-storage

pytorch-cifar

95.16% on CIFAR10 with PyTorch

ritm_interactive_segmentation

Reviving Iterative Training with Mask Guidance for Interactive Segmentation

SSD-Tensorflow

Single Shot MultiBox Detector in TensorFlow

zhongyi-zhou

viper

Code for the paper "ViperGPT: Visual Inference via Python Execution for Reasoning"

visualblocks

Visual Blocks for ML is a Google visual programming framework that lets you create ML pipelines in a no-code graph editor. You – and your users – can quickly prototype workflows by connecting drag-and-drop ML components, including models, user inputs, processors, and visualizations.