chenkeshuai Goto Github PK
Name: keshuai Chen
Type: User
Name: keshuai Chen
Type: User
The assignment of machine learning course for post-graduates at BUAA EE, 2019.
🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.
Implementation of A Deep Multi-Level Network for Saliency Prediction in Pytorch
PyTorch implementation of "Distilling the Knowledge in a Neural Network" for model compression
An Object Detection Knowledge Distillation framework powered by pytorch, now having SSD and yolov5.
Online Multi-Granularity Distillation for GAN Compression (ICCV2021)
In this study, we propose Perceptual Generative Adversarial Networks (PGANs) for image-to-image transformations. Different from existing application driven algorithms, PGAN provides a generic framework of learning to map from input images to desired images, such as a rainy image to its de-rained counterpart, object edges to photos, and semantic labels to a scenes image. The proposed PAN consists of two feed-forward convolutional neural networks: the image transformation net- work T and the discriminative network D. Besides the generative adversarial loss widely used in GANs, we propose the perceptual adversarial loss, which undergoes an adversarial training process between the image transformation network T and the hidden layers of the discriminative network D. The hidden layers and the output of the discriminative network D are upgraded to constantly and automatically discover the discrepancy between the transformed image and the corresponding ground truth, while the image transformation network T is trained to minimize the discrepancy explored by the discriminative network D. Through integrating the generative adversarial loss and the perceptual adversarial loss, D and T can be trained alternately to solve image-to-image transformation tasks. Experiments evaluated on several image-to-image transformation tasks (e.g., image de- raining and image inpainting) demonstrate the effectiveness of the proposed PAN and its advantages over many existing works.
convert dataset to coco/voc format
Tool box for PyTorch
PyTorch Implementation for Segmentation and Saliency Prediction
[CVPR 2022 Oral] QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection
TIP2019-GazeGAN Saliency Model
A saliency project based on SalGAN for ML lesson
SalGAN: Visual Saliency Prediction with Generative Adversarial Networks
List of the Papers Addressing Vision-based Small Object Detection
Spring Framework
vedai dataset for darknet
The dataset for drone based detection and tracking is released, including both image/video, and annotations.
How to create custom COCO data set for object detection
start from a rookie
YOLO ModelCompression MultidatasetTraining
这是一个YoloV4-pytorch的源码,可以用于训练自己的模型。
这是一个YoloV4-tiny-pytorch的源码,可以用于训练自己的模型。
implementation of Distilling Object Detectors with Fine-grained Feature Imitation on yolov5
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.