irfanICMLL/TorchDistiller

Stars
192
Rank 202,019 (Top 4 %)
Language
Python
Created over 3 years ago
Updated about 3 years ago

irfanICMLL/TorchDistiller

irfanICMLL

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

TorchDistiller

This project is a collection of the open source pytorch code for knowledge distillation, especially for the perception tasks, including semantic segmentation, depth estimation, object detection and instance segmentation.

Collection papers and codebase

Semantic Segmentation

Structured Knowledge Distillation for Semantic Segmentation, CVPR2019 [paper] [code]
Intra-class Feature Variation Distillation for Semantic Segmentation, ECCV2020 [paper] [code]
Channel-wise Knowledge Distillation for Dense Prediction, ICCV2021 [paper] [code]
Knowledge Distillation based on MMsegmentation [code]

Object Detection and Instance Segmentation

Knowledge Distillation based on MMdetection [code]
Knowledge Distillation based on Adet [code]

Update History

2021.08.20 Release the code for channel-wise distillation for semantic segmentation

We are integrating more of our work and other great studies into this project.

TO DO LIST

Distillation on FCOS
Distillation on CondInst

Contribute

To contribute, PR is appreciated and suggestions are welcome to discuss with.

structure_knowledge_distillation

The official code for the paper 'Structured Knowledge Distillation for Semantic Segmentation'. (CVPR 2019 ORAL) and extension to other tasks.

CoupleGenerator

Generate your lover with your photo

ETC-Real-time-Per-frame-Semantic-video-segmentation

Enforcing temporal consistency in real-time per-frame semantic video segmentation

Auto_painter

Recently, realistic image generation using deep neural networks has become a hot topic in machine learning and computer vision. Such an image can be generated at pixel level by learning from a large collection of images. Learning to generate colorful cartoon images from black-and-white sketches is not only an interesting research problem, but also a useful application in digital entertainment. In this paper, we investigate the sketch-to-image synthesis problem by using conditional generative adversarial networks (cGAN). We propose a model called auto-painter which can automatically generate compatible colors given a sketch. Wasserstein distance is used in training cGAN to overcome model collapse and enable the model converged much better. The new model is not only capable of painting hand-draw sketch with compatible colors, but also allowing users to indicate preferred colors. Experimental results on different sketch datasets show that the auto-painter performs better than other existing image-to-image methods.

EMM-for-stock-prediction

We propose a model to analyze sentiment of online stock forum and use the information to predict stock volatility in the Chinese market. By generating a sentimental dictionary, we analyze the sentimental tendencies of each post as sentiment indicators. Such sentimental information will be fused with market data for prediction based on Recurrent Neural Networks (RNNs). We manually labeled the sentiment of forum post and make the data public available for research. Empirical evidence shows that 8 of the 10 stocks perform better with sentimental indicators.

Auto_painter_demo

The code of building a web demo for Auto_painter

SSIW

The code of 'The devil is in the labels: Semantic segmentation from sentences'.

inceptionV2_finetune

Fine-tuning of inceptionV2 on CUB-200 Birds dataset in Tensorflow

stock_predict

This project predicts stock trends on the basis of online user comments and LSTM

colorization

horseSeg

dvn

dvn for semantic segmentation