Pinned Repositories
AI-RecommenderSystem
该仓库尝试整理推荐系统领域的一些经典算法模型
AI_Tutorial
精选机器学习，NLP，图像识别， 深度学习等人工智能领域学习资料，搜索，推荐，广告系统架构及算法技术资料整理。算法大牛笔记汇总
DABNet
Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation (BMVC2019)
GradCAM-and-GradCAMplus_plus
Based on pytoch, gradcam and gradcam + + are encapsulated into easy-to-use API, and some interesting tests are done with pre trained vgg16, alexnet, densenet 121, mobilenet, resnet18, squeezene. Interested friends can give a star, thank you.
Jiaozicup_keras_788_baseline
2020年“创青春·交子杯”新网银行金融科技挑战赛-AI算法赛道keras版本baseline，线上成绩788。
Jiaozicup_pytorch_776_baseline
2020年“创青春·交子杯”新网银行金融科技挑战赛-AI算法赛道pytorch版本baseline，线上成绩776。
Kaggle_M5_Forecasting_Accuracy_Pro
This is a competition M5 forecasting - accuracy on kaggle. For details, please refer to the link: https://www.kaggle.com/c/m5-forecasting-accuracy/overview. This is my first time to take part in the kaggle competition. After two months of hard work, I finally ranked 172, top4% and won a silver medal.
LMFFNet
Real-time semantic segmentation is widely used in the field of autonomous driving and robotics. Most previous networks achieved great accuracy based on a complicated model involving mass computing. The existing lightweight networks generally reduce the parameter sizes by sacrificing the segmentation accuracy. It is critical to balance the parameters and accuracy for real-time semantic segmentation tasks. In this paper, we introduce a Lightweight-Multiscale-Feature-Fusion Network (LMFFNet) mainly composed of three types of components: Split-Extract-Merge Bottleneck (SEM-B) block, Features Fusion Module (FFM), and Multiscale Attention Decoder (MAD). The SEM-B block extracts sufficient features with fewer parameters. FFMs fuse multiscale semantic features to effectively improve the segmentation accuracy. The MAD well recovers the details of the input images through the attention mechanism. Two networks combined with different components are proposed based on the LMFFNet model. Without pretraining, the smaller network of LMFFNet-S achieves 72.7% mIoU on Cityscapes test set at the 512×1024 resolution with only 1.1 M parameters at a reference speed of 98.9 fps running on a GTX1080Ti GPU while the larger version of LMFFNet-L achieves 74.7% mIoU with 1.4 M parameters at 89.6 fps. Besides, 67.7% mIoU at 208.9 fps and 70.3% mIoU at 72.4 fps are respectively achieved for 360 × 480 and 720 × 960 resolutions on CamVid test set using LMFFNet-S while LMFFNet--L achieves 68.1% mIoU at 182.9 fps and 71.0% mIoU at 66.5 fps, correspondingly. The proposed LMFFNets make an adequate trade-off between accuracy and parameter size for real-time inference for semantic segmentation tasks.
YOLOv5_NCNN
🍅 Deploy ncnn on mobile phones. Support Android and iOS. 移动端ncnn部署，支持Android与iOS。
Greak-1124's Repositories
Greak-1124/LMFFNet
Real-time semantic segmentation is widely used in the field of autonomous driving and robotics. Most previous networks achieved great accuracy based on a complicated model involving mass computing. The existing lightweight networks generally reduce the parameter sizes by sacrificing the segmentation accuracy. It is critical to balance the parameters and accuracy for real-time semantic segmentation tasks. In this paper, we introduce a Lightweight-Multiscale-Feature-Fusion Network (LMFFNet) mainly composed of three types of components: Split-Extract-Merge Bottleneck (SEM-B) block, Features Fusion Module (FFM), and Multiscale Attention Decoder (MAD). The SEM-B block extracts sufficient features with fewer parameters. FFMs fuse multiscale semantic features to effectively improve the segmentation accuracy. The MAD well recovers the details of the input images through the attention mechanism. Two networks combined with different components are proposed based on the LMFFNet model. Without pretraining, the smaller network of LMFFNet-S achieves 72.7% mIoU on Cityscapes test set at the 512×1024 resolution with only 1.1 M parameters at a reference speed of 98.9 fps running on a GTX1080Ti GPU while the larger version of LMFFNet-L achieves 74.7% mIoU with 1.4 M parameters at 89.6 fps. Besides, 67.7% mIoU at 208.9 fps and 70.3% mIoU at 72.4 fps are respectively achieved for 360 × 480 and 720 × 960 resolutions on CamVid test set using LMFFNet-S while LMFFNet--L achieves 68.1% mIoU at 182.9 fps and 71.0% mIoU at 66.5 fps, correspondingly. The proposed LMFFNets make an adequate trade-off between accuracy and parameter size for real-time inference for semantic segmentation tasks.
Greak-1124/GradCAM-and-GradCAMplus_plus
Based on pytoch, gradcam and gradcam + + are encapsulated into easy-to-use API, and some interesting tests are done with pre trained vgg16, alexnet, densenet 121, mobilenet, resnet18, squeezene. Interested friends can give a star, thank you.
Greak-1124/Kaggle_M5_Forecasting_Accuracy_Pro
This is a competition M5 forecasting - accuracy on kaggle. For details, please refer to the link: https://www.kaggle.com/c/m5-forecasting-accuracy/overview. This is my first time to take part in the kaggle competition. After two months of hard work, I finally ranked 172, top4% and won a silver medal.
Greak-1124/Jiaozicup_pytorch_776_baseline
2020年“创青春·交子杯”新网银行金融科技挑战赛-AI算法赛道pytorch版本baseline，线上成绩776。
Greak-1124/Jiaozicup_keras_788_baseline
2020年“创青春·交子杯”新网银行金融科技挑战赛-AI算法赛道keras版本baseline，线上成绩788。
Greak-1124/AI-RecommenderSystem
该仓库尝试整理推荐系统领域的一些经典算法模型
Greak-1124/AI_Tutorial
精选机器学习，NLP，图像识别， 深度学习等人工智能领域学习资料，搜索，推荐，广告系统架构及算法技术资料整理。算法大牛笔记汇总
Greak-1124/DABNet
Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation (BMVC2019)
Greak-1124/YOLOv5_NCNN
🍅 Deploy ncnn on mobile phones. Support Android and iOS. 移动端ncnn部署，支持Android与iOS。