机器之心整理
参与:张倩、泽南
在机器学习带来的所有颠覆性技术中,计算机视觉领域吸引了业内人士和学术界最大的关注。
VGG: Very Deep Convolutional Networks for Large-Scale Image Recognition
ResNet: Deep Residual Learning for Image Recognition
DenseNet: Densely Connected Convolutional Networks
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
ShuffleNet V2: Practical Guidelines for Ecient CNN Architecture Design
Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search
DeepLabV3: Rethinking Atrous Convolution for Semantic Image Segmentation
PSPNet: Pyramid Scene Parsing Network
DenseASPP: DenseASPP for Semantic Segmentation in Street Scenes
Asymmetric Non-local Neural Networks for Semantic Segmentation
SSD: Single Shot MultiBox Detector
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
YOLOv3: An Incremental Improvement
FPN: Feature Pyramid Networks for Object Detection
CPM: Convolutional Pose Machines
OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
Mask R-CNN
Pix2pix: Image-to-Image Translation with Conditional Adversarial Nets
CycleGAN: Unpaired Image-to-Image Translation using Cycle-Consistent
pip3 install -r requirements.txtcd extensions
sh make.sh
OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
Mask R-CNN
Pix2pix
CycleGAN
cd scripts/seg/cityscapes/
bash run_fs_pspnet_cityscapes_seg.sh train tag
cd scripts/seg/cityscapes/
bash run_fs_pspnet_cityscapes_seg.sh train tag
cd scripts/seg/cityscapes/
bash run_fs_pspnet_cityscapes_seg.sh val tag
cd scripts/seg/cityscapes/
bash run_fs_pspnet_cityscapes_seg.sh test tag
10月16日晚,NVIDIA GPU 计算专家团队高级工程师季光博士将带来线上主题分享:利用 TensorRT 自由搭建高性能推理模型。点击阅读原文立即免费报名。