DL_Notes

• CNN

1.

• 1-1 1-
• 1-2 2-
• 1-3 3-Python
• MIoU
• MIoUPyTorch
• KappaPyTorch
• k
• sklearnk
• Unpooling
• -
• -
• align_corners
• 11
• Focal-Loss
• labelme
• Pytorch
• Batch Normalization
• @-SyncBN-BN
• DO-Convdeeplabv3

2.

• CNN1-CNN
• CNN2-CNN
• CNN3-CNN_
• CNN4-CNN_
• CNN5-CNN_
• CNN6-CNN_
• CNN7-CNN_channels
• CNN8-
• DL-
  • softmax loss
  • Focal Loss
  • PyTorchnn.CrossEntropyLoss()
  • Pseudo Labeling
  • CNNFLOPs
  • ROCAUC

3.CNN

• 1. LeNet-5
• 2. AlexNet
• 3. VGGNet-16
• 4. GoogLeNet_v1-v3
• 5. ResNet_DRN
• 7. DenseNet

4.

• 1. FCN
• 2. UNet
• 3. Deeplabv3
• 4. Deeplabv3+
• 5. DFN
• 6. Non-local-Net
• 7. CCNet
• 8. DAN
• 9. PANet
• 10. ResNeSt
• 11. FarSeg
• 12. G-SCNN
• 13. GFF

5.

5.1

• Mask R-CNNBlendMask

5.2 R-CNN

• R-CNN:Rich feature hierarchies for accurate object detection and semantic segmentation Tech report (v5)
• R-CNN
• Fast R-CNN:Fast R-CNN
• Fast R-CNN
• Faster R-CNN:Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Faster R-CNN
• Mask R-CNN:Mask R-CNN
• Mask R-CNN

6.Attention

• CV
• Attention
• CVAttention-SENetSE
• | Non-localSelf-attention
• SENet
• SKNet
• SENetSKNetResNeXtResNetbackboneResNeSt
• CCNet
• CCNet
• Non-local-Net
• DANDual Attention Network for Scene Segmentation
• DAN12
• PANetPyramid Attention Network for Semantic Segmentation
• PAN12
• DFN
• EMANet Expectation-Maximization Attention Networks for Semantic Segmentation

7.

7.1

• mAP
• Pascal VOCCOCO
• Yolov1-v5
• Yolov1-v5
• Yolov1-v5
• Yolov1
• Yolov2

7.2 two-stage

• R-CNN:Rich feature hierarchies for accurate object detection and semantic segmentation Tech report (v5)
• R-CNN
• Fast R-CNN:Fast R-CNN
• Fast R-CNN
• Faster R-CNN:Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Faster R-CNN

7.3 one-stage

• Yolov1You Only Look Once: Unied, Real-Time Object Detection
• Yolov1
• Yolov1
• Yolov2YOLO9000: Better, Faster, Stronger
• Yolov2
• Yolov2

8.

8.1 tipsarxivPDF

• Cornel Universityhttps://arxiv.org
• cn.arxiv.org xxx.itp.ac.cn
• https://cn. http://xxx.itp.ac.cn/
• cn.arxiv.org/pdf/1710.06081v2 http://xxx.itp.ac.cn/pdf/1506.02640v5

8.2