Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

implement PaddleHub encoder #86

Closed
nan-wang opened this issue Mar 14, 2020 · 0 comments · Fixed by #105
Closed

implement PaddleHub encoder #86

nan-wang opened this issue Mar 14, 2020 · 0 comments · Fixed by #105
Assignees

Comments

@nan-wang
Copy link
Member

nan-wang commented Mar 14, 2020

image classification

PaddleHub has 14 types of models (17 models in total)

  1. Xception
  2. VGG
  3. ShuffleNet V2
  4. ResNeXt
    • ResNeXt_vd
    • SE_ResNeXt
    • ResNeXt_wsl
    • ResNeXt
  5. ResNet
    • ResNet V2
  6. PNASNet
  7. Mobilenet_v2
  8. Inception_V4
  9. GoogleNet
  10. EfficientNet
  11. DPN
  12. DenseNet
  13. DarkNet
  14. AlexNet

图像生成

使用GAN的隐层变量表示图片

  1. STGAN
  2. StarGAN
  3. CycleGAN
  4. AttGAN

discussion

  • 目标检测类目下的模型作为 transformer

    1. YOLOv3
    2. Ultra-Light-Fast-Generic-Face-Detector
    3. SSD
    4. PyramidBox
    5. faster_rcnn
  • 图像分割类目下的模型作为 transformer

    1. deeplabv3p
    2. ACE2P
  • 关键点检测类目下的模型输出需要配合embedding使用

    1. pos_resnet50

reference:

https://www.paddlepaddle.org.cn/hublist

@nan-wang nan-wang added this to the Essential CV Encoders milestone Mar 14, 2020
@nan-wang nan-wang self-assigned this Mar 14, 2020
@nan-wang nan-wang added the priority/research Possibly useful, but not yet enough research to actually get it done. label Mar 14, 2020
@nan-wang nan-wang removed the priority/research Possibly useful, but not yet enough research to actually get it done. label Mar 15, 2020
@nan-wang nan-wang linked a pull request Mar 18, 2020 that will close this issue
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging a pull request may close this issue.

1 participant