1. 15 5月, 2020 1 次提交
    • S
      Metric learning api update (#4631) · cb6f778b
      suytingwan 提交于
      * test=develop update one_hot usage according to 1.8
      
      * test=develop update dataloader api by 1.8
      
      * test=develop fix image shape
      
      * test=develop update save load fluid.data
      cb6f778b
  2. 11 5月, 2020 1 次提交
  3. 02 9月, 2019 1 次提交
  4. 21 8月, 2019 1 次提交
  5. 10 7月, 2019 1 次提交
  6. 08 4月, 2019 1 次提交
  7. 04 4月, 2019 1 次提交
  8. 02 2月, 2019 1 次提交
  9. 01 2月, 2019 1 次提交
  10. 27 11月, 2018 1 次提交
    • K
      Metric (#1467) · dcea1e9f
      kbChen 提交于
      * Add arcmargin loss
      * Update README
      * Update dataset
      dcea1e9f
  11. 29 10月, 2018 1 次提交
  12. 20 9月, 2018 1 次提交
  13. 29 8月, 2018 1 次提交
    • C
      Deep metric learning based on Fluid (#1146) · 3dccfbe1
      Chris Yann 提交于
      * initialize
      
      * add loss
      
      * update
      
      * Update README.md
      
      * Update README.md
      
      * add download
      
      * add split
      
      * Update README.md
      
      * Update README.md
      
      * Update README.md
      
      * update
      
      * update
      
      * Update README.md
      
      * Update README.md
      
      * Update README.md
      
      * Update README.md
      
      * Update README.md
      
      * Update README.md
      
      * Update README.md
      
      * update
      
      * update
      3dccfbe1
  14. 21 8月, 2018 1 次提交
  15. 15 6月, 2018 1 次提交
  16. 28 4月, 2018 1 次提交
    • C
      Model update: Update the parameter initialization of FC layer of SE-ResNeXt and add a README (#825) · f60005c6
      Chris Yann 提交于
      * revise se_resnext for imagenet classification
      
      * Add the method to train a SE-ResNeXt model
      
      The current code can successfully implement the result of SE-ResNeXt-50.
      
      * Update ImageNet2012 URL
      
      * update
      
      * update readme
      
      * Update readme with download URL
      
      * add unzip
      
      * update se_resnext.py with parallel_exe
      
      * delete train function in se_resnext.py
      
      * add eval.py and infer.py
      
      * move cosine_decay from se_resnext.py to train.py
      f60005c6