1. 03 4月, 2019 1 次提交
    • R
      Refine Image Classification Codes&Docs (#1943) · dc1b032d
      ruri 提交于
      * Move models to legacy, rename models_name to models, refine README
      * Refine eval/infer/train code
      * Release ResNet 18/34, GoogleNet and ShuffleNet v2.
      * Add RMSProp optimizer.
      dc1b032d
  2. 01 3月, 2019 1 次提交
  3. 02 2月, 2019 1 次提交
  4. 01 2月, 2019 1 次提交
  5. 09 1月, 2019 1 次提交
  6. 29 10月, 2018 1 次提交
  7. 21 8月, 2018 1 次提交
  8. 15 6月, 2018 1 次提交
  9. 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