1. 21 6月, 2018 1 次提交
    • W
      Refine ctc model code for English dataset. (#991) · db1edc25
      whs 提交于
      * Refine code for English dataset.
      1. Remove a pooling layer.
      2. Change classes_num to 94.
      3. Modify some arguments in ctc_train.py
      4. Add learning rate decay policy.
      
      * Fix readme.
      
      * Fix README.
      
      * Remove consine decay.
      
      * Remove eval.sh
      db1edc25
  2. 15 5月, 2018 1 次提交
  3. 10 5月, 2018 1 次提交
  4. 08 4月, 2018 1 次提交
    • W
      Fix some issues: · 53988dd3
      wanghaoshuang 提交于
      1. Remove illustration of arguments.
      2. Make inference support for more format input.
      53988dd3
  5. 01 4月, 2018 1 次提交
    • W
      Refine document and scripts. · 07d4531a
      wanghaoshuang 提交于
      1. Add document.
      2. Add arguments for saving model and init model.
      3. Refine inference.py and eval.py.
      4. Make ctc_reader.py support for custom data.
      07d4531a
  6. 29 3月, 2018 1 次提交
    • W
      Refine OCR CTC model. · ee154a8f
      wanghaoshuang 提交于
      1. Add download of data into ctc_read.py
      2. Use 'clone' instead of 'get_inference_program'
      3. Add time to train log
      ee154a8f
  7. 27 2月, 2018 1 次提交
    • W
      1. Add eval script · b5c17665
      wanghaoshuang 提交于
      2. Add inference script
      3. Add load model script
      4. Add some functions into ctc_reader
      b5c17665
  8. 05 2月, 2018 1 次提交
  9. 01 2月, 2018 1 次提交