1. 29 5月, 2018 1 次提交
  2. 12 2月, 2018 1 次提交
  3. 04 9月, 2017 1 次提交
  4. 17 5月, 2017 1 次提交
  5. 16 5月, 2017 1 次提交
  6. 20 12月, 2016 2 次提交
    • P
      fix style issues · 6e405a10
      Peng Li 提交于
      6e405a10
    • P
      Add excluded_chunk_types to ChunkEvaluator · 8fe3a3aa
      Peng Li 提交于
      The chunks of types in excluded_chunk_types will not be counted in
      ChunkEvaluator. This is useful for tasks such as SRL, in which chunks of
      type V (verb) will not be taken into account in evaluation.
      8fe3a3aa
  7. 09 12月, 2016 1 次提交
  8. 22 11月, 2016 2 次提交
  9. 20 11月, 2016 1 次提交
    • Y
      Fix several cpp issues · 20600e70
      Yu Yang 提交于
      * Different Type compare.
      * ostream << should pass a const object.
      * remove always true checks.
      20600e70
  10. 17 10月, 2016 1 次提交
    • E
      Fix sparse training for trainer_count=1 (#204) · 28bc05b1
      emailweixu 提交于
      * Fix sparse training for trainer_count=1
      
      For trainer_count=1, the gradient machine is NeuralNetwork, which does not create parameter buf for PARAMETER_GRADIENT for sparse update in Parameter::enableType. But gradient parameter buf is still used in SgdThreadUpdater.
      
      * Minor update to comment
      28bc05b1
  11. 29 8月, 2016 1 次提交