1. 14 Jun, 2019 1 commit
  2. 08 Jun, 2019 1 commit
  3. 27 May, 2019 1 commit
  4. 17 Jan, 2019 1 commit
  5. 15 Nov, 2018 1 commit
  6. 26 Sep, 2018 1 commit
  7. 06 Sep, 2018 1 commit
  8. 01 Aug, 2018 1 commit
  9. 05 Jul, 2018 1 commit
  10. 09 Jun, 2018 1 commit
  11. 16 May, 2018 1 commit
  12. 27 Apr, 2018 1 commit
  13. 28 Mar, 2018 1 commit
  14. 01 Mar, 2018 2 commits
  15. 06 Feb, 2018 1 commit
  16. 31 Jan, 2018 1 commit
  17. 29 Jan, 2018 1 commit
  18. 09 Nov, 2017 1 commit
  19. 27 Oct, 2017 1 commit
  20. 02 Oct, 2017 1 commit
  21. 26 Sep, 2017 1 commit
  22. 28 Jun, 2017 2 commits
    • Alexander Alekhin's avatar
      dnn: added trace macros · ed103833
      Alexander Alekhin authored
      ed103833
    • Vadim Pisarevsky's avatar
      another round of dnn optimization (#9011) · 8b3d6603
      Vadim Pisarevsky authored
      * another round of dnn optimization:
      * increased malloc alignment across OpenCV from 16 to 64 bytes to make it AVX2 and even AVX-512 friendly
      * improved SIMD optimization of pooling layer, optimized average pooling
      * cleaned up convolution layer implementation
      * made activation layer "attacheable" to all other layers, including fully connected and addition layer.
      * fixed bug in the fusion algorithm: "LayerData::consumers" should not be cleared, because it desctibes the topology.
      * greatly optimized permutation layer, which improved SSD performance
      * parallelized element-wise binary/ternary/... ops (sum, prod, max)
      
      * also, added missing copyrights to many of the layer implementation files
      
      * temporarily disabled (again) the check for intermediate blobs consistency; fixed warnings from various builders
      8b3d6603
  23. 26 Jun, 2017 1 commit