Skip to content
This project is mirrored from https://review.mlplatform.org/tosa/reference_model. Pull mirroring updated .
  1. Aug 02, 2023
  2. Jul 31, 2023
  3. Jul 27, 2023
    • Jerry-Ge's avatar
      Enable lazy tensor allocation · e5cabbf7
      Jerry-Ge authored
      
      
      - The previous ref_model was allocating the memory for all tensors in
      the graph upfront which is unnecessary and wasteful.
      - This patch changes to only allocate initial input tensors on the entry
      point using the allocateInputTensor() function.
      - The output tensors are ensured to have been allocated before executing
      a node. The output tenosrs are the inputs for the next node.
      - When a node's evaluation is finished, its input tensors will be freed
      if they will no longer be used by anyone else.
      
      Signed-off-by: Jerry-Ge's avatarJerry Ge <jerry.ge@arm.com>
      Change-Id: Ibb3e8c9e6344f6cd9eb20532a03b2097b93247f9
      e5cabbf7
  4. Jul 26, 2023
  5. Jul 25, 2023
  6. Jul 17, 2023
  7. Jul 14, 2023
  8. Jul 11, 2023
  9. Jul 07, 2023
  10. Jul 06, 2023
  11. Jul 05, 2023
  12. Jun 29, 2023
  13. Jun 26, 2023
  14. Jun 21, 2023
    • Tai Ly's avatar
      Add tf broadcast-to testing · fe36fa9f
      Tai Ly authored
      
      
      This patch adds BoradcastTo Op to the tf tests.
      Did not add tflite testing because the tf.lite.TFLiteConverter converts
      tf.broadcast-to to tfl.mul by 1.
      
      Signed-off-by: default avatarTai Ly <tai.ly@arm.com>
      Change-Id: Icd372e619c318121c19eca87d5716bcd5fbbbb23
      fe36fa9f
  15. Jun 20, 2023
  16. Jun 15, 2023
  17. Jun 12, 2023
  18. Jun 02, 2023
  19. May 25, 2023
  20. May 18, 2023
    • Tai Ly's avatar
      Add abs calculations under precise_mode · 307392a4
      Tai Ly authored and Eric Kunze's avatar Eric Kunze committed
      
      
      This adds a second run of reference model under precise_mode
      when test_desc.json contains a "compliance" dictionary which
      contains a "mode" entry with value "dot product".
      
      In this second run, abs_mode will be set to true, which causes:
      
      1. evaluation will take absolute values of inputs for these operators:
      	conv2d, conv3d, depthwise_conv2d, fully_connected,
      	matmul, transpose_conv2d, fft2d, rfft2d
      	reduce_sum, avg_pool2d
      2. output files will have prefix "bounds_" prepended to them
      
      Signed-off-by: default avatarTai Ly <tai.ly@arm.com>
      Change-Id: I7070ecc7ead2d2ea3375c44663d653c6772b88e0
      307392a4
  21. May 17, 2023
  22. May 16, 2023
  23. May 10, 2023
  24. May 05, 2023
    • Tai Ly's avatar
      [reference model] Add precise mode · a4d748b0
      Tai Ly authored
      
      
      This adds --precise_mode=1 option to tosa_referece_model,
      which will cause reference model to convert all floating point tensors
      to FP64 tensors and compute all operators accordingly.
      
      Also adds optional -p arguments to test runners tosa_verif_run_tests.py
      and tosa_verif_framework_compiler_runner.py to run tests in precise mode
      
      Signed-off-by: default avatarTai Ly <tai.ly@arm.com>
      Change-Id: I156055216ad61710096497a8fa1a653be2a602a3
      a4d748b0
  25. Apr 26, 2023
  26. Apr 25, 2023
  27. Apr 24, 2023
Loading