TOSA Reference Model 0.80 Release

Conformance test repository is now deprecated, conformance test
generation scripts are in the reference model repository
Deprecated TensorFlow Lite based conformance tests
    Framework tests still generate TFL tests
Add support for new operators
    DIM operator for shape inference
    New unsigned attributes for RESCALE input and output
Improve TOSA flatbuffer compatibility checks
Fixes for test and reference model cleanup
Enable reading/writing native data types for numpy files
Various other cleanup, see the git revision history for complete details

1. 5ffbc94 Remove draft tag for 0.23 release by Eric Kunze · 2 years, 8 months ago v0.23 v0.23.0
2. f3e016f more ERROR_IF fixes by Kevin Cheng · 2 years, 8 months ago
3. 8079480 Fix for tensor_ops.cc by Kevin Cheng · 2 years, 8 months ago
4. c0b24f0 RESIZE test generator updates by Jeremy Johnson · 2 years, 8 months ago
5. fe392ce Changes for 0.23.0 release by Kevin Cheng · 2 years, 8 months ago
6. 1009674 Add version to reference model by Kevin Cheng · 2 years, 8 months ago
7. 8c06a65 Limit tensor values for COND_IF/WHILE_LOOP tests to stop saturation by Jeremy Johnson · 2 years, 8 months ago
8. 6e52866 Fix typo in Concat ERROR_IF by Kevin Cheng · 2 years, 8 months ago
9. 58026d6 Fix pool2d generation and check to match specification by Jeremy Johnson · 2 years, 8 months ago
10. 5d00c69 Add ERROR_IF to control flow ops. by Kevin Cheng · 2 years, 9 months ago
11. cc61be3 More ERROR_IF supports by Kevin Cheng · 2 years, 9 months ago
12. e807aae Add Negative tests for pad, reshape, slice, transpose by Matthew Haddon · 2 years, 9 months ago
13. c4cf037 Add negative testing support to fully_connected, matmul, argmax by Matthew Haddon · 2 years, 9 months ago
14. c202521 Add negative testing support to RESCALE by Matthew Haddon · 2 years, 9 months ago
15. 8a0a663 Remove tosa_serializer.py and use the one from serialization_lib now. by Kevin Cheng · 2 years, 9 months ago
16. 7eb93d7 Catch ERROR_IF on AVG_POOL2D and MAX_POOL2D by Kevin Cheng · 2 years, 9 months ago
17. 6040b4d COND_IF int8, int16 tests by Les Bell · 2 years, 9 months ago
18. b6b59e3 Add negative testing for avg_pool2d, max_pool2d by Matthew Haddon · 2 years, 9 months ago
19. d6ce725 Add negative testing support for reduce operators by Matthew Haddon · 2 years, 9 months ago
20. 03bec73 Fix rank and dtype filtering for ops like conv3d & fully_connected by Jeremy Johnson · 2 years, 9 months ago
21. e4ecdb2 Add negative testing support for ew_unary operators by Matthew Haddon · 2 years, 9 months ago
22. eacff9a Add negative testing support to (most) EW Binary Ops by Matthew Haddon · 2 years, 9 months ago
23. 693ba9e Add ERROR_IF checks for mismatched batch/channel by Matthew Haddon · 2 years, 9 months ago
24. 1c00b71 Separate positive and negative test generation and refactor by Matthew Haddon · 2 years, 9 months ago
25. 960985a Fix shape generation with num-const-inputs-concat option by Jeremy Johnson · 2 years, 9 months ago
26. ec5586c Fix reduction ERROR_IF cases by Kevin Cheng · 2 years, 9 months ago
27. 478101b Couple of reference model fixes by Kevin Cheng · 2 years, 9 months ago
28. 848efb4 Add shared ERROR_IF statements by Matthew Haddon · 2 years, 10 months ago
29. 17e9202 Fix CONST test. by Kevin Cheng · 2 years, 9 months ago
30. c72b59c Fixes to pass NEGATE op test. by Kevin Cheng · 2 years, 9 months ago
31. 903763c Add SUBGRAPH_ERROR_IF() to catch graph-level error. by Kevin Cheng · 2 years, 9 months ago
32. 7fb8fa1 Remove duplicate output tensor in cond_if_binary test by Kevin Cheng · 2 years, 9 months ago
33. 269e898 Remove ReluN op. by Kevin Cheng · 2 years, 9 months ago
34. c42addc Removing rank 0 broadcast in binary op. by Kevin Cheng · 2 years, 9 months ago
35. 6097c3d Op that violates rank requirement now runs to the end and return ERROR instead of bailing out. by Kevin Cheng · 2 years, 9 months ago
36. e86fd34 Add ERROR_IF support for RESIZE by Matthew Haddon · 2 years, 10 months ago
37. 7aa69f4 Extended tests for 2D/3D tensor functions by Les Bell · 2 years, 9 months ago
38. 6132cfe Add stride larger than dimension error_if check for resize by Matthew Haddon · 2 years, 9 months ago
39. 7e7fccd Unit test runner ergonomics by Jared Smolens · 2 years, 9 months ago
40. 1918e8a Add maximum dimension check ERROR_IF in RESIZE. by Kevin Cheng · 2 years, 10 months ago
41. c94e63d Compatibility with flatbuffers 1.12.0 and 2.0.0 by Jared Smolens · 2 years, 10 months ago
42. f414b3c Generate more CONV3D tests by Les Bell · 2 years, 10 months ago
43. 1533b85 Implement Conv3D kernel. by Kevin Cheng · 2 years, 10 months ago
44. 93a1628 Rename attribute: Pool2d, Conv2d, TransposeConv2d -> Pool, Conv, TransposeConv by Kevin Cheng · 2 years, 10 months ago
45. e3d6a8f Add a top level license file by Eric Kunze · 2 years, 10 months ago
46. ef509a4 Fix for ADD/SUB saturation in tests by Jeremy Johnson · 2 years, 10 months ago
47. b227ae5 Fix while_loop test. by Kevin Cheng · 2 years, 10 months ago
48. 9034747 Add saturation REQUIREs for ADD,SUB,MUL,INTDIV by Jeremy Johnson · 2 years, 10 months ago
49. b724efc Remove invalid tests from test generator by Matthew Haddon · 2 years, 10 months ago
50. 7456709 Allow user to specify test type generated by Matthew Haddon · 3 years ago
51. 4b2881a Fix batch size if target shape set for SCATTER operator by Matthew Haddon · 2 years, 10 months ago
52. 459443c Rename DIV operator to INTDIV by Matthew Haddon · 2 years, 10 months ago
53. 82ad4d6 Set TILE multiple to one if input dimension is large by Matthew Haddon · 2 years, 10 months ago
54. a9d5395 Restore expectedFailure to test description files by Jared Smolens · 2 years, 10 months ago
55. acb550f Replace node level check ASSERT_MSG_NODE()/FATAL_ERROR_NODE() with REQUIRE() or ERROR_IF() by Kevin Cheng · 3 years ago
56. 68e7aee Make MATMUL output shape random by Matthew Haddon · 2 years, 11 months ago
57. 818ab90 Produce Concat tests with multiple input tensors by Matthew Haddon · 3 years ago
58. a901740 Support int4 weights read. Added conv2d int8xint4 in test generation. by Kevin Cheng · 3 years ago
59. 7ffccce test gen PAD agPad fix to cover all pad values by Les Bell · 3 years ago
60. cac4ee9 Add support for UINT8 by Matthew Haddon · 3 years ago
61. 2a29dc6 fully_connected test OC independent of input shape by Les Bell · 3 years ago
62. 33d837e fix output type for resize in test gen by Les Bell · 2 years, 11 months ago
63. 30e4680 fix quantization zero-point generation by Les Bell · 3 years ago
64. 18e2666 Fix random INT4 and INT8 dtype ranges and clamp attrs by Jeremy Johnson · 3 years ago
65. a44ac5e Fix bug causing test generator to create unused input tensor by Matthew Haddon · 3 years ago
66. f54d8a2 Add INT8 table operator support to test generator. by Jeremy Johnson · 3 years ago
67. 16aac57 Update serialization_lib hash. by Kevin Cheng · 3 years ago
68. 43e3719 Make operator tests follow consistent naming scheme by Matthew Haddon · 3 years ago
69. 97eb75f Allow selection of higher rank tests using --target-rank by Jeremy Johnson · 3 years ago
70. 5fc4e68 Fix bug causing reshape rank not to match test description. by Matthew Haddon · 3 years ago
71. 2ad047d Fix bug causing identical reshape permutations by Matthew Haddon · 3 years ago
72. d593414 Adding option -Coutput_dir= to control output location. by Kevin Cheng · 3 years ago
73. a618557 Fix transpose test gen of permutations & rank by Jeremy Johnson · 3 years ago
74. 82507d7 Update to use new serialization_lib API. by Kevin Cheng · 3 years ago
75. 2d60f00 adding batch dimension to MatMul. by Kevin Cheng · 3 years, 1 month ago
76. cd79f0e Rewrite model frontend to be json-driven. by Kevin Cheng · 3 years, 1 month ago
77. 571f718 Support 8-bit TABLE op. by Kevin Cheng · 3 years, 1 month ago
78. 47315e1 Fix typo in DIV unit test generator by Kevin Cheng · 3 years, 2 months ago
79. 14d7f7a Update to v0.22.0 by Kevin Cheng · 3 years, 2 months ago
80. d267dd9 Regenerate examples/ tests by Kevin Cheng · 3 years, 2 months ago
81. 9257fd5 Fix OpMul for 32-bit x 32-bit inputs by Kevin Cheng · 3 years, 3 months ago
82. 0f87c95 Support 16-bit Rescale by Kevin Cheng · 3 years, 3 months ago
83. ad15dfa Concat takes variadic inputs by Kevin Cheng · 3 years, 4 months ago
84. 573ecd4 Re-order TOSA unit tests to match the spec ordering by Jared Smolens · 3 years, 4 months ago
85. 989cb05 Support mixed-precision input tensors for TOSA unit test. by Kevin Cheng · 3 years, 2 months ago
86. 550ccc5 Replace serialization/ and verif/ with MLPlatform's serialization_lib submodule by Kevin Cheng · 3 years, 4 months ago
87. cf6224e Fix bug that NegateOp doesn't clip output value by Kevin Cheng · 3 years, 2 months ago
88. 2a76ad2 Update DTypes for TOSA ops, test rig fixes by Jared Smolens · 3 years, 4 months ago
89. df86269 Fix operator initialization bug when rank/dtype fails to initialize with Usage arrays by Kevin Cheng · 3 years, 4 months ago
90. 3a47857 Remove AINT8 by Kevin Cheng · 3 years, 5 months ago
91. e2e13cd TOSA Unit Test updates by Jared Smolens · 3 years, 5 months ago
92. 4025315 Numpy utility supports scalar (rank 0) .npy by Kevin Cheng · 3 years, 6 months ago
93. 77d0f76 Update reference model/serialization library to 0.21.0 with unit tests added/updated by Kevin Cheng · 3 years, 7 months ago
94. aee1fac Implement and add unit tests for MUL and ARITHMETIC_RIGHT_SHIFT by Kevin Cheng · 3 years, 8 months ago
95. 99bea14 Update apply_scale_32() by Kevin Cheng · 3 years, 8 months ago
96. e5e2676 Initial checkin of TOSA reference_model and tests by Eric Kunze · 3 years, 9 months ago
97. 88b7860 Initial empty repository by Eric Kunze · 3 years, 9 months ago