tree f40ba94c74db1538a7b42b0c9f2156f081d815ab
parent 17d0e7f6bb4edb70acaa69ddb6734cbb9ebfe49d
author David Davis <ddavis-2015@users.noreply.github.com> 1704234156 -0800
committer GitHub <noreply@github.com> 1704234156 +0000
gpgsig -----BEGIN PGP SIGNATURE-----
 
 wsBcBAABCAAQBQJllIysCRBK7hj4Ov3rIwAAbgYIAG4VOPi/+u9lRIUV5sRo0kdj
 xH/SGAc4v3jymZyIFE3iMQAubg4GIfpL+I/PQoV/pfzIiRD31jTuhTSu7scBJ3fB
 +0v6ZPG6/otXSrn/6/IqaQ7+fevZIHGZ9jSjbihGafkjqnnzjonsd5TauQLfWRZJ
 eHjanHUQF6jqOG3O9fsXInTW7bIEENhxW9r3ietOfYykOOjn7KosX2D87Mv0qGyN
 xlyaVPcTsXXNDCf+sYxyJZkHeWSNur39MFs9HFs3xLtvKNxpPnTZv3baMXLZjRyU
 hmKsRfikuJbw+6favE4a2C4gi9RnsSAXAqIVGzIKXSt3GXQ/wKyWaMq+vVxIovg=
 =ECGj
 -----END PGP SIGNATURE-----
 

Compute output shapes for some kernels (#2356)

@tensorflow/micro

Update the output tensor shape during prepare phase when the computed shape does not match the shape in the flatbuffer.

Kernels:
- BATCH_TO_SPACE_ND
- SPACE_TO_BATCH_ND
- CONV
- RESHAPE
- EXPAND_DIMS
- DEPTHWISE_CONV

Update CMSIS_NN and ARC_MLI optimized kernels.
Add additional tests from TfLite for BATCH_TO_SPACE_ND and SPACE_TO_BATCH_ND.
Update existing tests.
Add tests for Keras model using convolution with dilation > 1.

Update memory_arena_threshold_test to increase total, tail, and persistent allocation sizes:
- Add 20 bytes for CONV output shape
- Add 15 bytes for arena allocation alignment
- x2 convolution layers

Update micro_speech_test arena size as per description in C++ code.

See #2319 for additional details.

Resolves [b/317362237](https://issuetracker.google.com/317362237)

bug=fixes #2368 #1646 #1629 #1231 #2338 #2319