tree 2924e4b32206617d28dc8dfcc4b8e3007db077f9
parent be11bd79e4a8b28c9ee92c6f02ca0e85414fb768
author RJ Ascani <rjascani@google.com> 1716955542 -0700
committer GitHub <noreply@github.com> 1716955542 +0000
gpgsig -----BEGIN PGP SIGNATURE-----
 
 wsFcBAABCAAQBQJmVqmWCRC1aQ7uu5UhlAAAavEQAHZ1mq4NSlkx468fwf1rjg0I
 MTLGshEflo8pIEvbBp5Rpk6mmnn51odlDX0YA450HtY+B1jcUe7OyIX6fFvlqV1P
 e7Kf+yTJkwjx8lf8dGzgSBgs+gbgyh4tRwdW4jBMHQbaz5jrtSEsKjh0P5VBihXT
 ogMUCEb692d9GjlwYKgJQbBoU4xnv5QPpCqKY9yngwwqc2P2l3WlJbSywCYHvOt3
 M5p7Q1k03/t6soiJXfJsD91cNMyks/A/qwZmo/iM0kRdhWD3Ee7kPcAOHOW347Aw
 p1P3Y43NydvnHzf5kC3czHUIRXMuftrAaEOZg4oG5zkTcOM+i5+MzKD9cMABh/Xg
 if2DRNo77S2CPjUZkxep+uGfYHTIRtbU8YqL5qCI12bfcDdLYcZz/8Cfx1nKYscp
 2MAERMADvDKTiaBWl4buOBzeA99jhWfRJ05ErvncRrKvqqtEUmh88RqIW69ECdUi
 OLGdN5e7CIcLgGhM7mB6nyTkcGIPJwe4/2N8RJSGID2sIDPMM/hD0jtsZSTNjY57
 1C4L+MK/ncRgJuygvsvvm7h3a2Gz9hmuPRnAKB1J8bJ/8uExjrt89lwFtd/3e2p4
 86yXcW1OjJ7Uy0LN7uzy1DAEDVfyhfDIPyvVejcZooErzizhYCwcFZZNZUXRQNyY
 932lsdXAb38+VdqR8oiD
 =g1Cl
 -----END PGP SIGNATURE-----
 

Fail per-channel quantized FullyConnected layers (#2602)

The TFLiteConverter recently switched over to using per-channel quantization for all Dense/FullyConnected layers. TFLite-Micro does not yet have support for this, and was using incorrect quantization parameters for FullyConnected layers on newly converted models. Unsurprisingly, this leads to invalid output.

While we intend to add per-channel quantization support for FullyConnected, this PR adds a runtime check for per-channel quantization until it can be supported by individual kernels. If you encounter this runtime error, you can disable the new Converter behavior by setting:

`TfLiteConverter._experimental_disable_per_channel_quantization_for_dense_layers = True` https://github.com/tensorflow/tensorflow/blob/377f47694fa790e98db6665b9adecde00b5e0d68/tensorflow/lite/python/lite.py#L674

BUG=b/324385802