quantized TFLITE model support #650
muzafferkal
started this conversation in
General
Replies: 1 comment
-
|
Not supported and I am not aware of anyone working on it. FlatBuffers are not that easy to parse, and in most cases users have access to original model that can be quantized with QKeras rather than TFLite for better compatibility with hls4ml. We do welcome contributions if anyone is interested in contributing support for .tflite files. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hi all,
I saw a PR about QONNX support and I was wondering what level of quantized TFLITE support there is.
Thanks
Beta Was this translation helpful? Give feedback.
All reactions