tensor1to5

Not loading encodings for quantizer: ****** as it is disabled in Tensorflow framework

1

Hi, I have tried the following code that **use the function sim.load_encoding_to_sim to achieve mixed precision quantization of operators** : ``` from aimet_tensorflow.keras.quantsim import QuantizationSimModel from aimet_common.defs import QuantScheme sim...

tf.matmul operator does not support

20

Using the AIMET scheme to quantify the model, but encountering a problem: the tf.matmul operator does not support it

can not find AimetOnnx-onnx_cpu_1.27.0-cp38-cp38-linux_x86_64.whl, then compiled and packaged the whl

2

We can not find AimetOnnx-onnx_cpu_1.27.0-cp38-cp38-linux_x86_64.whl in https://github.com/quic/aimet/releases. > Aimet-tf_cpu_1.27.0-cp38-cp38-linux_x86_64.whl > 6.57 KB 2023-07-28T19:14:47Z > Aimet-tf_gpu_1.27.0-cp38-cp38-linux_x86_64.whl > 6.57 KB 2023-07-28T19:14:33Z > Aimet-torch_cpu_1.27.0-cp38-cp38-linux_x86_64.whl > 6.61 KB 2023-07-28T19:14:53Z > Aimet-torch_gpu_1.27.0-cp38-cp38-linux_x86_64.whl > 6.62 KB...

Hi，we use the following code ``` from aimet_tensorflow.keras.quantsim import QuantizationSimModel from aimet_common.defs import QuantScheme sim = QuantizationSimModel(model=model, quant_scheme=QuantScheme.post_training_tf, rounding_mode="nearest", default_output_bw=8, default_param_bw=8) ``` The tf.matmul operator in the model is not...