lovodkin93

@Xhark Ok, I think I understand. So I have a followup question - is the validation done using the quantized version of the model (with the fake-quant weights), or is...

@Xhark So I tried what you suggested, and it appears the `quantizer` parameters (the second one in q_aware_model.layers[2]._weight_vars[0]) is None. This is weird, given the model is wrapped in the...

@Xhark So after checking, it appears that when trying to access the quantizer after reloading the model's parameters, namely: ``` checkpoint_path="/home/taaviv/dl-quantization/post_train_quant/best_checkpoint/cp.ckpt" model = tf.keras.models.load_model(checkpoint_path) unquantized_weight, quantizer, quantizer_vars = model.layers[2]._weight_vars[0] ```...

@Xhark What I want is to have quantized weights during inference. In fact, I am comparing it to post-train quantization, therefore I need the weights to be quantized. So I...

sure thing: https://colab.research.google.com/drive/1o9hbgv4Toc59DTkM3h5PaBY1G1duiIdE?usp=sharing Thanks!

So I tried to replace every `x = Activation(activations.relu)(x)` line with `x = Activation(ReLU)(x)`, and now I get the following error (which is the reason I worked with `x =...

Hello, I have tried all the solutions suggeted in this issue, but I keep getting that same error. I have set my variables as follows: ``` export LD_LIBRARY_PATH=/data/anaconda/envs/resnet50_pytorch2/lib/python3.6/site-packages/aimet_common/x86_64-linux-gnu:/data/anaconda/envs/resnet50_pytorch2/lib/python3.6/site-packages/aimet_common/:/data/anaconda/envs/resnet50_pytorch2/lib/:$LD_LIBRARY_PATH export PYTHONPATH=/data/anaconda/envs/resnet50_pytorch2/lib/python3.6/site-packages/aimet_common/x86_64-linux-gnu:$PYTHONPATH...