Input Scale of Quantized TFLite Model

merkan — Wed, 15 Jan 2025 13:11:33 GMT

I am trying to quantize VGG19 to run it on i.MX 8M Plus NPU and I need multiple convolutional outputs. When I try to quantize it with the following code, input scale is like 3.9e-9 and the responses for different inputs are the same.

def create_vgg19_c(batch_normalization=False, required_layers=None): base_model = VGG19(include_top=False, weights='imagenet', input_shape=(256, 256, 3)) base_model.trainable = True if required_layers is None: required_layers = [2, 5, 8, 13, 18, 19] outputs = [base_model.layers[i].output for i in required_layers] model = Model(inputs=base_model.input, outputs=outputs) return model model = create_vgg19_c() quant_aware_model = tfmot.quantization.keras.quantize_model(model) def representative_data_gen(): _, h, w, _ = quant_aware_model.input_shape samples = 100 for i in range(samples): img_in = np.random.uniform(0, 255, (1, h, w, 3)).astype('float32') img_in = tf.keras.applications.vgg19.preprocess_input(img_in) yield [img_in] converter = tf.lite.TFLiteConverter.from_keras_model(quant_aware_model) converter.optimizations = [tf.lite.Optimize.DEFAULT] converter.representative_dataset = representative_data_gen converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8] converter.experimental_new_converter = True converter.inference_input_type = tf.uint8 converter.inference_output_type = tf.uint8 quantized_tflite_model = converter.convert()

I tried to normalize the values between [-128, 127] for int8 and between [-1,1] for float32. I changed the parameters of the converter, I used just optimizer but scale and same results didn't changed. Also I changed the preprocess function but nothing changed. I want to quantize pretrained VGG19 backbone with specified outputs.

Re: Input Scale of Quantized TFLite Model

Bio_TICFSL — Thu, 16 Jan 2025 14:03:04 GMT

Hello,

Try to use the latest BSP since some problems has ben encounter with VGG19 but is suppose to be fixed in latest BSP.

Regards

topic Input Scale of Quantized TFLite Model in i.MX Processors

Input Scale of Quantized TFLite Model

Re: Input Scale of Quantized TFLite Model