Duplicated quantization flag assignment makes impossible to create a int8 quantized model

[juandoso]

Convert_Darknet_YOLO_to_TensorFlow/convert_tflite.py

Lines 39 to 41 in 149ff02

	converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8]
	converter.optimizations = [tf.lite.Optimize.DEFAULT]
	converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS, tf.lite.OpsSet.SELECT_TF_OPS]

The second assignment to converter.target_spec.supported_ops supersedes the first one that contains the int8 flag