3 The `ArmnnQuantizer` is a program for loading a 32-bit float network into ArmNN and converting it into a quantized asymmetric 8-bit or quantized symmetric 16-bit network.
4 It supports static quantization by default, dynamic quantization is enabled if CSV file of raw input tensors is provided. Run the program with no arguments to see command-line help.
6 **NOTE**: The ArmnnQuantizer is deprecated in Arm NN 21.02 and will be removed in 21.05.
10 | -h | --help | Display help messages |
11 | -f | --infile | Input file containing float 32 ArmNN Input Graph |
12 | -s | --scheme | Quantization scheme, "QAsymm8" or "QSymm16". Default value: QAsymm8 |
13 | -c | --csvfile | CSV file containing paths for raw input tensors for dynamic quantization. If unset, static quantization is used |
14 | -p | --preserve-data-type | Preserve the input and output data types. If unset, input and output data types are not preserved |
15 | -d | --outdir | Directory that output file will be written to |
16 | -o | --outfile | ArmNN output file name |
19 <code>./ArmnnQuantizer -f /path/to/armnn/input/graph/ -s "QSymm16" -c /path/to/csv/file -p 1 -d /path/to/output -o outputFileName</code>
1.8.13 