• Home
Name Date Size #Lines LOC

..--

test/03-May-2024-140105

ArmNNQuantizerMain.cppD03-May-20243.5 KiB9982

CommandLineProcessor.cppD03-May-20244.9 KiB186151

CommandLineProcessor.hppD03-May-20242 KiB5331

QuantizationDataSet.cppD03-May-20244.9 KiB174137

QuantizationDataSet.hppD03-May-20241.8 KiB5537

QuantizationInput.cppD03-May-20242.6 KiB10382

QuantizationInput.hppD03-May-20241.5 KiB5425

README.mdD03-May-20241.2 KiB1914

README.md

1# The ArmnnQuantizer
2
3The `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.
4It 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.
5
6
7|Cmd:|||
8| ---|---|---|
9| -h | --help               | Display help messages |
10| -f | --infile             | Input file containing float 32 ArmNN Input Graph |
11| -s | --scheme             | Quantization scheme, "QAsymm8" or "QSymm16". Default value: QAsymm8 |
12| -c | --csvfile            | CSV file containing paths for raw input tensors for dynamic quantization. If unset, static quantization is used |
13| -p | --preserve-data-type | Preserve the input and output data types. If unset, input and output data types are not preserved |
14| -d | --outdir             | Directory that output file will be written to |
15| -o | --outfile            | ArmNN output file name |
16
17Example usage: <br>
18<code>./ArmnnQuantizer -f /path/to/armnn/input/graph/ -s "QSymm16" -c /path/to/csv/file -p 1 -d /path/to/output -o outputFileName</code>
19