1 # The ModelAccuracyTool-Armnn
3 The `ModelAccuracyTool-Armnn` is a program for measuring the Top 5 accuracy results of a model against an image dataset.
6 1. The model is in .armnn format model file. The `ArmnnConverter` can be used to convert a model to this format.
9 To build ModelAccuracyTool, pass the following options to Cmake:
10 * -DFLATC_DIR=/path/to/flatbuffers/x86build/
11 * -DBUILD_ACCURACY_TOOL=1
12 * -DBUILD_ARMNN_SERIALIZER=1
16 | -h | --help | Display help messages |
17 | -m | --model-path | Path to armnn format model file |
18 | -f | --model-format | The model format. Supported values: caffe, tensorflow, tflite |
19 | -i | --input-name | Identifier of the input tensors in the network separated by comma |
20 | -o | --output-name | Identifier of the output tensors in the network separated by comma |
21 | -d | --data-dir | Path to directory containing the ImageNet test data |
22 | -p | --model-output-labels | Path to model output labels file.
23 | -v | --validation-labels-path | Path to ImageNet Validation Label file
24 | -l | --data-layout ] | Data layout. Supported value: NHWC, NCHW. Default: NHWC
25 | -c | --compute | Which device to run layers on by default. Possible choices: CpuRef, CpuAcc, GpuAcc. Default: CpuAcc, CpuRef |
26 | -r | --validation-range | The range of the images to be evaluated. Specified in the form <begin index>:<end index>. The index starts at 1 and the range is inclusive. By default the evaluation will be performed on all images. |
27 | -b | --blacklist-path | Path to a blacklist file where each line denotes the index of an image to be excluded from evaluation. |
30 <code>./ModelAccuracyTool -m /path/to/model/model.armnn -f tflite -i input -o output -d /path/to/test/directory/ -p /path/to/model-output-labels -v /path/to/file/val.txt -c CpuRef -r 1:100</code>
1.8.13 