From fd627ffaec8fd8801d980b4c91ee7c0607ab6aaf Mon Sep 17 00:00:00 2001 From: Jan Eilers Date: Thu, 25 Feb 2021 17:44:00 +0000 Subject: IVGCVSW-5687 Update Doxygen Docu * Update Doxygen Documentation for 21.02 release Signed-off-by: Jan Eilers Change-Id: I9ed2f9caab038836ea99d7b378d7899fe431a4e5 --- ...racy_tool-_armnn_2_r_e_a_d_m_e_8md_source.xhtml | 113 +++++++++++++++++++++ 1 file changed, 113 insertions(+) create mode 100644 21.02/tests_2_model_accuracy_tool-_armnn_2_r_e_a_d_m_e_8md_source.xhtml (limited to '21.02/tests_2_model_accuracy_tool-_armnn_2_r_e_a_d_m_e_8md_source.xhtml') diff --git a/21.02/tests_2_model_accuracy_tool-_armnn_2_r_e_a_d_m_e_8md_source.xhtml b/21.02/tests_2_model_accuracy_tool-_armnn_2_r_e_a_d_m_e_8md_source.xhtml new file mode 100644 index 0000000000..d5fa8143b6 --- /dev/null +++ b/21.02/tests_2_model_accuracy_tool-_armnn_2_r_e_a_d_m_e_8md_source.xhtml @@ -0,0 +1,113 @@ + + + + + + + + + + + + + +ArmNN: tests/ModelAccuracyTool-Armnn/README.md Source File + + + + + + + + + + + + + + + + +
+
+ + + + ArmNN + + + +
+
+  21.02 +
+
+
+ + + + + + + +
+
+ +
+
+
+ +
+ +
+
+ + +
+ +
+ +
+
+
tests/ModelAccuracyTool-Armnn/README.md
+
+
+Go to the documentation of this file.
1 # The ModelAccuracyTool-Armnn
2 
3 The `ModelAccuracyTool-Armnn` is a program for measuring the Top 5 accuracy results of a model against an image dataset.
4 
5 Prerequisites:
6 1. The model is in .armnn format model file. The `ArmnnConverter` can be used to convert a model to this format.
7 
8 Build option:
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
13 
14 |Cmd:|||
15 | ---|---|---|
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. |
28 
29 Example usage: <br>
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>
+
+ + + + -- cgit v1.2.1