diff options
author | Cisco Cervellera <cisco.cervellera@arm.com> | 2021-08-02 09:32:07 +0100 |
---|---|---|
committer | Isabella Gottardi <isabella.gottardi@arm.com> | 2021-08-03 16:10:16 +0100 |
commit | f085fa5a2859178741f39563b4d9d68ca41d916a (patch) | |
tree | 62fd8411c63a853be4c32683a3ada0b6affb0399 /docs/use_cases | |
parent | 81c4c9178598e5c26af7373eca67842a8fe4179f (diff) | |
download | ml-embedded-evaluation-kit-f085fa5a2859178741f39563b4d9d68ca41d916a.tar.gz |
MLECO-2051: Work with Corstone-300 + Ethos-U65
Change-Id: I64ab930a1de5210f435f91bed7600a700581946f
Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com>
Reviewed-on: https://eu-gerrit-2.euhpc.arm.com/c/ml/ecosystem/ml-embedded-evaluation-kit/+/459126
Tested-by: mlecosys <mlecosys@arm.com>
Tested-by: George Gekov <george.gekov@arm.com>
Reviewed-by: George Gekov <george.gekov@arm.com>
Reviewed-by: Kshitij Sisodia <kshitij.sisodia@arm.com>
Diffstat (limited to 'docs/use_cases')
-rw-r--r-- | docs/use_cases/ad.md | 27 | ||||
-rw-r--r-- | docs/use_cases/asr.md | 27 | ||||
-rw-r--r-- | docs/use_cases/img_class.md | 29 | ||||
-rw-r--r-- | docs/use_cases/inference_runner.md | 29 | ||||
-rw-r--r-- | docs/use_cases/kws.md | 29 | ||||
-rw-r--r-- | docs/use_cases/kws_asr.md | 26 |
6 files changed, 86 insertions, 81 deletions
diff --git a/docs/use_cases/ad.md b/docs/use_cases/ad.md index 58272db..1a16a83 100644 --- a/docs/use_cases/ad.md +++ b/docs/use_cases/ad.md @@ -10,8 +10,8 @@ - [Build process](#build-process) - [Add custom input](#add-custom-input) - [Add custom model](#add-custom-model) - - [Setting-up and running Ethos-U55 Code Sample](#setting-up-and-running-ethos-u55-code-sample) - - [Setting up the Ethos-U55 Fast Model](#setting-up-the-ethos-u55-fast-model) + - [Setting-up and running Ethos-U55 Code Sample](#setting-up-and-running-ethos-u-npu-code-sample) + - [Setting up the Ethos-U Fast Model](#setting-up-the-ethos-u-fast-model) - [Starting Fast Model simulation](#starting-fast-model-simulation) - [Running Anomaly Detection](#running-anomaly-detection) @@ -65,12 +65,12 @@ In addition to the already specified build option in the main documentation, the - `ad_MODEL_TFLITE_PATH` - Path to the NN model file in the `TFLite` format. The model is then processed and included in the application `axf` file. The default value points to one of the delivered set of models. - Note that the parameters `ad_LABELS_TXT_FILE`, `TARGET_PLATFORM`, and `ETHOS_U55_ENABLED` must be aligned with the + Note that the parameters `ad_LABELS_TXT_FILE`, `TARGET_PLATFORM`, and `ETHOS_U_NPU_ENABLED` must be aligned with the chosen model. In other words: - - If `ETHOS_U55_ENABLED` is set to `On` or `1`, then the NN model is assumed to be optimized. The model naturally + - If `ETHOS_U_NPU_ENABLED` is set to `On` or `1`, then the NN model is assumed to be optimized. The model naturally falls back to the Arm® *Cortex®-M* CPU if an unoptimized model is supplied. - - if `ETHOS_U55_ENABLED` is set to `Off` or `0`, the NN model is assumed to be unoptimized. Supplying an optimized + - if `ETHOS_U_NPU_ENABLED` is set to `Off` or `0`, the NN model is assumed to be unoptimized. Supplying an optimized model in this case results in a runtime error. - `ad_FILE_PATH`: Path to the directory containing audio files, or a path to single WAV file, to be used in the @@ -134,6 +134,7 @@ For additional information, please refer to: - [Using Arm Compiler](../sections/building.md#using-arm-compiler) - [Configuring the build for simple_platform](../sections/building.md#configuring-the-build-for-simple_platform) - [Working with model debugger from Arm Fast Model Tools](../sections/building.md#working-with-model-debugger-from-arm-fast-model-tools) +- [Building for different Ethos-U NPU variants](../sections/building.md#building-for-different-ethos-u-npu-variants) > **Note:** If re-building with changed parameters values, we recommend that you clean the build directory and then > re-run the CMake command. @@ -222,7 +223,7 @@ After compiling, your custom inputs have now replaced the default ones in the ap The application performs inference using the model pointed to by the CMake parameter ``ad_MODEL_TFLITE_PATH``. -> **Note:** If you want to run the model using an *Ethos-U55*, ensure that your custom model has been successfully run +> **Note:** If you want to run the model using an *Ethos-U*, ensure that your custom model has been successfully run > through the Vela compiler *before* continuing. Please refer to this section for more help: > [Optimize model with Vela compiler](../sections/building.md#Optimize-custom-model-with-Vela-compiler). @@ -257,13 +258,13 @@ After compiling, your custom model has now replaced the default one in the appli ## Setting-up and running Ethos-U55 Code Sample -### Setting up the Ethos-U55 Fast Model +### Setting up the Ethos-U Fast Model The FVP is available publicly from [Arm Ecosystem FVP downloads](https://developer.arm.com/tools-and-software/open-source-software/arm-platforms-software/arm-ecosystem-fvps). -For the *Ethos-U55* evaluation, please download the MPS3 version of the Arm® *Corstone™-300* model that contains both -the *Ethos-U55* and *Cortex-M55*. The model is currently only supported on Linux-based machines. +For the *Ethos-U* evaluation, please download the MPS3 based version of the Arm® *Corstone™-300* model that contains *Cortex-M55* +and offers a choice of the *Ethos-U55* and *Ethos-U65* processors. To install the FVP: @@ -272,7 +273,7 @@ To install the FVP: - Run the install script in the extracted package: ```commandline -.FVP_Corstone_SSE-300_Ethos-U55.sh +./FVP_Corstone_SSE-300.sh ``` - Follow the instructions to install the FVP to the required location. @@ -409,7 +410,7 @@ chosen anomaly threshold. Therefore, an anomaly was detected with the machine in The profiling section of the log shows that for each inference. For the last inference, the profiling reports: -- *Ethos-U55* PMU report: +- *Ethos-U* PMU report: - 1,081,634 total cycle: The number of NPU cycles @@ -418,12 +419,12 @@ The profiling section of the log shows that for each inference. For the last inf - 626 idle cycles: number of cycles for which the NPU was idle - 628,122 AXI0 read beats: The number of AXI beats with read transactions from AXI0 bus. AXI0 is the bus where - Ethos-U55 NPU reads and writes to the computation buffers, activation buf, or tensor arenas. + *Ethos-U* NPU reads and writes to the computation buffers, activation buf, or tensor arenas. - 135,087 AXI0 write beats: The number of AXI beats with write transactions to AXI0 bus. - 62,870 AXI1 read beats: The number of AXI beats with read transactions from AXI1 bus. AXI1 is the bus where - Ethos-U55 NPU reads the model. So, read-only. + *Ethos-U* NPU reads the model. So, read-only. - For FPGA platforms, a CPU cycle count can also be enabled. However, do not use cycle counters for FVP, as the CPU model is not cycle-approximate or cycle-accurate. diff --git a/docs/use_cases/asr.md b/docs/use_cases/asr.md index 162d9e9..fb62afa 100644 --- a/docs/use_cases/asr.md +++ b/docs/use_cases/asr.md @@ -10,8 +10,8 @@ - [Build process](#build-process) - [Add custom input](#add-custom-input) - [Add custom model](#add-custom-model) - - [Setting-up and running Ethos-U55 Code Samples](#setting-up-and-running-ethos-u55-code-samples) - - [Setting up the Ethos-U55 Fast Model](#setting-up-the-ethos-u55-fast-model) + - [Setting up and running Ethos-U NPU code sample](#setting-up-and-running-ethos-u-npu-code-sample) + - [Setting up the Ethos-U Fast Model](#setting-up-the-ethos-u-fast-model) - [Starting Fast Model simulation](#starting-fast-model-simulation) - [Running Automatic Speech Recognition](#running-automatic-speech-recognition) @@ -110,11 +110,11 @@ adds: - `asr_MODEL_TFLITE_PATH` - The path to the NN model file in `TFLite` format. The model is processed and then included into the application `axf` file. The default value points to one of the delivered set of models. Note that the - parameters `asr_LABELS_TXT_FILE`,`TARGET_PLATFORM`, and `ETHOS_U55_ENABLED` must be aligned with the chosen model. In + parameters `asr_LABELS_TXT_FILE`,`TARGET_PLATFORM`, and `ETHOS_U_NPU_ENABLED` must be aligned with the chosen model. In other words: - - If `ETHOS_U55_ENABLED` is set to `On` or `1`, then the NN model is assumed to be optimized. The model naturally + - If `ETHOS_U_NPU_ENABLED` is set to `On` or `1`, then the NN model is assumed to be optimized. The model naturally falls back to the Arm® *Cortex®-M* CPU if an unoptimized model is supplied. - - If `ETHOS_U55_ENABLED` is set to `Off` or `0`, then the NN model is assumed to be unoptimized. Supplying an + - If `ETHOS_U_NPU_ENABLED` is set to `Off` or `0`, then the NN model is assumed to be unoptimized. Supplying an optimized model in this case results in a runtime error. - `asr_FILE_PATH`: The path to the directory containing audio files, or a path to single WAV file, to be used in the @@ -181,6 +181,7 @@ For further information, please refer to: - [Using Arm Compiler](../sections/building.md#using-arm-compiler) - [Configuring the build for simple_platform](../sections/building.md#configuring-the-build-for-simple_platform) - [Working with model debugger from Arm Fast Model Tools](../sections/building.md#working-with-model-debugger-from-arm-fast-model-tools) +- [Building for different Ethos-U NPU variants](../sections/building.md#building-for-different-ethos-u-npu-variants) > **Note:** If re-building with changed parameters values, we recommend that you clean the build directory and re-run > the CMake command. @@ -271,7 +272,7 @@ After compiling, your custom inputs have now replaced the default ones in the ap The application performs inference using the model pointed to by the CMake parameter `MODEL_TFLITE_PATH`. -> **Note:** If you want to run the model using an *Ethos-U55*, ensure that your custom model has been successfully run +> **Note:** If you want to run the model using an *Ethos-U*, ensure that your custom model has been successfully run > through the Vela compiler *before* continuing. For further information: [Optimize model with Vela compiler](../sections/building.md#Optimize-custom-model-with-Vela-compiler). @@ -316,15 +317,15 @@ custom_model_after_vela.tflite.cc After compiling, your custom model has now replaced the default one in the application. -## Setting-up and running Ethos-U55 Code Samples +## Setting up and running Ethos-U NPU code sample -### Setting up the Ethos-U55 Fast Model +### Setting up the Ethos-U Fast Model The FVP is available publicly from [Arm Ecosystem FVP downloads](https://developer.arm.com/tools-and-software/open-source-software/arm-platforms-software/arm-ecosystem-fvps). -For the *Ethos-U55* evaluation, please download the MPS3 version of the Arm® *Corstone™-300* model that contains both -the *Ethos-U55* and *Cortex-M55*. The model is currently only supported on Linux-based machines. +For the *Ethos-U* evaluation, please download the MPS3 based version of the Arm® *Corstone™-300* model that contains *Cortex-M55* +and offers a choice of the *Ethos-U55* and *Ethos-U65* processors. To install the FVP: @@ -333,7 +334,7 @@ To install the FVP: - Run the install script in the extracted package: ```commandline -./FVP_Corstone_SSE-300_Ethos-U55.sh +./FVP_Corstone_SSE-300.sh ``` - Follow the instructions to install the FVP to the required location. @@ -462,7 +463,7 @@ multiple inferences were required to cover the whole clip. The profiling section of the log shows that for the first inference: -- *Ethos-U55* PMU report: +- *Ethos-U* PMU report: - 28,451,172 total cycle: The number of NPU cycles. @@ -471,7 +472,7 @@ The profiling section of the log shows that for the first inference: - 476 idle cycles: The number of cycles for which the NPU was idle. - 6,564,262 AXI0 read beats: The number of AXI beats with read transactions from the AXI0 bus. AXI0 is the bus where - the *Ethos-U55* NPU reads and writes to the computation buffers, activation buf, or tensor arenas. + - the *Ethos-U* NPU reads and writes to the computation buffers, activation buf, or tensor arenas. - 928,889 AXI0 write beats: The number of AXI beats with write transactions to the AXI0 bus. diff --git a/docs/use_cases/img_class.md b/docs/use_cases/img_class.md index 237a972..9423a4e 100644 --- a/docs/use_cases/img_class.md +++ b/docs/use_cases/img_class.md @@ -8,8 +8,8 @@ - [Build process](#build-process) - [Add custom input](#add-custom-input) - [Add custom model](#add-custom-model) - - [Setting up and running Ethos-U55 code sample](#setting-up-and-running-ethos-u55-code-sample) - - [Setting up the Ethos-U55 Fast Model](#setting-up-the-ethos-u55-fast-model) + - [Setting up and running Ethos-U NPU code sample](#setting-up-and-running-ethos-u-npu-code-sample) + - [Setting up the Ethos-U Fast Model](#setting-up-the-ethos-u-fast-model) - [Starting Fast Model simulation](#starting-fast-model-simulation) - [Running Image Classification](#running-image-classification) @@ -36,12 +36,12 @@ specifies: - `img_class_MODEL_TFLITE_PATH` - The path to the NN model file in the `TFLite` format. The model is then processed and included in the application `axf` file. The default value points to one of the delivered set of models. - Note that the parameters `img_class_LABELS_TXT_FILE`,`TARGET_PLATFORM`, and `ETHOS_U55_ENABLED` must be aligned with + Note that the parameters `img_class_LABELS_TXT_FILE`,`TARGET_PLATFORM`, and `ETHOS_U_NPU_ENABLED` must be aligned with the chosen model. In other words: - - If `ETHOS_U55_ENABLED` is set to `On` or `1`, then the NN model is assumed to be optimized. The model naturally + - If `ETHOS_U_NPU_ENABLED` is set to `On` or `1`, then the NN model is assumed to be optimized. The model naturally falls back to the Arm® *Cortex®-M* CPU if an unoptimized model is supplied. - - if `ETHOS_U55_ENABLED` is set to `Off` or `0`, the NN model is assumed to be unoptimized. Supplying an optimized + - if `ETHOS_U_NPU_ENABLED` is set to `Off` or `0`, the NN model is assumed to be unoptimized. Supplying an optimized model in this case results in a runtime error. - `img_class_FILE_PATH`: The path to the directory containing the images, or a path to a single image file, that is to @@ -100,6 +100,7 @@ For further information, please refer to: - [Using Arm Compiler](../sections/building.md#using-arm-compiler) - [Configuring the build for simple_platform](../sections/building.md#configuring-the-build-for-simple_platform) - [Working with model debugger from Arm Fast Model Tools](../sections/building.md#working-with-model-debugger-from-arm-fast-model-tools) +- [Building for different Ethos-U NPU variants](../sections/building.md#building-for-different-ethos-u-npu-variants) > **Note:** If re-building with changed parameters values, we recommend that you clean the build directory and re-run > the CMake command. @@ -193,7 +194,7 @@ of any image does not match `IMAGE_SIZE`, then it is rescaled and padded so that The application performs inference using the model pointed to by the CMake parameter `MODEL_TFLITE_PATH`. -> **Note:** If you want to run the model using an *Ethos-U55*, ensure that your custom model has been successfully run +> **Note:** If you want to run the model using an *Ethos-U*, ensure that your custom model has been successfully run > through the Vela compiler *before* continuing. For further information: [Optimize model with Vela compiler](../sections/building.md#Optimize-custom-model-with-Vela-compiler). @@ -238,15 +239,15 @@ custom_model_after_vela.tflite.cc After compiling, your custom model has now replaced the default one in the application. -## Setting up and running Ethos-U55 code sample +## Setting up and running Ethos-U NPU code sample -### Setting up the Ethos-U55 Fast Model +### Setting up the Ethos-U Fast Model The FVP is available publicly from [Arm Ecosystem FVP downloads](https://developer.arm.com/tools-and-software/open-source-software/arm-platforms-software/arm-ecosystem-fvps). -For the *Ethos-U55* evaluation, please download the MPS3 version of the Arm® *Corstone™-300* model that contains both -the *Ethos-U55* and *Cortex-M55*. The model is currently only supported on Linux-based machines. +For the *Ethos-U* evaluation, please download the MPS3 based version of the Arm® *Corstone™-300* model that contains *Cortex-M55* +and offers a choice of the *Ethos-U55* and *Ethos-U65* processors. To install the FVP: @@ -255,7 +256,7 @@ To install the FVP: - Run the install script in the extracted package: ```commandline -./FVP_Corstone_SSE-300_Ethos-U55.sh +./FVP_Corstone_SSE-300.sh ``` - Follow the instructions to install the FVP to the required location. @@ -384,7 +385,7 @@ resource folder. The profiling section of the log shows that for this inference: -- *Ethos-U55* PMU report: +- *Ethos-U* PMU report: - 7,490,172 total cycle: The number of NPU cycles. @@ -393,12 +394,12 @@ The profiling section of the log shows that for this inference: - 914 idle cycles: The number of cycles for which the NPU was idle. - 2,489,726 AXI0 read beats: The number of AXI beats with read transactions from AXI0 bus. AXI0 is the bus where the - *Ethos-U55* NPU reads and writes to the computation buffers, activation buf, or tensor arenas. + *Ethos-U* NPU reads and writes to the computation buffers, activation buf, or tensor arenas. - 1,098,726 AXI0 write beats: The number of AXI beats with write transactions to AXI0 bus. - 471,129 AXI1 read beats: The number of AXI beats with read transactions from AXI1 bus. AXI1 is the bus where the - *Ethos-U55* NPU reads the model. So, read-only. + *Ethos-U* NPU reads the model. So, read-only. - For FPGA platforms, a CPU cycle count can also be enabled. However, do not use cycle counters for FVP, as the CPU model is not cycle-approximate or cycle-accurate diff --git a/docs/use_cases/inference_runner.md b/docs/use_cases/inference_runner.md index 975d56b..bd19840 100644 --- a/docs/use_cases/inference_runner.md +++ b/docs/use_cases/inference_runner.md @@ -7,8 +7,8 @@ - [Build options](#build-options) - [Build process](#build-process) - [Add custom model](#add-custom-model) - - [Setting up and running Ethos-U55 code sample](#setting-up-and-running-ethos-u55-code-sample) - - [Setting up the Ethos-U55 Fast Model](#setting-up-the-ethos-u55-fast-model) + - [Setting up and running Ethos-U NPU code sample](#setting-up-and-running-ethos-u-npu-code-sample) + - [Setting up the Ethos-U Fast Model](#setting-up-the-ethos-u-fast-model) - [Starting Fast Model simulation](#starting-fast-model-simulation) - [Running Inference Runner](#running-inference-runner) @@ -44,12 +44,12 @@ following: - `inference_runner_MODEL_TFLITE_PATH` - The path to the NN model file in the `TFLite` format. The model is then processed and included in the application `axf` file. The default value points to one of the delivered set of models. - Note that the parameters `TARGET_PLATFORM` and `ETHOS_U55_ENABLED` must be aligned with the chosen model. In other + Note that the parameters `TARGET_PLATFORM` and `ETHOS_U_NPU_ENABLED` must be aligned with the chosen model. In other words: - - If `ETHOS_U55_ENABLED` is set to `On` or `1`, then the NN model is assumed to be optimized. The model naturally + - If `ETHOS_U_NPU_ENABLED` is set to `On` or `1`, then the NN model is assumed to be optimized. The model naturally falls back to the Arm® *Cortex®-M* CPU if an unoptimized model is supplied. - - if `ETHOS_U55_ENABLED` is set to `Off` or `0`, the NN model is assumed to be unoptimized. Supplying an optimized + - if `ETHOS_U_NPU_ENABLED` is set to `Off` or `0`, the NN model is assumed to be unoptimized. Supplying an optimized model in this case results in a runtime error. - `inference_runner_ACTIVATION_BUF_SZ`: The intermediate, or activation, buffer size reserved for the NN model. By @@ -92,6 +92,7 @@ For further information, please refer to: - [Using Arm Compiler](../sections/building.md#using-arm-compiler) - [Configuring the build for simple_platform](../sections/building.md#configuring-the-build-for-simple_platform) - [Working with model debugger from Arm Fast Model Tools](../sections/building.md#working-with-model-debugger-from-arm-fast-model-tools) +- [Building for different Ethos-U NPU variants](../sections/building.md#building-for-different-ethos-u-npu-variants) > **Note:** If re-building with changed parameters values, we recommend that you clean the build directory and re-run > the CMake command. @@ -137,7 +138,7 @@ The `bin` folder contains the following files: The application performs inference using the model pointed to by the CMake parameter `inference_runner_MODEL_TFLITE_PATH`. -> **Note:** If you want to run the model using an *Ethos-U55*, ensure that your custom model has been successfully run +> **Note:** If you want to run the model using an *Ethos-U*, ensure that your custom model has been successfully run > through the Vela compiler *before* continuing. For further information: [Optimize model with Vela compiler](../sections/building.md#Optimize-custom-model-with-Vela-compiler). @@ -170,15 +171,15 @@ custom_model_after_vela.tflite.cc After compiling, your custom model has now replaced the default one in the application. -## Setting up and running Ethos-U55 code sample +## Setting up and running Ethos-U NPU code sample -### Setting up the Ethos-U55 Fast Model +### Setting up the Ethos-U Fast Model The FVP is available publicly from [Arm Ecosystem FVP downloads](https://developer.arm.com/tools-and-software/open-source-software/arm-platforms-software/arm-ecosystem-fvps). -For the *Ethos-U55* evaluation, please download the MPS3 version of the Arm® *Corstone™-300* model that contains both -the *Ethos-U55* and *Cortex-M55*. The model is currently only supported on Linux-based machines. +For the *Ethos-U* evaluation, please download the MPS3 based version of the Arm® *Corstone™-300* model that contains *Cortex-M55* +and offers a choice of the *Ethos-U55* and *Ethos-U65* processors. To install the FVP: @@ -187,7 +188,7 @@ To install the FVP: - Run the install script in the extracted package: ```commandline -./FVP_Corstone_SSE-300_Ethos-U55.sh +./FVP_Corstone_SSE-300.sh ``` - Follow the instructions to install the FVP to the required location. @@ -238,7 +239,7 @@ INFO - NPU TOTAL cycles: 34178 After running an inference on randomly generated data, the output of the log shows the profiling results that for this inference. For example: -- *Ethos-U55* PMU report: +- *Ethos-U* PMU report: - 34,178 total cycle: The number of NPU cycles. @@ -247,12 +248,12 @@ inference. For example: - 1,033 idle cycles: The number of cycles for which the NPU was idle. - 9,332 AXI0 read beats: The number of AXI beats with read transactions from AXI0 bus. AXI0 is the bus where the - *Ethos-U55* NPU reads and writes to the computation buffers, activation buf, or tensor arenas. + *Ethos-U* NPU reads and writes to the computation buffers, activation buf, or tensor arenas. - 3,248 AXI0 write beats: The number of AXI beats with write transactions to AXI0 bus. - 2,219 AXI1 read beats: The number of AXI beats with read transactions from AXI1 bus. AXI1 is the bus where the - *Ethos-U55* NPU reads the model. So, read-only. + *Ethos-U* NPU reads the model. So, read-only. - For FPGA platforms, a CPU cycle count can also be enabled. However, do not use cycle counters for FVP, as the CPU model is not cycle-approximate or cycle-accurate. diff --git a/docs/use_cases/kws.md b/docs/use_cases/kws.md index a6daadb..5839947 100644 --- a/docs/use_cases/kws.md +++ b/docs/use_cases/kws.md @@ -10,8 +10,8 @@ - [Build process](#build-process) - [Add custom input](#add-custom-input) - [Add custom model](#add-custom-model) - - [Setting up and running Ethos-U55 code sample](#setting-up-and-running-ethos-u55-code-sample) - - [Setting up the Ethos-U55 Fast Model](#setting-up-the-ethos-u55-fast-model) + - [Setting up and running Ethos-U NPU code sample](#setting-up-and-running-ethos-u-npu-code-sample) + - [Setting up the Ethos-U Fast Model](#setting-up-the-ethos-u-fast-model) - [Starting Fast Model simulation](#starting-fast-model-simulation) - [Running Keyword Spotting](#running-keyword-spotting) @@ -78,11 +78,11 @@ In addition to the already specified build option in the main documentation, the - `kws_MODEL_TFLITE_PATH` - The path to the NN model file in `TFLite` format. The model is processed and then included into the application `axf` file. The default value points to one of the delivered set of models. Note that the - parameters `kws_LABELS_TXT_FILE`,`TARGET_PLATFORM`, and `ETHOS_U55_ENABLED` must be aligned with the chosen model. In + parameters `kws_LABELS_TXT_FILE`,`TARGET_PLATFORM`, and `ETHOS_U_NPU_ENABLED` must be aligned with the chosen model. In other words: - - If `ETHOS_U55_ENABLED` is set to `On` or `1`, then the NN model is assumed to be optimized. The model naturally + - If `ETHOS_U_NPU_ENABLED` is set to `On` or `1`, then the NN model is assumed to be optimized. The model naturally falls back to the Arm® *Cortex®-M* CPU if an unoptimized model is supplied. - - If `ETHOS_U55_ENABLED` is set to `Off` or `0`, then the NN model is assumed to be unoptimized. Supplying an + - If `ETHOS_U_NPU_ENABLED` is set to `Off` or `0`, then the NN model is assumed to be unoptimized. Supplying an optimized model in this case results in a runtime error. - `kws_FILE_PATH`: The path to the directory containing audio files, or a path to single WAV file, to be used in the @@ -149,6 +149,7 @@ For further information, please refer to: - [Using Arm Compiler](../sections/building.md#using-arm-compiler) - [Configuring the build for simple_platform](../sections/building.md#configuring-the-build-for-simple_platform) - [Working with model debugger from Arm Fast Model Tools](../sections/building.md#working-with-model-debugger-from-arm-fast-model-tools) +- [Building for different Ethos-U NPU variants](../sections/building.md#building-for-different-ethos-u-npu-variants) > **Note:** If re-building with changed parameters values, we recommend that you clean the build directory and re-run > the CMake command. @@ -239,7 +240,7 @@ After compiling, your custom inputs have now replaced the default ones in the ap The application performs inference using the model pointed to by the CMake parameter `kws_MODEL_TFLITE_PATH`. -> **Note:** If you want to run the model using an *Ethos-U55*, ensure that your custom model has been successfully run +> **Note:** If you want to run the model using an *Ethos-U*, ensure that your custom model has been successfully run > through the Vela compiler *before* continuing. For further information: [Optimize model with Vela compiler](../sections/building.md#Optimize-custom-model-with-Vela-compiler). @@ -283,15 +284,15 @@ custom_model_after_vela.tflite.cc After compiling, your custom model has now replaced the default one in the application. -## Setting up and running Ethos-U55 code sample +## Setting up and running Ethos-U NPU code sample -### Setting up the Ethos-U55 Fast Model +### Setting up the Ethos-U Fast Model The FVP is available publicly from [Arm Ecosystem FVP downloads](https://developer.arm.com/tools-and-software/open-source-software/arm-platforms-software/arm-ecosystem-fvps). -For the *Ethos-U55* evaluation, please download the MPS3 version of the Arm® *Corstone™-300* model that contains both -the *Ethos-U55* and *Cortex-M55*. The model is only supported on Linux-based machines. +For the *Ethos-U* evaluation, please download the MPS3 based version of the Arm® *Corstone™-300* model that contains *Cortex-M55* +and offers a choice of the *Ethos-U55* and *Ethos-U65* processors. To install the FVP: @@ -300,7 +301,7 @@ To install the FVP: - Run the install script in the extracted package: ```commandline -./FVP_Corstone_SSE-300_Ethos-U55.sh +./FVP_Corstone_SSE-300.sh ``` - Follow the instructions to install the FVP to the required location. @@ -423,7 +424,7 @@ On most systems running Fast Model, each inference takes under 30 seconds. The profiling section of the log shows that for this inference: -- *Ethos-U55* PMU report: +- *Ethos-U* PMU report: - 681,172 total cycle: The number of NPU cycles. @@ -432,12 +433,12 @@ The profiling section of the log shows that for this inference: - 561 idle cycles: The number of cycles for which the NPU was idle. - 217,385 AXI0 read beats: The number of AXI beats with read transactions from the AXI0 bus. AXI0 is the bus where the - *Ethos-U55* NPU reads and writes to the computation buffers, activation buf, or tensor arenas. + *Ethos-U* NPU reads and writes to the computation buffers, activation buf, or tensor arenas. - 82,607 write cycles: The number of AXI beats with write transactions to AXI0 bus. - 59,608 AXI1 read beats: The number of AXI beats with read transactions from the AXI1 bus. AXI1 is the bus where the - *Ethos-U55* NPU reads the model. So, read-only. + *Ethos-U* NPU reads the model. So, read-only. - For FPGA platforms, a CPU cycle count can also be enabled. However, do not use cycle counters for FVP, as the CPU model is not cycle-approximate or cycle-accurate. diff --git a/docs/use_cases/kws_asr.md b/docs/use_cases/kws_asr.md index 52d66ab..51d1840 100644 --- a/docs/use_cases/kws_asr.md +++ b/docs/use_cases/kws_asr.md @@ -12,8 +12,8 @@ - [Build process](#build-process) - [Add custom input](#add-custom-input) - [Add custom model](#add-custom-model) - - [Setting-up and running Ethos-U55 Code Samples](#setting-up-and-running-ethos-u55-code-samples) - - [Setting up the Ethos-U55 Fast Model](#setting-up-the-ethos-u55-fast-model) + - [Setting up and running Ethos-U NPU code sample](#setting-up-and-running-ethos-u-npu-code-sample) + - [Setting up the Ethos-U Fast Model](#setting-up-the-ethos-u-fast-model) - [Starting Fast Model simulation](#starting-fast-model-simulation) - [Running Keyword Spotting and Automatic Speech Recognition](#running-keyword-spotting-and-automatic-speech-recognition) @@ -166,11 +166,11 @@ Recognition use-case adds: - `kws_asr_MODEL_TFLITE_PATH_ASR` and `kws_asr_MODEL_TFLITE_PATH_KWS`: The path to the NN model file in `TFLite` format. The model is processed and then included into the application `axf` file. The default value points to one of the delivered set of models. Note that the parameters `kws_asr_LABELS_TXT_FILE_KWS`, - `kws_asr_LABELS_TXT_FILE_ASR`,`TARGET_PLATFORM`, and `ETHOS_U55_ENABLED` must be aligned with the chosen model. In + `kws_asr_LABELS_TXT_FILE_ASR`,`TARGET_PLATFORM`, and `ETHOS_U_NPU_ENABLED` must be aligned with the chosen model. In other words: - - If `ETHOS_U55_ENABLED` is set to `On` or `1`, then the NN model is assumed to be optimized. The model naturally + - If `ETHOS_U_NPU_ENABLED` is set to `On` or `1`, then the NN model is assumed to be optimized. The model naturally falls back to the Arm® *Cortex®-M* CPU if an unoptimized model is supplied. - - If `ETHOS_U55_ENABLED` is set to `Off` or `0`, then the NN model is assumed to be unoptimized. Supplying an + - If `ETHOS_U_NPU_ENABLED` is set to `Off` or `0`, then the NN model is assumed to be unoptimized. Supplying an optimized model in this case results in a runtime error. - `kws_asr_FILE_PATH`: The path to the directory containing audio files, or a path to single WAV file, to be used in the @@ -242,6 +242,7 @@ For further information, please refer to: - [Using Arm Compiler](../sections/building.md#using-arm-compiler) - [Configuring the build for simple_platform](../sections/building.md#configuring-the-build-for-simple_platform) - [Working with model debugger from Arm Fast Model Tools](../sections/building.md#working-with-model-debugger-from-arm-fast-model-tools) +- [Building for different Ethos-U NPU variants](../sections/building.md#building-for-different-ethos-u-npu-variants) > **Note:** If re-building with changed parameters values, we recommend that you clean the build directory and re-run > the CMake command. @@ -328,7 +329,7 @@ The application performs KWS inference using the model pointed to by the CMake p This section assumes you want to change the existing ASR model to a custom one. If, instead, you want to change the KWS model, then the instructions are the same. Except ASR changes to KWS. -> **Note:** If you want to run the model using an *Ethos-U55*, ensure that your custom model has been successfully run +> **Note:** If you want to run the model using an *Ethos-U*, ensure that your custom model has been successfully run > through the Vela compiler *before* continuing. For further information: @@ -374,15 +375,14 @@ custom_asr_model_after_vela.tflite.cc After compiling, your custom model has now replaced the default one in the application. -## Setting-up and running Ethos-U55 Code Samples +## Setting up and running Ethos-U NPU code sample -### Setting up the Ethos-U55 Fast Model +### Setting up the Ethos-U Fast Model The FVP is available publicly from [Arm Ecosystem FVP downloads](https://developer.arm.com/tools-and-software/open-source-software/arm-platforms-software/arm-ecosystem-fvps). -For the *Ethos-U55* evaluation, please download the MPS3 version of the Arm® *Corstone™-300* model that contains both -the *Ethos-U55* and *Cortex-M55*. The model is only supported on Linux-based machines. +For the *Ethos-U* evaluation, please download the MPS3 based version of the Arm® *Corstone™-300* model that contains *Cortex-M55* and offers a choice of the *Ethos-U55* and *Ethos-U65* processors. To install the FVP: @@ -391,7 +391,7 @@ To install the FVP: - Run the install script in the extracted package: ```commandline -./FVP_Corstone_SSE-300_Ethos-U55.sh +./FVP_Corstone_SSE-300.sh ``` - Follow the instructions to install the FVP to the required location. @@ -566,7 +566,7 @@ words recognized from the input sample. The profiling section of the log shows that for the ASR inference: -- *Ethos-U55* PMU report: +- *Ethos-U* PMU report: - 28,910,172 total cycle: The number of NPU cycles. @@ -575,7 +575,7 @@ The profiling section of the log shows that for the ASR inference: - 863 idle cycles: The number of cycles for which the NPU was idle. - 13,520,864 AXI0 read beats: The number of AXI beats with read transactions from the AXI0 bus. AXI0 is the bus where - the *Ethos-U55* NPU reads and writes to the computation buffers, activation buf, or tensor arenas. + the *Ethos-U* NPU reads and writes to the computation buffers, activation buf, or tensor arenas. - 2,841,970 AXI0 write beats: The number of AXI beats with write transactions to AXI0 bus. |