diff options
author | Tim Hall <tim.hall@arm.com> | 2020-08-21 13:36:21 +0100 |
---|---|---|
committer | Tim Hall <tim.hall@arm.com> | 2020-08-28 12:00:07 +0100 |
commit | 7201932246734b8b5db016106ad8df108d2513d0 (patch) | |
tree | 278de6c942dd186c3cada34cc80c35b56707e651 /README.md | |
parent | 5e990c88e418df7e885e54dcaf2434efbed3a284 (diff) | |
download | ethos-u-vela-7201932246734b8b5db016106ad8df108d2513d0.tar.gz |
MLBEDSW-2411: Update README with example networks
- Added reference to TensorFlow Hub
- Updated relative .md links to release location
Signed-off-by: Tim Hall <tim.hall@arm.com>
Change-Id: I7f7b3508bd530d76681d25594ea7ff8241fe964d
Diffstat (limited to 'README.md')
-rw-r--r-- | README.md | 29 |
1 files changed, 19 insertions, 10 deletions
@@ -4,17 +4,20 @@ This tool is used to compile a [TensorFlow Lite for Microcontrollers](https://www.tensorflow.org/lite/microcontrollers) neural network model into an optimised version that can run on an embedded system containing an -[Ethos-U55 NPU](https://www.arm.com/products/silicon-ip-cpu/ethos/ethos-u55). +[Arm Ethos-U NPU](https://www.arm.com/products/silicon-ip-cpu). + +In order to be accelerated by the Ethos-U NPU the network operators must be +quantised to either 8-bit (unsigned or signed) or 16-bit (signed). The optimised model will contain TensorFlow Lite Custom operators for those -parts of the model that can be accelerated by the Ethos-U55. Parts of the model -that cannot be accelerated are left unchanged and will instead run on the +parts of the model that can be accelerated by the Ethos-U NPU. Parts of the +model that cannot be accelerated are left unchanged and will instead run on the Cortex-M series CPU using an appropriate kernel (such as the [Arm](https://www.arm.com) optimised [CMSIS-NN](https://github.com/ARM-software/CMSIS_5/tree/develop/CMSIS/NN) kernels). -After compilation the optimised model can only be run on an Ethos-U55 NPU +After compilation the optimised model can only be run on an Ethos-U NPU embedded system. The tool will also generate performance estimates (EXPERIMENTAL) for the @@ -111,7 +114,7 @@ version with a `_vela.tflite` file prefix, along with the performance estimate (EXPERIMENTAL) CSV files, all to the output directory. If you use the `pipenv` virtual environment tool then first start by spawning a -shell in the virtual environment.: +shell in the virtual environment: ```bash pipenv shell @@ -152,11 +155,17 @@ vela --help ``` Information about all of Vela's CLI options as well as the system configuration -file format can be found in [Vela Options](OPTIONS.md) +file format can be found in [Vela Options](OPTIONS.md). + +## Example Networks + +Some example networks that contain quantised operators which can be compiled by +Vela to run on the Ethos-U NPU can be found at: +<https://tfhub.dev/s?deployment-format=lite&q=quantized> ## Testing -Please see [Vela Testing](TESTING.md) +Please see [Vela Testing](TESTING.md). ## Contributions @@ -174,9 +183,9 @@ Please see [Vela Releases](RELEASES.md). Additional useful information: -* [Arm Products: Ethos-U55](https://www.arm.com/products/silicon-ip-cpu/ethos/ethos-u55) -* [Arm Developer: Ethos-U55](https://developer.arm.com/ip-products/processors/machine-learning/ethos-u55) +* [Arm Products: Ethos-U55 NPU](https://www.arm.com/products/silicon-ip-cpu/ethos/ethos-u55) +* [Arm Developer: Ethos-U55 NPU](https://developer.arm.com/ip-products/processors/machine-learning/ethos-u55) ## License -Vela is licensed under [Apache License 2.0](LICENSE.txt) +Vela is licensed under [Apache License 2.0](LICENSE.txt). |