diff options
| author | George Gekov <george.gekov@arm.com> | 2021-07-06 12:02:26 +0100 |
|---|---|---|
| committer | George Gekov <george.gekov@arm.com> | 2021-07-09 13:43:06 +0100 |
| commit | be54c625bbec3b0c5927c772053951c06e336ae2 (patch) | |
| tree | e5ebf88f3940152a0c787a27f01c8b30e2c6d595 /docs | |
| parent | 80eecfbdaad689c52d5a6d370a322f3d6a6150e4 (diff) | |
| download | ml-embedded-evaluation-kit-be54c625bbec3b0c5927c772053951c06e336ae2.tar.gz | |
MLECO-2036: Fix Vela3 documentation references & update Vela .ini configuration
Signed-off-by: George Gekov <george.gekov@arm.com>
Change-Id: I92b9ab60974ad266246994deae5833f7f374633d
Diffstat (limited to 'docs')
| -rw-r--r-- | docs/quick_start.md | 2 | ||||
| -rw-r--r-- | docs/sections/building.md | 4 |
2 files changed, 3 insertions, 3 deletions
diff --git a/docs/quick_start.md b/docs/quick_start.md index 9a2937c..9d059fe 100644 --- a/docs/quick_start.md +++ b/docs/quick_start.md @@ -63,7 +63,7 @@ mkdir resources_downloaded && cd resources_downloaded python3 -m venv env env/bin/python3 -m pip install --upgrade pip env/bin/python3 -m pip install --upgrade setuptools -env/bin/python3 -m pip install ethos-u-vela==2.1.1 +env/bin/python3 -m pip install ethos-u-vela==3.0.0 cd .. curl -L https://github.com/ARM-software/ML-zoo/raw/7c32b097f7d94aae2cd0b98a8ed5a3ba81e66b18/models/anomaly_detection/micronet_medium/tflite_int8/ad_medium_int8.tflite \ diff --git a/docs/sections/building.md b/docs/sections/building.md index 96af70d..63f8d53 100644 --- a/docs/sections/building.md +++ b/docs/sections/building.md @@ -672,11 +672,11 @@ vela \ <model>.tflite ``` -The Vela folder contains the following: +The Vela command contains the following: - `--accelerator-config`: Specifies the accelerator configuration to use between `ethos-u55-256`, `ethos-u55-128`, `ethos-u55-64`, and `ethos-u55-32`. -- `--block-config-limit`: Limits the block config search space. Use `zero` for unlimited search space. +- `--optimise`: Sets the optimisation strategy to Performance or Size. The Size strategy results in a model minimising the SRAM usage whereas the Performance strategy optimises the neural network for maximal perforamance. Note that if using the Performance strategy, you can also pass the `--arena-cache-size` option to Vela. - `--config`: Specifies the path to the Vela configuration file. The format of the file is a Python ConfigParser `.ini` file. An example can be found in the `dependencies` folder [default_vela.ini](../../scripts/vela/default_vela.ini). - `--memory-mode`: Selects the memory mode to use as specified in the Vela configuration file. |