Changes between Version 18 and Version 19 of venice/npu

Timestamp:

08/19/2024 11:10:36 PM (4 weeks ago)

Author:

Tim Harvey

Comment:

updated upstream/mainline example to use python3.9 to avoid python dependency issues

venice/npu

@@ -236 +236 @@
 Therefore to support the NPU you need to build a custom fork of mesa that is being worked on by [https://blog.tomeuvizoso.net/ Tomeu Vizoso] with the work being sponsored by [https://ideasonboard.com/ Ideas On board].
 
-On a Gateworks Venice board with an IMX8MP and Ubuntu 22.04 (jammy) root filesystem:
+On a Gateworks Venice board with an IMX8MP and an Ubuntu root filesystem:
 - update kernel to v6.10 with NPU support
 {{{#!bash
@@ -255 +255 @@
 su -l $USER
 }}}
-- install python virtualenv which allows us to prevent conflicts between package libraries
-{{{#!bash
-sudo apt update && sudo apt upgrade -y && sudo apt install -y python3-pip python3-venv
-# create tflite1-env" virtualenv
-python3 -m venv tflite1-env
+- to avoid a lot of python dependency issues with tensorflow-lite install an older version of python (python3.9) using the [https://launchpad.net/%7Edeadsnakes/+archive/ubuntu/ppa deadsnakes ppa] and create a virtualenv
+{{{#!bash
+sudo add-apt-repository ppa:deadsnakes/ppa
+sudo apt update
+sudo apt install -y python3.9 python3.9-venv
+# create tflite-env virtualenv
+python3.9 -m venv tflite-env
 # activate the venv (repeat or every new shell)
-source tflite1-env/bin/activate
+source tflite-env/bin/activate
 }}}
 - build mesa (fork with updated teflon support for imx8mp)
@@ -273 +275 @@
 # mesa requires meson >= 1.1.0 (newer than jammy's), pycparser >= 2.20, and mako
 pip3 install meson pycparser mako
-~/tflite1-env/bin/meson setup build -Dgallium-drivers=etnaviv -Dvulkan-drivers= -Dteflon=true
-~/tflite1-env/bin/meson compile -C build # 20 mins or so on imx8mp
+meson setup build -Dgallium-drivers=etnaviv -Dvulkan-drivers= -Dteflon=true
+meson compile -C build # 20 mins or so on imx8mp
 ldd build/src/gallium/targets/teflon/libteflon.so
 }}}
@@ -288 +290 @@
 {{{#!bash
 # note this test requires python pillow, python numpy<2.0 and write access to /dev/dri/renderD128
-pip3 install "numpy<2.0" pillow tflite_runtime # tflite_runtime requires pillow as well as numpy<2
+pip3 install "numpy<2.0" pillow
 groups # make sure your in the render group (or have write access to /dev/dri/renderD128)
 # without teflon (175.335ms on imx8mp)
@@ -333 +335 @@
 patch -p1
 # without acceleration (175.993ms on imx8mp)
-python3 ~/tensorflow/lite/examples/python/label_image.py \
+python3 ~/tensorflow/tensorflow/lite/examples/python/label_image.py \
   -m ~/mesa/src/gallium/targets/teflon/tests/mobilenet_v1_1.0_224_quant.tflite \
   -l ~/mesa/src/gallium/frontends/teflon/tests/labels_mobilenet_quant_v1_224.txt \
   -i ~/tensorflow/tensorflow/lite/examples/label_image/testdata/grace_hopper.bmp
 # with acceleration (14.138ms on imx8mp)
-python3 ~/tensorflow/lite/examples/python/label_image.py \
+python3 ~/tensorflow/tensorflow/lite/examples/python/label_image.py \
  -m ~/mesa/src/gallium/targets/teflon/tests/mobilenet_v1_1.0_224_quant.tflite \
  -l ~/mesa/src/gallium/frontends/teflon/tests/labels_mobilenet_quant_v1_224.txt \