HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

Add compatible tensorstore versions for aarch64 (#14697)

Browse source 
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Lakshantha Dissanayake 2024-07-25 15:28:08 -07:00 • committed by GitHub
parent db42d180d9
commit 1d5d105c62
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

3
docker/Dockerfile-arm64
View file

@ -32,9 +32,8 @@ ADD https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n.pt $A
RUN rm -rf /usr/lib/python3.11/EXTERNALLY-MANAGED
# Install pip packages
# Install tensorstore from .whl because PyPI does not include aarch64 binaries
RUN python3 -m pip install --upgrade pip wheel
RUN pip install --no-cache-dir https://github.com/ultralytics/assets/releases/download/v0.0.0/tensorstore-0.1.59-cp311-cp311-linux_aarch64.whl -e ".[export]"
RUN pip install --no-cache-dir -e ".[export]"
# Creates a symbolic link to make 'python' point to 'python3'
RUN ln -sf /usr/bin/python3 /usr/bin/python

1
pyproject.toml
View file

@ -101,6 +101,7 @@ export = [
"openvino>=2024.0.0", # OpenVINO export
"tensorflow>=2.0.0", # TF bug https://github.com/ultralytics/ultralytics/issues/5161
"tensorflowjs>=3.9.0", # TF.js export, automatically installs tensorflow
"tensorstore>=0.1.63; platform_machine == 'aarch64' and python_version >= '3.9'", # for TF Raspberry Pi exports
"keras", # not installed automatically by tensorflow>=2.16
"flatbuffers>=23.5.26,<100; platform_machine == 'aarch64'", # update old 'flatbuffers' included inside tensorflow package
"numpy==1.23.5; platform_machine == 'aarch64'", # fix error: `np.bool` was a deprecated alias for the builtin `bool` when using TensorRT models on NVIDIA Jetson