Duckietown Jetson Nano 4GB Ultralytics YoloV11 attempt
Testing Ultralytics Nvidia Jetson instructions on Duckietown Duckiebot DB21-J
https://docs.ultralytics.com/guides/nvidia-jetson/#
First attempt on ultralytics Docker image:
sampsa@Moebels:~/duckie/duckietown_dataset/yolov5$ ssh -l duckie duckgull.local
duckie@duckgull.local's password:
Welcome to Ubuntu 18.04.5 LTS (GNU/Linux 4.9.140-tegra aarch64)
* Documentation: https://help.ubuntu.com
* Management: https://landscape.canonical.com
* Support: https://ubuntu.com/advantage
This system has been minimized by removing packages and content that are
not required on a system that users do not log into.
To restore this content, you can run the 'unminimize' command.
353 updates can be applied immediately.
311 of these updates are standard security updates.
To see these additional updates run: apt list --upgradable
Last login: Mon Dec 30 14:13:48 2024 from 192.168.1.100
duckie@duckgull:~$ docker ps -q
da97d046a6bf
39fe6f7afdee
63b9d5730641
d290e59c865c
518f481b522c
0ce4a76d030b
14039cc09d95
26325c78a190
ac15ab314aa6
76de6b5e695b
0a6b5757b335
duckie@duckgull:~$ docker kill $(docker ps -q)
da97d046a6bf
39fe6f7afdee
63b9d5730641
d290e59c865c
518f481b522c
0ce4a76d030b
14039cc09d95
26325c78a190
ac15ab314aa6
76de6b5e695b
0a6b5757b335
duckie@duckgull:~$ docker pull ultralytics/ultralytics:latest-jetson-jetpack4
latest-jetson-jetpack4: Pulling from ultralytics/ultralytics
f46992f278c2: Pull complete
d0ec296fcb76: Extracting [==================================================>] 164.9MB/164.9MB
9e18ddc8ca7a: Download complete
457ba495c8e5: Download complete
71bca45e35bd: Download complete
644761cdc735: Download complete
11628dbc31eb: Download complete
d364c3700c33: Download complete
01869d070b2e: Download complete
cc3009375042: Verifying Checksum
3e182d6364dc: Download complete
f72feb4812f9: Download complete
151eb940bbec: Download complete
0e9dda2495b9: Download complete
0e78bdc2f297: Download complete
8dc68d594a4e: Download complete
777499412cc5: Download complete
1ca27931ddcb: Download complete
d0ec296fcb76: Pull complete
9e18ddc8ca7a: Pull complete
457ba495c8e5: Pull complete
71bca45e35bd: Pull complete
644761cdc735: Pull complete
11628dbc31eb: Pull complete
d364c3700c33: Pull complete
01869d070b2e: Pull complete
cc3009375042: Pull complete
3e182d6364dc: Pull complete
f72feb4812f9: Pull complete
151eb940bbec: Pull complete
0e9dda2495b9: Pull complete
0e78bdc2f297: Pull complete
8dc68d594a4e: Pull complete
777499412cc5: Pull complete
1ca27931ddcb: Pull complete
4fb3d314e9f2: Pull complete
841fe4d09b1d: Pull complete
bfef8915158a: Pull complete
30534ba90a81: Pull complete
95248f4c0ee9: Pull complete
9492797590fc: Pull complete
dd6c7e2afa32: Pull complete
477ed70ce3c3: Pull complete
5d51f33687ec: Pull complete
1e1342d3c751: Pull complete
0a04cbc9d718: Pull complete
58772a5ec6cc: Pull complete
1f97c6fd0f42: Pull complete
78e81412103b: Pull complete
adddd2437bd6: Pull complete
b432c9f470c0: Pull complete
2cb67339f5ef: Pull complete
6fb7a67f9e2f: Pull complete
523bc3dec52e: Pull complete
0ce3932e06e3: Pull complete
Digest: sha256:714218f14cc790514622aad9de4bf06848a9f598a95a1340b3445c039a5417c4
Status: Downloaded newer image for ultralytics/ultralytics:latest-jetson-jetpack4
docker.io/ultralytics/ultralytics:latest-jetson-jetpack4
duckie@duckgull:~$duckie@duckgull:~$ docker run -it --ipc=host --runtime=nvidia ultralytics/ultralytics:latest-jetson-jetpack4
docker: Error response from daemon: OCI runtime create failed: container_linux.go:380: starting container process caused: process_linux.go:545: container init caused: Running hook #1:: error running hook: exit status 1, stdout: , stderr: exec command: [/usr/bin/nvidia-container-cli --load-kmods configure --ldconfig=@/sbin/ldconfig.real --device=all --compute --utility --require=cuda>=10.2 --require=base-only --pid=6512 /var/lib/docker/overlay2/cff74f9049d435a3eae46409e9f9f7245cff5a2b51f81910222b2c45354a8964/merged]
nvidia-container-cli: requirement error: invalid expression: unknown.
ERRO[0008] error waiting for container: context canceled
duckie@duckgull:~$ docker run -it ultralytics/ultralytics:latest-jetson-jetpack4
docker: Error response from daemon: OCI runtime create failed: container_linux.go:380: starting container process caused: process_linux.go:545: container init caused: Running hook #1:: error running hook: exit status 1, stdout: , stderr: exec command: [/usr/bin/nvidia-container-cli --load-kmods configure --ldconfig=@/sbin/ldconfig.real --device=all --compute --utility --require=cuda>=10.2 --require=base-only --pid=10560 /var/lib/docker/overlay2/e721ac18ecc80e155c1508b923fea63d149d35c252e45f77f82f9538979d863e/merged]
nvidia-container-cli: requirement error: invalid expression: unknown.
ERRO[0000] error waiting for container: context canceled
duckie@duckgull:~$-> Seems Duckietown Jetson Jetpack 4 is old or otherwise not directly compatible. 2nd attempt on Duckietown image.
duckie@duckgull:~$ docker pull duckietown/dt-machine-learning-base-pytorch:daffy-arm64v8
daffy-arm64v8: Pulling from duckietown/dt-machine-learning-base-pytorch
Digest: sha256:22672674df0ce3e23e9bcb169ff0bee18e15e23481b5faf67ae5999810f291a6
Status: Image is up to date for duckietown/dt-machine-learning-base-pytorch:daffy-arm64v8
docker.io/duckietown/dt-machine-learning-base-pytorch:daffy-arm64v8
duckie@duckgull:~$ docker run -it duckietown/dt-machine-learning-base-pytorch:daffy-arm64v8 /bin/bash
==> Entrypoint
INFO: The environment variable VEHICLE_NAME is not set. Using 'cd72a4fb68a2'.
INFO: Network configured successfully.
WARNING: robot_type file does not exist. Using 'duckiebot' as default type.
WARNING: robot_configuration file does not exist.
WARNING: robot_hardware file does not exist.
<== Entrypoint
root@cd72a4fb68a2:/code/dt-machine-learning-base-pytorch# pip install ultralytics
Collecting ultralytics
Downloading ultralytics-8.3.81-py3-none-any.whl.metadata (35 kB)
Requirement already satisfied: numpy<=2.1.1,>=1.23.0 in /usr/local/lib/python3.8/dist-packages (from ultralytics) (1.24.4)
Requirement already satisfied: matplotlib>=3.3.0 in /usr/local/lib/python3.8/dist-packages (from ultralytics) (3.7.5)
Collecting opencv-python>=4.6.0 (from ultralytics)
Downloading opencv_python-4.11.0.86-cp37-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl.metadata (20 kB)
Requirement already satisfied: pillow>=7.1.2 in /usr/local/lib/python3.8/dist-packages (from ultralytics) (10.1.0)
Requirement already satisfied: pyyaml>=5.3.1 in /usr/lib/python3/dist-packages (from ultralytics) (5.3.1)
Requirement already satisfied: requests>=2.23.0 in /usr/local/lib/python3.8/dist-packages (from ultralytics) (2.31.0)
Requirement already satisfied: scipy>=1.4.1 in /usr/local/lib/python3.8/dist-packages (from ultralytics) (1.10.1)
Collecting torch>=1.8.0 (from ultralytics)
Downloading torch-2.4.1-cp38-cp38-manylinux2014_aarch64.whl.metadata (26 kB)
Collecting torchvision>=0.9.0 (from ultralytics)
Downloading torchvision-0.19.1-cp38-cp38-manylinux2014_aarch64.whl.metadata (6.0 kB)
Requirement already satisfied: tqdm>=4.64.0 in /usr/local/lib/python3.8/dist-packages (from ultralytics) (4.66.2)
Requirement already satisfied: psutil in /usr/lib/python3/dist-packages (from ultralytics) (5.5.1)
Collecting py-cpuinfo (from ultralytics)
Downloading py_cpuinfo-9.0.0-py3-none-any.whl.metadata (794 bytes)
Requirement already satisfied: pandas>=1.1.4 in /usr/local/lib/python3.8/dist-packages (from ultralytics) (2.0.3)
Requirement already satisfied: seaborn>=0.11.0 in /usr/local/lib/python3.8/dist-packages (from ultralytics) (0.13.2)
Collecting ultralytics-thop>=2.0.0 (from ultralytics)
Downloading ultralytics_thop-2.0.14-py3-none-any.whl.metadata (9.4 kB)
Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.8/dist-packages (from matplotlib>=3.3.0->ultralytics) (1.1.1)
Requirement already satisfied: cycler>=0.10 in /usr/lib/python3/dist-packages (from matplotlib>=3.3.0->ultralytics) (0.10.0)
Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.8/dist-packages (from matplotlib>=3.3.0->ultralytics) (4.51.0)
Requirement already satisfied: kiwisolver>=1.0.1 in /usr/lib/python3/dist-packages (from matplotlib>=3.3.0->ultralytics) (1.0.1)
Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.8/dist-packages (from matplotlib>=3.3.0->ultralytics) (24.0)
Requirement already satisfied: pyparsing>=2.3.1 in /usr/lib/python3/dist-packages (from matplotlib>=3.3.0->ultralytics) (2.4.6)
Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.8/dist-packages (from matplotlib>=3.3.0->ultralytics) (2.9.0.post0)
Requirement already satisfied: importlib-resources>=3.2.0 in /usr/local/lib/python3.8/dist-packages (from matplotlib>=3.3.0->ultralytics) (6.4.0)
Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.8/dist-packages (from pandas>=1.1.4->ultralytics) (2024.1)
Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.8/dist-packages (from pandas>=1.1.4->ultralytics) (2024.1)
Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.8/dist-packages (from requests>=2.23.0->ultralytics) (3.3.2)
Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.8/dist-packages (from requests>=2.23.0->ultralytics) (3.7)
Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.8/dist-packages (from requests>=2.23.0->ultralytics) (2.2.1)
Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.8/dist-packages (from requests>=2.23.0->ultralytics) (2024.2.2)
Collecting filelock (from torch>=1.8.0->ultralytics)
Downloading filelock-3.16.1-py3-none-any.whl.metadata (2.9 kB)
Requirement already satisfied: typing-extensions>=4.8.0 in /usr/local/lib/python3.8/dist-packages (from torch>=1.8.0->ultralytics) (4.11.0)
Collecting sympy (from torch>=1.8.0->ultralytics)
Downloading sympy-1.13.3-py3-none-any.whl.metadata (12 kB)
Requirement already satisfied: networkx in /usr/local/lib/python3.8/dist-packages (from torch>=1.8.0->ultralytics) (2.8.8)
Requirement already satisfied: jinja2 in /usr/local/lib/python3.8/dist-packages (from torch>=1.8.0->ultralytics) (3.1.3)
Collecting fsspec (from torch>=1.8.0->ultralytics)
Downloading fsspec-2025.2.0-py3-none-any.whl.metadata (11 kB)
Requirement already satisfied: zipp>=3.1.0 in /usr/local/lib/python3.8/dist-packages (from importlib-resources>=3.2.0->matplotlib>=3.3.0->ultralytics) (3.18.1)
Requirement already satisfied: six>=1.5 in /usr/lib/python3/dist-packages (from python-dateutil>=2.7->matplotlib>=3.3.0->ultralytics) (1.14.0)
Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.8/dist-packages (from jinja2->torch>=1.8.0->ultralytics) (2.1.5)
Collecting mpmath<1.4,>=1.1.0 (from sympy->torch>=1.8.0->ultralytics)
Downloading mpmath-1.3.0-py3-none-any.whl.metadata (8.6 kB)
Downloading ultralytics-8.3.81-py3-none-any.whl (922 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 922.1/922.1 kB 2.7 MB/s eta 0:00:00
Downloading opencv_python-4.11.0.86-cp37-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (42.2 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 42.2/42.2 MB 3.7 MB/s eta 0:00:00
Downloading torch-2.4.1-cp38-cp38-manylinux2014_aarch64.whl (89.7 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 89.7/89.7 MB 1.7 MB/s eta 0:00:00
Downloading torchvision-0.19.1-cp38-cp38-manylinux2014_aarch64.whl (14.1 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 14.1/14.1 MB 4.2 MB/s eta 0:00:00
Downloading ultralytics_thop-2.0.14-py3-none-any.whl (26 kB)
Downloading py_cpuinfo-9.0.0-py3-none-any.whl (22 kB)
Downloading filelock-3.16.1-py3-none-any.whl (16 kB)
Downloading fsspec-2025.2.0-py3-none-any.whl (184 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 184.5/184.5 kB 4.3 MB/s eta 0:00:00
Downloading sympy-1.13.3-py3-none-any.whl (6.2 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 6.2/6.2 MB 3.9 MB/s eta 0:00:00
Downloading mpmath-1.3.0-py3-none-any.whl (536 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 536.2/536.2 kB 3.9 MB/s eta 0:00:00
Installing collected packages: py-cpuinfo, mpmath, sympy, opencv-python, fsspec, filelock, torch, ultralytics-thop, torchvision, ultralytics
Attempting uninstall: torch
Found existing installation: torch 1.7.0
Uninstalling torch-1.7.0:
Successfully uninstalled torch-1.7.0
Successfully installed filelock-3.16.1 fsspec-2025.2.0 mpmath-1.3.0 opencv-python-4.11.0.86 py-cpuinfo-9.0.0 sympy-1.13.3 torch-2.4.1 torchvision-0.19.1 ultralytics-8.3.81 ultralytics-thop-2.0.14
[notice] A new release of pip is available: 24.0 -> 25.0.1
[notice] To update, run: python3 -m pip install --upgrade pip
root@cd72a4fb68a2:/code/dt-machine-learning-base-pytorch#
Benchmark attempt on dt-machine-learning-base-pytorch
root@cd72a4fb68a2:/code/dt-machine-learning-base-pytorch# yolo benchmark model=yolo11n.pt data=coco8.yaml imgsz=640
Creating new Ultralytics Settings v0.0.6 file ✅
View Ultralytics Settings with 'yolo settings' or at '/root/.config/Ultralytics/settings.json'
Update Settings with 'yolo settings key=value', i.e. 'yolo settings runs_dir=path/to/dir'. For help see https://docs.ultralytics.com/quickstart/#ultralytics-settings.
Downloading https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n.pt to 'yolo11n.pt'...
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 5.35M/5.35M [00:08<00:00, 690kB/s]
/usr/local/lib/python3.8/dist-packages/pandas/core/computation/expressions.py:20: UserWarning: Pandas requires version '2.7.3' or newer of 'numexpr' (version '2.7.1' currently installed).
from pandas.core.computation.check import NUMEXPR_INSTALLED
Dataset 'coco8.yaml' images not found ⚠️, missing path '/code/dt-machine-learning-base-pytorch/datasets/coco8/images/val'
Downloading https://ultralytics.com/assets/coco8.zip to '/code/dt-machine-learning-base-pytorch/datasets/coco8.zip'...
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 433k/433k [00:00<00:00, 2.58MB/s]
Unzipping /code/dt-machine-learning-base-pytorch/datasets/coco8.zip to /code/dt-machine-learning-base-pytorch/datasets/coco8...: 100%|██████████| 25/25 [00:00<00
Dataset download success ✅ (1.5s), saved to /code/dt-machine-learning-base-pytorch/datasets
Downloading https://ultralytics.com/assets/Arial.ttf to '/root/.config/Ultralytics/Arial.ttf'...
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 755k/755k [00:01<00:00, 604kB/s]
val: Scanning /code/dt-machine-learning-base-pytorch/datasets/coco8/labels/val... 4 images, 0 backgrounds, 0 corrupt: 100%|██████████| 4/4 [00:00<00:00, 173.74it
val: New cache created: /code/dt-machine-learning-base-pytorch/datasets/coco8/labels/val.cache
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 4/4 [00:05<00:00, 1.34s/it]
all 4 17 0.574 0.85 0.815 0.61
Speed: 2.7ms preprocess, 1316.5ms inference, 0.0ms loss, 5.0ms postprocess per image
PyTorch: starting from 'yolo11n.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) (1, 84, 8400) (5.4 MB)
TorchScript: starting export with torch 2.4.1...
TorchScript: export success ✅ 14.4s, saved as 'yolo11n.torchscript' (10.5 MB)
Export complete (17.7s)
Results saved to /code/dt-machine-learning-base-pytorch
Predict: yolo predict task=detect model=yolo11n.torchscript imgsz=640
Validate: yolo val task=detect model=yolo11n.torchscript imgsz=640 data=/usr/src/ultralytics/ultralytics/cfg/datasets/coco.yaml
Visualize: https://netron.app
Loading yolo11n.torchscript for TorchScript inference...
Loading yolo11n.torchscript for TorchScript inference...
val: Scanning /code/dt-machine-learning-base-pytorch/datasets/coco8/labels/val.cache... 4 images, 0 backgrounds, 0 corrupt: 100%|██████████| 4/4 [00:00<?, ?it/s]
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 4/4 [00:07<00:00, 1.79s/it]
all 4 17 0.846 0.637 0.85 0.608
Speed: 5.4ms preprocess, 1761.9ms inference, 0.0ms loss, 5.0ms postprocess per image
PyTorch: starting from 'yolo11n.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) (1, 84, 8400) (5.4 MB)
requirements: Ultralytics requirements ['onnx>=1.12.0', 'onnxslim', 'onnxruntime'] not found, attempting AutoUpdate...
[notice] A new release of pip is available: 24.0 -> 25.0.1
[notice] To update, run: python3 -m pip install --upgrade pip
Collecting onnx>=1.12.0
Downloading onnx-1.17.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl.metadata (16 kB)
Collecting onnxslim
Downloading onnxslim-0.1.48-py3-none-any.whl.metadata (4.6 kB)
Collecting onnxruntime
Downloading onnxruntime-1.19.2-cp38-cp38-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl.metadata (4.5 kB)
Requirement already satisfied: numpy>=1.20 in /usr/local/lib/python3.8/dist-packages (from onnx>=1.12.0) (1.24.4)
Collecting protobuf>=3.20.2 (from onnx>=1.12.0)
Downloading protobuf-5.29.3-cp38-abi3-manylinux2014_aarch64.whl.metadata (592 bytes)
Requirement already satisfied: sympy in /usr/local/lib/python3.8/dist-packages (from onnxslim) (1.13.3)
Requirement already satisfied: packaging in /usr/local/lib/python3.8/dist-packages (from onnxslim) (24.0)
Collecting coloredlogs (from onnxruntime)
Downloading coloredlogs-15.0.1-py2.py3-none-any.whl.metadata (12 kB)
Collecting flatbuffers (from onnxruntime)
Downloading flatbuffers-25.2.10-py2.py3-none-any.whl.metadata (875 bytes)
Requirement already satisfied: humanfriendly>=9.1 in /usr/local/lib/python3.8/dist-packages (from coloredlogs->onnxruntime) (10.0)
Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.8/dist-packages (from sympy->onnxslim) (1.3.0)
Downloading onnx-1.17.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (15.9 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 15.9/15.9 MB 3.7 MB/s eta 0:00:00
Downloading onnxslim-0.1.48-py3-none-any.whl (142 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 142.9/142.9 kB 4.3 MB/s eta 0:00:00
Downloading onnxruntime-1.19.2-cp38-cp38-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl (11.5 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 11.5/11.5 MB 3.9 MB/s eta 0:00:00
Downloading protobuf-5.29.3-cp38-abi3-manylinux2014_aarch64.whl (319 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 319.6/319.6 kB 4.0 MB/s eta 0:00:00
Downloading coloredlogs-15.0.1-py2.py3-none-any.whl (46 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 46.0/46.0 kB 6.4 MB/s eta 0:00:00
Downloading flatbuffers-25.2.10-py2.py3-none-any.whl (30 kB)
Installing collected packages: flatbuffers, protobuf, coloredlogs, onnxruntime, onnx, onnxslim
Successfully installed coloredlogs-15.0.1 flatbuffers-25.2.10 onnx-1.17.0 onnxruntime-1.19.2 onnxslim-0.1.48 protobuf-5.29.3
requirements: AutoUpdate success ✅ 28.8s, installed 3 packages: ['onnx>=1.12.0', 'onnxslim', 'onnxruntime']
requirements: ⚠️ Restart runtime or rerun command for updates to take effect
ONNX: starting export with onnx 1.17.0 opset 19...
ONNX: slimming with onnxslim 0.1.48...
ONNX: export success ✅ 35.3s, saved as 'yolo11n.onnx' (10.2 MB)
Export complete (38.6s)
Results saved to /code/dt-machine-learning-base-pytorch
Predict: yolo predict task=detect model=yolo11n.onnx imgsz=640
Validate: yolo val task=detect model=yolo11n.onnx imgsz=640 data=/usr/src/ultralytics/ultralytics/cfg/datasets/coco.yaml
Visualize: https://netron.app
Loading yolo11n.onnx for ONNX Runtime inference...
requirements: Ultralytics requirement ['numpy==1.23.5'] not found, attempting AutoUpdate...
[notice] A new release of pip is available: 24.0 -> 25.0.1
[notice] To update, run: python3 -m pip install --upgrade pip
Collecting numpy==1.23.5
Downloading numpy-1.23.5-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl.metadata (2.3 kB)
Downloading numpy-1.23.5-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (14.0 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 14.0/14.0 MB 3.3 MB/s eta 0:00:00
Installing collected packages: numpy
Attempting uninstall: numpy
Found existing installation: numpy 1.24.4
Uninstalling numpy-1.24.4:
Successfully uninstalled numpy-1.24.4
Successfully installed numpy-1.23.5
requirements: AutoUpdate success ✅ 21.9s, installed 1 package: ['numpy==1.23.5']
requirements: ⚠️ Restart runtime or rerun command for updates to take effect
Using ONNX Runtime CPUExecutionProvider
Loading yolo11n.onnx for ONNX Runtime inference...
Using ONNX Runtime CPUExecutionProvider
Setting batch=1 input of shape (1, 3, 640, 640)
val: Scanning /code/dt-machine-learning-base-pytorch/datasets/coco8/labels/val.cache... 4 images, 0 backgrounds, 0 corrupt: 100%|██████████| 4/4 [00:00<?, ?it/s]
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 4/4 [00:02<00:00, 1.71it/s]
all 4 17 0.846 0.637 0.85 0.608
Speed: 8.0ms preprocess, 536.9ms inference, 0.0ms loss, 17.5ms postprocess per image
PyTorch: starting from 'yolo11n.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) (1, 84, 8400) (5.4 MB)
requirements: Ultralytics requirement ['openvino>=2024.0.0,<2025.0.0'] not found, attempting AutoUpdate...
[notice] A new release of pip is available: 24.0 -> 25.0.1
[notice] To update, run: python3 -m pip install --upgrade pip
Collecting openvino<2025.0.0,>=2024.0.0
Downloading openvino-2024.4.0-16579-cp38-cp38-manylinux_2_31_aarch64.whl.metadata (8.3 kB)
Requirement already satisfied: numpy<2.1.0,>=1.16.6 in /usr/local/lib/python3.8/dist-packages (from openvino<2025.0.0,>=2024.0.0) (1.23.5)
Collecting openvino-telemetry>=2023.2.1 (from openvino<2025.0.0,>=2024.0.0)
Downloading openvino_telemetry-2025.0.1-py3-none-any.whl.metadata (2.3 kB)
Requirement already satisfied: packaging in /usr/local/lib/python3.8/dist-packages (from openvino<2025.0.0,>=2024.0.0) (24.0)
Downloading openvino-2024.4.0-16579-cp38-cp38-manylinux_2_31_aarch64.whl (24.5 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 24.5/24.5 MB 3.5 MB/s eta 0:00:00
Downloading openvino_telemetry-2025.0.1-py3-none-any.whl (24 kB)
Installing collected packages: openvino-telemetry, openvino
Successfully installed openvino-2024.4.0 openvino-telemetry-2025.0.1
requirements: AutoUpdate success ✅ 16.6s, installed 1 package: ['openvino>=2024.0.0,<2025.0.0']
requirements: ⚠️ Restart runtime or rerun command for updates to take effect
OpenVINO: starting export with openvino 2024.4.0-16579-c3152d32c9c-releases/2024/4...
OpenVINO: export success ✅ 35.5s, saved as 'yolo11n_openvino_model/' (10.4 MB)
Export complete (38.8s)
Results saved to /code/dt-machine-learning-base-pytorch
Predict: yolo predict task=detect model=yolo11n_openvino_model imgsz=640
Validate: yolo val task=detect model=yolo11n_openvino_model imgsz=640 data=/usr/src/ultralytics/ultralytics/cfg/datasets/coco.yaml
Visualize: https://netron.app
Loading yolo11n_openvino_model for OpenVINO inference...
Using OpenVINO LATENCY mode for batch=1 inference...
Loading yolo11n_openvino_model for OpenVINO inference...
Using OpenVINO LATENCY mode for batch=1 inference...
Setting batch=1 input of shape (1, 3, 640, 640)
val: Scanning /code/dt-machine-learning-base-pytorch/datasets/coco8/labels/val.cache... 4 images, 0 backgrounds, 0 corrupt: 100%|██████████| 4/4 [00:00<?, ?it/s]
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 4/4 [00:01<00:00, 2.03it/s]
all 4 17 0.846 0.637 0.85 0.608
Speed: 5.2ms preprocess, 462.3ms inference, 0.0ms loss, 6.5ms postprocess per image
ERROR ❌️ Benchmark failure for TensorRT: inference not supported on CPU
ERROR ❌️ Benchmark failure for CoreML: CoreML and TF.js export only supported on macOS and non-aarch64 Linux
PyTorch: starting from 'yolo11n.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) (1, 84, 8400) (5.4 MB)
requirements: Ultralytics requirement ['tensorflow-aarch64>=2.0.0'] not found, attempting AutoUpdate...
error: subprocess-exited-with-error
× Building wheel for h5py (pyproject.toml) did not run successfully.
│ exit code: 1
╰─> [75 lines of output]
running bdist_wheel
running build
running build_py
creating build/lib.linux-aarch64-cpython-38/h5py
copying h5py/h5py_warnings.py -> build/lib.linux-aarch64-cpython-38/h5py
copying h5py/version.py -> build/lib.linux-aarch64-cpython-38/h5py
copying h5py/ipy_completer.py -> build/lib.linux-aarch64-cpython-38/h5py
copying h5py/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py
creating build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/vds.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/selections.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/compat.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/dataset.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/selections2.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/group.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/dims.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/base.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/filters.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/files.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/attrs.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/datatype.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
creating build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_completions.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dataset.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/conftest.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file_alignment.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_datatype.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_ros3.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dtype.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_attribute_create.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file2.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_base.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5o.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file_image.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_selections.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_slicing.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_attrs.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5f.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_attrs_data.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5p.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_filters.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_objects.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dataset_getitem.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dataset_swmr.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5t.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/common.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_group.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dims_dimensionproxy.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_big_endian_file.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5pl.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_errors.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5z.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5d_direct_chunk.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dimension_scales.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
creating build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
copying h5py/tests/data_files/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
creating build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/test_highlevel_vds.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/test_lowlevel_vds.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/test_virtual_source.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/data_files/vlen_string_s390x.h5 -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
copying h5py/tests/data_files/vlen_string_dset_utc.h5 -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
copying h5py/tests/data_files/vlen_string_dset.h5 -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
warning: build_py: byte-compiling is disabled, skipping.
running build_ext
Loading library to get build settings and version: libhdf5.so
error: Unable to load dependency HDF5, make sure HDF5 is installed properly
Library dirs checked: []
error: libhdf5.so: cannot open shared object file: No such file or directory
[end of output]
note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for h5py
ERROR: Could not build wheels for h5py, which is required to install pyproject.toml-based projects
[notice] A new release of pip is available: 24.0 -> 25.0.1
[notice] To update, run: python3 -m pip install --upgrade pip
Retry 1/2 failed: Command 'pip install --no-cache-dir "tensorflow-aarch64>=2.0.0" ' returned non-zero exit status 1.
error: subprocess-exited-with-error
× Building wheel for h5py (pyproject.toml) did not run successfully.
│ exit code: 1
╰─> [75 lines of output]
running bdist_wheel
running build
running build_py
creating build/lib.linux-aarch64-cpython-38/h5py
copying h5py/h5py_warnings.py -> build/lib.linux-aarch64-cpython-38/h5py
copying h5py/version.py -> build/lib.linux-aarch64-cpython-38/h5py
copying h5py/ipy_completer.py -> build/lib.linux-aarch64-cpython-38/h5py
copying h5py/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py
creating build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/vds.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/selections.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/compat.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/dataset.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/selections2.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/group.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/dims.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/base.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/filters.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/files.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/attrs.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/datatype.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
creating build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_completions.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dataset.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/conftest.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file_alignment.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_datatype.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_ros3.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dtype.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_attribute_create.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file2.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_base.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5o.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file_image.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_selections.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_slicing.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_attrs.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5f.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_attrs_data.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5p.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_filters.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_objects.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dataset_getitem.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dataset_swmr.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5t.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/common.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_group.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dims_dimensionproxy.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_big_endian_file.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5pl.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_errors.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5z.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5d_direct_chunk.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dimension_scales.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
creating build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
copying h5py/tests/data_files/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
creating build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/test_highlevel_vds.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/test_lowlevel_vds.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/test_virtual_source.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/data_files/vlen_string_s390x.h5 -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
copying h5py/tests/data_files/vlen_string_dset_utc.h5 -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
copying h5py/tests/data_files/vlen_string_dset.h5 -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
warning: build_py: byte-compiling is disabled, skipping.
running build_ext
Loading library to get build settings and version: libhdf5.so
error: Unable to load dependency HDF5, make sure HDF5 is installed properly
Library dirs checked: []
error: libhdf5.so: cannot open shared object file: No such file or directory
[end of output]
note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for h5py
ERROR: Could not build wheels for h5py, which is required to install pyproject.toml-based projects
[notice] A new release of pip is available: 24.0 -> 25.0.1
[notice] To update, run: python3 -m pip install --upgrade pip
Retry 2/2 failed: Command 'pip install --no-cache-dir "tensorflow-aarch64>=2.0.0" ' returned non-zero exit status 1.
requirements: ❌ Command 'pip install --no-cache-dir "tensorflow-aarch64>=2.0.0" ' returned non-zero exit status 1.
TensorFlow SavedModel: export failure ❌ 230.7s: No module named 'tensorflow'
ERROR ❌️ Benchmark failure for TensorFlow SavedModel: No module named 'tensorflow'
PyTorch: starting from 'yolo11n.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) (1, 84, 8400) (5.4 MB)
requirements: Ultralytics requirement ['tensorflow-aarch64>=2.0.0'] not found, attempting AutoUpdate...
error: subprocess-exited-with-error
× Building wheel for h5py (pyproject.toml) did not run successfully.
│ exit code: 1
╰─> [75 lines of output]
running bdist_wheel
running build
running build_py
creating build/lib.linux-aarch64-cpython-38/h5py
copying h5py/h5py_warnings.py -> build/lib.linux-aarch64-cpython-38/h5py
copying h5py/version.py -> build/lib.linux-aarch64-cpython-38/h5py
copying h5py/ipy_completer.py -> build/lib.linux-aarch64-cpython-38/h5py
copying h5py/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py
creating build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/vds.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/selections.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/compat.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/dataset.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/selections2.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/group.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/dims.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/base.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/filters.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/files.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/attrs.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/datatype.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
creating build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_completions.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dataset.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/conftest.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file_alignment.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_datatype.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_ros3.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dtype.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_attribute_create.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file2.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_base.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5o.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file_image.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_selections.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_slicing.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_attrs.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5f.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_attrs_data.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5p.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_filters.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_objects.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dataset_getitem.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dataset_swmr.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5t.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/common.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_group.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dims_dimensionproxy.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_big_endian_file.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5pl.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_errors.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5z.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5d_direct_chunk.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dimension_scales.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
creating build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
copying h5py/tests/data_files/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
creating build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/test_highlevel_vds.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/test_lowlevel_vds.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/test_virtual_source.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/data_files/vlen_string_s390x.h5 -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
copying h5py/tests/data_files/vlen_string_dset_utc.h5 -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
copying h5py/tests/data_files/vlen_string_dset.h5 -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
warning: build_py: byte-compiling is disabled, skipping.
running build_ext
Loading library to get build settings and version: libhdf5.so
error: Unable to load dependency HDF5, make sure HDF5 is installed properly
Library dirs checked: []
error: libhdf5.so: cannot open shared object file: No such file or directory
[end of output]
note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for h5py
ERROR: Could not build wheels for h5py, which is required to install pyproject.toml-based projects
[notice] A new release of pip is available: 24.0 -> 25.0.1
[notice] To update, run: python3 -m pip install --upgrade pip
Retry 1/2 failed: Command 'pip install --no-cache-dir "tensorflow-aarch64>=2.0.0" ' returned non-zero exit status 1.
error: subprocess-exited-with-error
× Building wheel for h5py (pyproject.toml) did not run successfully.
│ exit code: 1
╰─> [75 lines of output]
running bdist_wheel
running build
running build_py
creating build/lib.linux-aarch64-cpython-38/h5py
copying h5py/h5py_warnings.py -> build/lib.linux-aarch64-cpython-38/h5py
copying h5py/version.py -> build/lib.linux-aarch64-cpython-38/h5py
copying h5py/ipy_completer.py -> build/lib.linux-aarch64-cpython-38/h5py
copying h5py/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py
creating build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/vds.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/selections.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/compat.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/dataset.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/selections2.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/group.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/dims.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/base.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/filters.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/files.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/attrs.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/datatype.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
creating build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_completions.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dataset.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/conftest.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file_alignment.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_datatype.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_ros3.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dtype.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_attribute_create.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file2.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_base.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5o.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file_image.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_selections.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_slicing.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_attrs.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5f.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_attrs_data.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5p.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_filters.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_objects.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dataset_getitem.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dataset_swmr.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5t.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/common.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_group.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dims_dimensionproxy.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_big_endian_file.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5pl.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_errors.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5z.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5d_direct_chunk.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dimension_scales.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
creating build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
copying h5py/tests/data_files/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
creating build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/test_highlevel_vds.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/test_lowlevel_vds.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/test_virtual_source.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/data_files/vlen_string_s390x.h5 -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
copying h5py/tests/data_files/vlen_string_dset_utc.h5 -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
copying h5py/tests/data_files/vlen_string_dset.h5 -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
warning: build_py: byte-compiling is disabled, skipping.
running build_ext
Loading library to get build settings and version: libhdf5.so
error: Unable to load dependency HDF5, make sure HDF5 is installed properly
Library dirs checked: []
error: libhdf5.so: cannot open shared object file: No such file or directory
[end of output]
note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for h5py
ERROR: Could not build wheels for h5py, which is required to install pyproject.toml-based projects
[notice] A new release of pip is available: 24.0 -> 25.0.1
[notice] To update, run: python3 -m pip install --upgrade pip
Retry 2/2 failed: Command 'pip install --no-cache-dir "tensorflow-aarch64>=2.0.0" ' returned non-zero exit status 1.
requirements: ❌ Command 'pip install --no-cache-dir "tensorflow-aarch64>=2.0.0" ' returned non-zero exit status 1.
TensorFlow SavedModel: export failure ❌ 216.5s: No module named 'tensorflow'
ERROR ❌️ Benchmark failure for TensorFlow GraphDef: No module named 'tensorflow'
PyTorch: starting from 'yolo11n.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) (1, 84, 8400) (5.4 MB)
requirements: Ultralytics requirement ['tensorflow-aarch64>=2.0.0'] not found, attempting AutoUpdate...
error: subprocess-exited-with-error
× Building wheel for h5py (pyproject.toml) did not run successfully.
│ exit code: 1
╰─> [75 lines of output]
running bdist_wheel
running build
running build_py
creating build/lib.linux-aarch64-cpython-38/h5py
copying h5py/h5py_warnings.py -> build/lib.linux-aarch64-cpython-38/h5py
copying h5py/version.py -> build/lib.linux-aarch64-cpython-38/h5py
copying h5py/ipy_completer.py -> build/lib.linux-aarch64-cpython-38/h5py
copying h5py/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py
creating build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/vds.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/selections.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/compat.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/dataset.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/selections2.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/group.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/dims.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/base.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/filters.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/files.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/attrs.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/datatype.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
creating build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_completions.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dataset.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/conftest.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file_alignment.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_datatype.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_ros3.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dtype.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_attribute_create.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file2.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_base.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5o.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file_image.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_selections.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_slicing.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_attrs.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5f.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_attrs_data.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5p.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_filters.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_objects.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dataset_getitem.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dataset_swmr.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5t.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/common.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_group.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dims_dimensionproxy.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_big_endian_file.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5pl.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_errors.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5z.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5d_direct_chunk.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dimension_scales.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
creating build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
copying h5py/tests/data_files/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
creating build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/test_highlevel_vds.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/test_lowlevel_vds.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/test_virtual_source.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/data_files/vlen_string_s390x.h5 -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
copying h5py/tests/data_files/vlen_string_dset_utc.h5 -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
copying h5py/tests/data_files/vlen_string_dset.h5 -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
warning: build_py: byte-compiling is disabled, skipping.
running build_ext
Loading library to get build settings and version: libhdf5.so
error: Unable to load dependency HDF5, make sure HDF5 is installed properly
Library dirs checked: []
error: libhdf5.so: cannot open shared object file: No such file or directory
[end of output]
note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for h5py
ERROR: Could not build wheels for h5py, which is required to install pyproject.toml-based projects
[notice] A new release of pip is available: 24.0 -> 25.0.1
[notice] To update, run: python3 -m pip install --upgrade pip
Retry 1/2 failed: Command 'pip install --no-cache-dir "tensorflow-aarch64>=2.0.0" ' returned non-zero exit status 1.
error: subprocess-exited-with-error
× Building wheel for h5py (pyproject.toml) did not run successfully.
│ exit code: 1
╰─> [75 lines of output]
running bdist_wheel
running build
running build_py
creating build/lib.linux-aarch64-cpython-38/h5py
copying h5py/h5py_warnings.py -> build/lib.linux-aarch64-cpython-38/h5py
copying h5py/version.py -> build/lib.linux-aarch64-cpython-38/h5py
copying h5py/ipy_completer.py -> build/lib.linux-aarch64-cpython-38/h5py
copying h5py/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py
creating build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/vds.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/selections.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/compat.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/dataset.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/selections2.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/group.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/dims.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/base.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/filters.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/files.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/attrs.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
copying h5py/_hl/datatype.py -> build/lib.linux-aarch64-cpython-38/h5py/_hl
creating build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_completions.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dataset.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/conftest.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file_alignment.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_datatype.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_ros3.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dtype.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_attribute_create.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file2.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_base.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5o.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file_image.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_selections.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_slicing.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_attrs.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5f.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_attrs_data.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5p.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_filters.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_objects.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dataset_getitem.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dataset_swmr.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5t.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/common.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_group.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dims_dimensionproxy.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_big_endian_file.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5pl.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_errors.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5z.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_h5d_direct_chunk.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_file.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
copying h5py/tests/test_dimension_scales.py -> build/lib.linux-aarch64-cpython-38/h5py/tests
creating build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
copying h5py/tests/data_files/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
creating build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/test_highlevel_vds.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/__init__.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/test_lowlevel_vds.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/test_vds/test_virtual_source.py -> build/lib.linux-aarch64-cpython-38/h5py/tests/test_vds
copying h5py/tests/data_files/vlen_string_s390x.h5 -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
copying h5py/tests/data_files/vlen_string_dset_utc.h5 -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
copying h5py/tests/data_files/vlen_string_dset.h5 -> build/lib.linux-aarch64-cpython-38/h5py/tests/data_files
warning: build_py: byte-compiling is disabled, skipping.
running build_ext
Loading library to get build settings and version: libhdf5.so
error: Unable to load dependency HDF5, make sure HDF5 is installed properly
Library dirs checked: []
error: libhdf5.so: cannot open shared object file: No such file or directory
[end of output]
note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for h5py
ERROR: Could not build wheels for h5py, which is required to install pyproject.toml-based projects
[notice] A new release of pip is available: 24.0 -> 25.0.1
[notice] To update, run: python3 -m pip install --upgrade pip
Retry 2/2 failed: Command 'pip install --no-cache-dir "tensorflow-aarch64>=2.0.0" ' returned non-zero exit status 1.
requirements: ❌ Command 'pip install --no-cache-dir "tensorflow-aarch64>=2.0.0" ' returned non-zero exit status 1.
TensorFlow SavedModel: export failure ❌ 222.2s: No module named 'tensorflow'
ERROR ❌️ Benchmark failure for TensorFlow Lite: No module named 'tensorflow'
ERROR ❌️ Benchmark failure for TensorFlow Edge TPU: Edge TPU export only supported on non-aarch64 Linux
ERROR ❌️ Benchmark failure for TensorFlow.js: CoreML and TF.js export only supported on macOS and non-aarch64 Linux
PyTorch: starting from 'yolo11n.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) (1, 84, 8400) (5.4 MB)
requirements: Ultralytics requirements ['paddlepaddle', 'x2paddle'] not found, attempting AutoUpdate...
[notice] A new release of pip is available: 24.0 -> 25.0.1
[notice] To update, run: python3 -m pip install --upgrade pip
Collecting paddlepaddle
Downloading paddlepaddle-2.6.2-cp38-cp38-manylinux2014_aarch64.whl.metadata (8.6 kB)
Collecting x2paddle
Downloading x2paddle-1.6.0-py3-none-any.whl.metadata (863 bytes)
Collecting httpx (from paddlepaddle)
Downloading httpx-0.28.1-py3-none-any.whl.metadata (7.1 kB)
Requirement already satisfied: numpy>=1.13 in /usr/local/lib/python3.8/dist-packages (from paddlepaddle) (1.23.5)
Requirement already satisfied: Pillow in /usr/local/lib/python3.8/dist-packages (from paddlepaddle) (10.1.0)
Requirement already satisfied: decorator in /usr/lib/python3/dist-packages (from paddlepaddle) (4.4.2)
Collecting astor (from paddlepaddle)
Downloading astor-0.8.1-py2.py3-none-any.whl.metadata (4.2 kB)
Collecting opt-einsum==3.3.0 (from paddlepaddle)
Downloading opt_einsum-3.3.0-py3-none-any.whl.metadata (6.5 kB)
Requirement already satisfied: protobuf>=3.20.2 in /usr/local/lib/python3.8/dist-packages (from paddlepaddle) (5.29.3)
Requirement already satisfied: sympy in /usr/local/lib/python3.8/dist-packages (from x2paddle) (1.13.3)
Requirement already satisfied: packaging in /usr/local/lib/python3.8/dist-packages (from x2paddle) (24.0)
Collecting anyio (from httpx->paddlepaddle)
Downloading anyio-4.5.2-py3-none-any.whl.metadata (4.7 kB)
Requirement already satisfied: certifi in /usr/local/lib/python3.8/dist-packages (from httpx->paddlepaddle) (2024.2.2)
Collecting httpcore==1.* (from httpx->paddlepaddle)
Downloading httpcore-1.0.7-py3-none-any.whl.metadata (21 kB)
Requirement already satisfied: idna in /usr/local/lib/python3.8/dist-packages (from httpx->paddlepaddle) (3.7)
Collecting h11<0.15,>=0.13 (from httpcore==1.*->httpx->paddlepaddle)
Downloading h11-0.14.0-py3-none-any.whl.metadata (8.2 kB)
Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.8/dist-packages (from sympy->x2paddle) (1.3.0)
Collecting sniffio>=1.1 (from anyio->httpx->paddlepaddle)
Downloading sniffio-1.3.1-py3-none-any.whl.metadata (3.9 kB)
Collecting exceptiongroup>=1.0.2 (from anyio->httpx->paddlepaddle)
Downloading exceptiongroup-1.2.2-py3-none-any.whl.metadata (6.6 kB)
Requirement already satisfied: typing-extensions>=4.1 in /usr/local/lib/python3.8/dist-packages (from anyio->httpx->paddlepaddle) (4.11.0)
Downloading paddlepaddle-2.6.2-cp38-cp38-manylinux2014_aarch64.whl (74.3 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 74.3/74.3 MB 4.4 MB/s eta 0:00:00
Downloading opt_einsum-3.3.0-py3-none-any.whl (65 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 65.5/65.5 kB 9.5 MB/s eta 0:00:00
Downloading x2paddle-1.6.0-py3-none-any.whl (325 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 325.9/325.9 kB 5.0 MB/s eta 0:00:00
Downloading astor-0.8.1-py2.py3-none-any.whl (27 kB)
Downloading httpx-0.28.1-py3-none-any.whl (73 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 73.5/73.5 kB 9.0 MB/s eta 0:00:00
Downloading httpcore-1.0.7-py3-none-any.whl (78 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 78.6/78.6 kB 9.5 MB/s eta 0:00:00
Downloading anyio-4.5.2-py3-none-any.whl (89 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 89.8/89.8 kB 4.2 MB/s eta 0:00:00
Downloading exceptiongroup-1.2.2-py3-none-any.whl (16 kB)
Downloading h11-0.14.0-py3-none-any.whl (58 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 58.3/58.3 kB 11.9 MB/s eta 0:00:00
Downloading sniffio-1.3.1-py3-none-any.whl (10 kB)
Installing collected packages: sniffio, opt-einsum, h11, exceptiongroup, astor, x2paddle, httpcore, anyio, httpx, paddlepaddle
Successfully installed anyio-4.5.2 astor-0.8.1 exceptiongroup-1.2.2 h11-0.14.0 httpcore-1.0.7 httpx-0.28.1 opt-einsum-3.3.0 paddlepaddle-2.6.2 sniffio-1.3.1 x2paddle-1.6.0
requirements: AutoUpdate success ✅ 46.3s, installed 2 packages: ['paddlepaddle', 'x2paddle']
requirements: ⚠️ Restart runtime or rerun command for updates to take effect
PaddlePaddle: starting export with X2Paddle 1.6.0...
Now translating model from PyTorch to Paddle.
Model optimizing ...
Model optimized!
Exporting inference model from python code ('/code/dt-machine-learning-base-pytorch/yolo11n_paddle_model/x2paddle_code.py')...
I0301 11:43:09.729400 136 program_interpreter.cc:212] New Executor is Running.
Successfully exported Paddle static graph model!
================================================
Model Converted! Fill this survey to help X2Paddle better, https://iwenjuan.baidu.com/?code=npyd51
================================================
PaddlePaddle: export success ✅ 74.3s, saved as 'yolo11n_paddle_model/' (20.4 MB)
Export complete (77.5s)
Results saved to /code/dt-machine-learning-base-pytorch
Predict: yolo predict task=detect model=yolo11n_paddle_model imgsz=640
Validate: yolo val task=detect model=yolo11n_paddle_model imgsz=640 data=/usr/src/ultralytics/ultralytics/cfg/datasets/coco.yaml
Visualize: https://netron.app
Loading yolo11n_paddle_model for PaddlePaddle inference...
--- Running analysis [ir_graph_build_pass]
I0301 11:43:09.918308 136 executor.cc:187] Old Executor is Running.
--- Running analysis [ir_analysis_pass]
--- Running IR pass [simplify_with_basic_ops_pass]
--- Running IR pass [layer_norm_fuse_pass]
--- Running IR pass [attention_lstm_fuse_pass]
--- Running IR pass [seqconv_eltadd_relu_fuse_pass]
--- Running IR pass [seqpool_cvm_concat_fuse_pass]
--- Running IR pass [mul_lstm_fuse_pass]
--- Running IR pass [fc_gru_fuse_pass]
--- Running IR pass [mul_gru_fuse_pass]
--- Running IR pass [seq_concat_fc_fuse_pass]
--- Running IR pass [gpu_cpu_squeeze2_matmul_fuse_pass]
--- Running IR pass [gpu_cpu_reshape2_matmul_fuse_pass]
--- Running IR pass [gpu_cpu_flatten2_matmul_fuse_pass]
--- Running IR pass [matmul_v2_scale_fuse_pass]
--- Running IR pass [gpu_cpu_map_matmul_v2_to_mul_pass]
--- Running IR pass [gpu_cpu_map_matmul_v2_to_matmul_pass]
I0301 11:43:10.074098 136 fuse_pass_base.cc:59] --- detected 2 subgraphs
--- Running IR pass [matmul_scale_fuse_pass]
I0301 11:43:10.080572 136 fuse_pass_base.cc:59] --- detected 1 subgraphs
--- Running IR pass [gpu_cpu_map_matmul_to_mul_pass]
--- Running IR pass [fc_fuse_pass]
--- Running IR pass [repeated_fc_relu_fuse_pass]
--- Running IR pass [squared_mat_sub_fuse_pass]
--- Running IR pass [conv_bn_fuse_pass]
--- Running IR pass [conv_eltwiseadd_bn_fuse_pass]
--- Running IR pass [conv_transpose_bn_fuse_pass]
--- Running IR pass [conv_transpose_eltwiseadd_bn_fuse_pass]
--- Running IR pass [is_test_pass]
--- Running IR pass [constant_folding_pass]
I0301 11:43:10.374950 136 fuse_pass_base.cc:59] --- detected 87 subgraphs
--- Running analysis [save_optimized_model_pass]
--- Running analysis [ir_params_sync_among_devices_pass]
--- Running analysis [adjust_cudnn_workspace_size_pass]
--- Running analysis [inference_op_replace_pass]
--- Running analysis [ir_graph_to_program_pass]
I0301 11:43:10.590739 136 analysis_predictor.cc:1838] ======= optimize end =======
I0301 11:43:10.611150 136 naive_executor.cc:200] --- skip [feed], feed -> x0
I0301 11:43:10.621057 136 naive_executor.cc:200] --- skip [save_infer_model/scale_0.tmp_0], fetch -> fetch
Loading yolo11n_paddle_model for PaddlePaddle inference...
--- Running analysis [ir_graph_build_pass]
--- Running analysis [ir_analysis_pass]
--- Running IR pass [simplify_with_basic_ops_pass]
--- Running IR pass [layer_norm_fuse_pass]
--- Running IR pass [attention_lstm_fuse_pass]
--- Running IR pass [seqconv_eltadd_relu_fuse_pass]
--- Running IR pass [seqpool_cvm_concat_fuse_pass]
--- Running IR pass [mul_lstm_fuse_pass]
--- Running IR pass [fc_gru_fuse_pass]
--- Running IR pass [mul_gru_fuse_pass]
--- Running IR pass [seq_concat_fc_fuse_pass]
--- Running IR pass [gpu_cpu_squeeze2_matmul_fuse_pass]
--- Running IR pass [gpu_cpu_reshape2_matmul_fuse_pass]
--- Running IR pass [gpu_cpu_flatten2_matmul_fuse_pass]
--- Running IR pass [matmul_v2_scale_fuse_pass]
--- Running IR pass [gpu_cpu_map_matmul_v2_to_mul_pass]
--- Running IR pass [gpu_cpu_map_matmul_v2_to_matmul_pass]
I0301 11:43:12.751484 136 fuse_pass_base.cc:59] --- detected 2 subgraphs
--- Running IR pass [matmul_scale_fuse_pass]
I0301 11:43:12.757658 136 fuse_pass_base.cc:59] --- detected 1 subgraphs
--- Running IR pass [gpu_cpu_map_matmul_to_mul_pass]
--- Running IR pass [fc_fuse_pass]
--- Running IR pass [repeated_fc_relu_fuse_pass]
--- Running IR pass [squared_mat_sub_fuse_pass]
--- Running IR pass [conv_bn_fuse_pass]
--- Running IR pass [conv_eltwiseadd_bn_fuse_pass]
--- Running IR pass [conv_transpose_bn_fuse_pass]
--- Running IR pass [conv_transpose_eltwiseadd_bn_fuse_pass]
--- Running IR pass [is_test_pass]
--- Running IR pass [constant_folding_pass]
I0301 11:43:13.069953 136 fuse_pass_base.cc:59] --- detected 87 subgraphs
--- Running analysis [save_optimized_model_pass]
--- Running analysis [ir_params_sync_among_devices_pass]
--- Running analysis [adjust_cudnn_workspace_size_pass]
--- Running analysis [inference_op_replace_pass]
--- Running analysis [ir_graph_to_program_pass]
I0301 11:43:13.300237 136 analysis_predictor.cc:1838] ======= optimize end =======
I0301 11:43:13.309646 136 naive_executor.cc:200] --- skip [feed], feed -> x0
I0301 11:43:13.319238 136 naive_executor.cc:200] --- skip [save_infer_model/scale_0.tmp_0], fetch -> fetch
Setting batch=1 input of shape (1, 3, 640, 640)
val: Scanning /code/dt-machine-learning-base-pytorch/datasets/coco8/labels/val.cache... 4 images, 0 backgrounds, 0 corrupt: 100%|██████████| 4/4 [00:00<?, ?it/s]
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 4/4 [00:06<00:00, 1.69s/it]
all 4 17 0.846 0.637 0.85 0.608
Speed: 4.6ms preprocess, 1663.4ms inference, 0.0ms loss, 5.2ms postprocess per image
PyTorch: starting from 'yolo11n.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) (1, 84, 8400) (5.4 MB)
ONNX: starting export with onnx 1.17.0 opset 19...
ONNX: slimming with onnxslim 0.1.48...
ONNX: export success ✅ 5.9s, saved as 'yolo11n.onnx' (10.2 MB)
requirements: Ultralytics requirement ['MNN>=2.9.6'] not found, attempting AutoUpdate...
[notice] A new release of pip is available: 24.0 -> 25.0.1
[notice] To update, run: python3 -m pip install --upgrade pip
Collecting MNN>=2.9.6
Downloading MNN-3.1.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl.metadata (1.5 kB)
Requirement already satisfied: numpy in /usr/local/lib/python3.8/dist-packages (from MNN>=2.9.6) (1.23.5)
Downloading MNN-3.1.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (14.6 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 14.6/14.6 MB 3.6 MB/s eta 0:00:00
Installing collected packages: MNN
Successfully installed MNN-3.1.0
requirements: AutoUpdate success ✅ 11.7s, installed 1 package: ['MNN>=2.9.6']
requirements: ⚠️ Restart runtime or rerun command for updates to take effect
Can't open file:/sys/devices/system/cpu/cpufreq/cpuload/affected_cpus
Can't open file:/sys/devices/system/cpu/cpufreq/schedutil/affected_cpus
CPU Group: [ 0 1 2 3 ], 102000 - 1479000
The device supports: i8sdot:0, fp16:0, i8mm: 0, sve2: 0, sme2: 0
Can't open file:/sys/devices/system/cpu/cpufreq/cpuload/affected_cpus
Can't open file:/sys/devices/system/cpu/cpufreq/schedutil/affected_cpus
CPU Group: [ 0 1 2 3 ], 102000 - 1479000
The device supports: i8sdot:0, fp16:0, i8mm: 0, sve2: 0, sme2: 0
try 'pip install -U aliyun-log-python-sdk'
Collecting aliyun-log-python-sdk
Downloading aliyun_log_python_sdk-0.9.14.tar.gz (139 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 139.7/139.7 kB 1.6 MB/s eta 0:00:00
Preparing metadata (setup.py) ... done
Collecting dateparser (from aliyun-log-python-sdk)
Downloading dateparser-1.2.1-py3-none-any.whl.metadata (29 kB)
Collecting elasticsearch (from aliyun-log-python-sdk)
Downloading elasticsearch-8.17.1-py3-none-any.whl.metadata (8.8 kB)
Collecting jmespath (from aliyun-log-python-sdk)
Downloading jmespath-1.0.1-py3-none-any.whl.metadata (7.6 kB)
Requirement already satisfied: protobuf<6.0.0,>=3.20.3 in /usr/local/lib/python3.8/dist-packages (from aliyun-log-python-sdk) (5.29.3)
Requirement already satisfied: python-dateutil in /usr/local/lib/python3.8/dist-packages (from aliyun-log-python-sdk) (2.9.0.post0)
Requirement already satisfied: requests in /usr/local/lib/python3.8/dist-packages (from aliyun-log-python-sdk) (2.31.0)
Requirement already satisfied: six in /usr/lib/python3/dist-packages (from aliyun-log-python-sdk) (1.14.0)
Collecting pytz>=2024.2 (from dateparser->aliyun-log-python-sdk)
Downloading pytz-2025.1-py2.py3-none-any.whl.metadata (22 kB)
Collecting regex!=2019.02.19,!=2021.8.27,>=2015.06.24 (from dateparser->aliyun-log-python-sdk)
Downloading regex-2024.11.6-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl.metadata (40 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 40.5/40.5 kB 6.2 MB/s eta 0:00:00
Collecting tzlocal>=0.2 (from dateparser->aliyun-log-python-sdk)
Downloading tzlocal-5.2-py3-none-any.whl.metadata (7.8 kB)
Collecting elastic-transport<9,>=8.15.1 (from elasticsearch->aliyun-log-python-sdk)
Downloading elastic_transport-8.17.0-py3-none-any.whl.metadata (3.6 kB)
Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.8/dist-packages (from requests->aliyun-log-python-sdk) (3.3.2)
Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.8/dist-packages (from requests->aliyun-log-python-sdk) (3.7)
Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.8/dist-packages (from requests->aliyun-log-python-sdk) (2.2.1)
Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.8/dist-packages (from requests->aliyun-log-python-sdk) (2024.2.2)
Collecting backports.zoneinfo (from tzlocal>=0.2->dateparser->aliyun-log-python-sdk)
Downloading backports.zoneinfo-0.2.1.tar.gz (74 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 74.1/74.1 kB 9.2 MB/s eta 0:00:00
Installing build dependencies ... done
Getting requirements to build wheel ... done
Preparing metadata (pyproject.toml) ... done
Downloading dateparser-1.2.1-py3-none-any.whl (295 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 295.7/295.7 kB 5.2 MB/s eta 0:00:00
Downloading elasticsearch-8.17.1-py3-none-any.whl (653 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 654.0/654.0 kB 3.6 MB/s eta 0:00:00
Downloading jmespath-1.0.1-py3-none-any.whl (20 kB)
Downloading elastic_transport-8.17.0-py3-none-any.whl (64 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 64.5/64.5 kB 50.4 MB/s eta 0:00:00
Downloading pytz-2025.1-py2.py3-none-any.whl (507 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 507.9/507.9 kB 4.4 MB/s eta 0:00:00
Downloading regex-2024.11.6-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (783 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 783.6/783.6 kB 3.8 MB/s eta 0:00:00
Downloading tzlocal-5.2-py3-none-any.whl (17 kB)
Building wheels for collected packages: aliyun-log-python-sdk, backports.zoneinfo
Building wheel for aliyun-log-python-sdk (setup.py) ... done
Created wheel for aliyun-log-python-sdk: filename=aliyun_log_python_sdk-0.9.14-py3-none-any.whl size=179988 sha256=510df7dd2810fa884ced498f61dd2433dce3e04fcb90dd69a5e4b1bedde72948
Stored in directory: /tmp/pip-ephem-wheel-cache-w9h1dwn4/wheels/ab/7d/98/9c8d17906734a4fc9acfa7b1b1526f263adaefa9a4f7a85c84
Building wheel for backports.zoneinfo (pyproject.toml) ... done
Created wheel for backports.zoneinfo: filename=backports.zoneinfo-0.2.1-cp38-cp38-linux_aarch64.whl size=82104 sha256=1ce837e3f09557d743052d0a039d538c0c27625b8054d021f94afd61363c6833
Stored in directory: /tmp/pip-ephem-wheel-cache-w9h1dwn4/wheels/c7/de/cc/c405827ed64f81b56142f1e0075a970b2731b00d21983d54fb
Successfully built aliyun-log-python-sdk backports.zoneinfo
Installing collected packages: pytz, regex, jmespath, elastic-transport, backports.zoneinfo, tzlocal, elasticsearch, dateparser, aliyun-log-python-sdk
Attempting uninstall: pytz
Found existing installation: pytz 2024.1
Uninstalling pytz-2024.1:
Successfully uninstalled pytz-2024.1
Successfully installed aliyun-log-python-sdk-0.9.14 backports.zoneinfo-0.2.1 dateparser-1.2.1 elastic-transport-8.17.0 elasticsearch-8.17.1 jmespath-1.0.1 pytz-2025.1 regex-2024.11.6 tzlocal-5.2
[notice] A new release of pip is available: 24.0 -> 25.0.1
[notice] To update, run: python3 -m pip install --upgrade pip
MNN: starting export with MNN 3.1.0...
Start to Convert Other Model Format To MNN Model..., target version: 3.1
[11:44:22] :46: ONNX Model ir version: 9
[11:44:22] :47: ONNX Model opset version: 19
[11:44:22] :146: Check it out ==> /model.11/Resize_output_0 has empty input, the index is 1
[11:44:22] :146: Check it out ==> /model.14/Resize_output_0 has empty input, the index is 1
Start to Optimize the MNN Net...
inputTensors : [ images, ]
outputTensors: [ output0, ]
Converted Success!
MNN: export success ✅ 59.3s, saved as 'yolo11n.mnn' (10.1 MB)
Export complete (62.4s)
Results saved to /code/dt-machine-learning-base-pytorch
Predict: yolo predict task=detect model=yolo11n.mnn imgsz=640
Validate: yolo val task=detect model=yolo11n.mnn imgsz=640 data=/usr/src/ultralytics/ultralytics/cfg/datasets/coco.yaml
Visualize: https://netron.app
Loading yolo11n.mnn for MNN inference...
MNN use low precision
Loading yolo11n.mnn for MNN inference...
MNN use low precision
Setting batch=1 input of shape (1, 3, 640, 640)
val: Scanning /code/dt-machine-learning-base-pytorch/datasets/coco8/labels/val.cache... 4 images, 0 backgrounds, 0 corrupt: 100%|██████████| 4/4 [00:00<?, ?it/s]
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 4/4 [00:02<00:00, 1.73it/s]
all 4 17 0.846 0.637 0.85 0.608
Speed: 3.1ms preprocess, 552.8ms inference, 0.0ms loss, 5.2ms postprocess per image
PyTorch: starting from 'yolo11n.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) (1, 84, 8400) (5.4 MB)
TorchScript: starting export with torch 2.4.1...
TorchScript: export success ✅ 13.9s, saved as 'yolo11n.torchscript' (10.5 MB)
requirements: Ultralytics requirement ['ncnn'] not found, attempting AutoUpdate...
[notice] A new release of pip is available: 24.0 -> 25.0.1
[notice] To update, run: python3 -m pip install --upgrade pip
Collecting ncnn
Downloading ncnn-1.0.20241226-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl.metadata (27 kB)
Requirement already satisfied: numpy in /usr/local/lib/python3.8/dist-packages (from ncnn) (1.23.5)
Requirement already satisfied: tqdm in /usr/local/lib/python3.8/dist-packages (from ncnn) (4.66.2)
Requirement already satisfied: requests in /usr/local/lib/python3.8/dist-packages (from ncnn) (2.31.0)
Collecting portalocker (from ncnn)
Downloading portalocker-3.0.0-py3-none-any.whl.metadata (8.5 kB)
Requirement already satisfied: opencv-python in /usr/local/lib/python3.8/dist-packages (from ncnn) (4.11.0.86)
Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.8/dist-packages (from requests->ncnn) (3.3.2)
Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.8/dist-packages (from requests->ncnn) (3.7)
Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.8/dist-packages (from requests->ncnn) (2.2.1)
Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.8/dist-packages (from requests->ncnn) (2024.2.2)
Downloading ncnn-1.0.20241226-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (4.1 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 4.1/4.1 MB 3.2 MB/s eta 0:00:00
Downloading portalocker-3.0.0-py3-none-any.whl (19 kB)
Installing collected packages: portalocker, ncnn
Successfully installed ncnn-1.0.20241226 portalocker-3.0.0
requirements: AutoUpdate success ✅ 9.7s, installed 1 package: ['ncnn']
requirements: ⚠️ Restart runtime or rerun command for updates to take effect
NCNN: starting export with NCNN 1.0.20241226...
NCNN: WARNING ⚠️ PNNX not found. Attempting to download binary file from https://github.com/pnnx/pnnx/.
Note PNNX Binary file must be placed in current working directory or in /usr/local/lib/python3.8/dist-packages/ultralytics. See PNNX repo for full installation instructions.
NCNN: successfully found latest PNNX asset file pnnx-20241223-linux-aarch64.zip
Downloading https://github.com/pnnx/pnnx/releases/download/20241223/pnnx-20241223-linux-aarch64.zip to 'pnnx-20241223-linux-aarch64.zip'...
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 19.9M/19.9M [00:07<00:00, 2.84MB/s]
Unzipping pnnx-20241223-linux-aarch64.zip to /code/dt-machine-learning-base-pytorch/pnnx-20241223-linux-aarch64...: 100%|██████████| 3/3 [00:01<00:00, 2.96file/
NCNN: running '/usr/local/lib/python3.8/dist-packages/ultralytics/pnnx yolo11n.torchscript ncnnparam=yolo11n_ncnn_model/model.ncnn.param ncnnbin=yolo11n_ncnn_model/model.ncnn.bin ncnnpy=yolo11n_ncnn_model/model_ncnn.py pnnxparam=yolo11n_ncnn_model/model.pnnx.param pnnxbin=yolo11n_ncnn_model/model.pnnx.bin pnnxpy=yolo11n_ncnn_model/model_pnnx.py pnnxonnx=yolo11n_ncnn_model/model.pnnx.onnx fp16=0 device=cpu inputshape="[1, 3, 640, 640]"'
pnnxparam = yolo11n_ncnn_model/model.pnnx.param
pnnxbin = yolo11n_ncnn_model/model.pnnx.bin
pnnxpy = yolo11n_ncnn_model/model_pnnx.py
pnnxonnx = yolo11n_ncnn_model/model.pnnx.onnx
ncnnparam = yolo11n_ncnn_model/model.ncnn.param
ncnnbin = yolo11n_ncnn_model/model.ncnn.bin
ncnnpy = yolo11n_ncnn_model/model_ncnn.py
fp16 = 0
optlevel = 2
device = cpu
inputshape = [1,3,640,640]f32
inputshape2 =
customop =
moduleop =
get inputshape from traced inputs
inputshape = [1,3,640,640]f32
Error in cpuinfo: prctl(PR_SVE_GET_VL) failed
############# pass_level0
inline module = torch.nn.modules.linear.Identity
inline module = ultralytics.nn.modules.block.Attention
inline module = ultralytics.nn.modules.block.Bottleneck
inline module = ultralytics.nn.modules.block.C2PSA
inline module = ultralytics.nn.modules.block.C3k
inline module = ultralytics.nn.modules.block.C3k2
inline module = ultralytics.nn.modules.block.DFL
inline module = ultralytics.nn.modules.block.PSABlock
inline module = ultralytics.nn.modules.block.SPPF
inline module = ultralytics.nn.modules.conv.Concat
inline module = ultralytics.nn.modules.conv.Conv
inline module = ultralytics.nn.modules.conv.DWConv
inline module = ultralytics.nn.modules.head.Detect
inline module = torch.nn.modules.linear.Identity
inline module = ultralytics.nn.modules.block.Attention
inline module = ultralytics.nn.modules.block.Bottleneck
inline module = ultralytics.nn.modules.block.C2PSA
inline module = ultralytics.nn.modules.block.C3k
inline module = ultralytics.nn.modules.block.C3k2
inline module = ultralytics.nn.modules.block.DFL
inline module = ultralytics.nn.modules.block.PSABlock
inline module = ultralytics.nn.modules.block.SPPF
inline module = ultralytics.nn.modules.conv.Concat
inline module = ultralytics.nn.modules.conv.Conv
inline module = ultralytics.nn.modules.conv.DWConv
inline module = ultralytics.nn.modules.head.Detect
----------------
############# pass_level1
############# pass_level2
############# pass_level3
############# pass_level4
############# pass_level5
############# pass_ncnn
NCNN: export success ✅ 26.8s, saved as 'yolo11n_ncnn_model' (10.2 MB)
Export complete (43.8s)
Results saved to /code/dt-machine-learning-base-pytorch
Predict: yolo predict task=detect model=yolo11n_ncnn_model imgsz=640
Validate: yolo val task=detect model=yolo11n_ncnn_model imgsz=640 data=/usr/src/ultralytics/ultralytics/cfg/datasets/coco.yaml
Visualize: https://netron.app
Loading yolo11n_ncnn_model for NCNN inference...
Loading yolo11n_ncnn_model for NCNN inference...
Setting batch=1 input of shape (1, 3, 640, 640)
val: Scanning /code/dt-machine-learning-base-pytorch/datasets/coco8/labels/val.cache... 4 images, 0 backgrounds, 0 corrupt: 100%|██████████| 4/4 [00:00<?, ?it/s]
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 4/4 [00:01<00:00, 2.19it/s]
all 4 17 0.846 0.637 0.85 0.608
Speed: 6.8ms preprocess, 426.4ms inference, 0.0ms loss, 5.0ms postprocess per image
ERROR ❌️ Benchmark failure for IMX: IMX only supported for YOLOv8
ERROR ❌️ Benchmark failure for RKNN: inference not supported on CPU
Setup complete ✅ (4 CPUs, 3.9 GB RAM, 38.9/57.6 GB disk)
Benchmarks complete for yolo11n.pt on coco8.yaml at imgsz=640 (1029.31s)
Benchmarks legend: - ✅ Success - ❎ Export passed but validation failed - ❌️ Export failed
Format Status❔ Size (MB) metrics/mAP50-95(B) Inference time (ms/im) FPS
0 PyTorch ✅ 5.4 0.61 1316.52 0.76
1 TorchScript ✅ 10.5 0.6082 1761.91 0.57
2 ONNX ✅ 10.2 0.6082 536.89 1.86
3 OpenVINO ✅ 10.4 0.6082 462.34 2.16
4 TensorRT ❌ 0.0 - - -
5 CoreML ❌ 0.0 - - -
6 TensorFlow SavedModel ❌ 0.0 - - -
7 TensorFlow GraphDef ❌ 0.0 - - -
8 TensorFlow Lite ❌ 0.0 - - -
9 TensorFlow Edge TPU ❌ 0.0 - - -
10 TensorFlow.js ❌ 0.0 - - -
11 PaddlePaddle ✅ 20.4 0.6082 1663.41 0.6
12 MNN ✅ 10.1 0.6082 552.8 1.81
13 NCNN ✅ 10.2 0.6082 426.4 2.35
14 IMX ❌ 0.0 - - -
15 RKNN ❌ 0.0 - - -
💡 Learn more at https://docs.ultralytics.com/modes/benchmark
root@cd72a4fb68a2:/code/dt-machine-learning-base-pytorch#
Kommentit
Lähetä kommentti