search

ultralytics / ultralytics

Ultralytics YOLO11 🚀
https://docs.ultralytics.com
GNU Affero General Public License v3.0
31.12k stars 5.99k forks source link

yolo export model=yolov8n.pt format=tflite int8=true dynamic=true fails #15024

Open harufumigithub opened 2 months ago

harufumigithub commented 2 months ago

Search before asking

Ultralytics YOLO Component

Export

Bug

yolo export model=yolov8n.pt format=tflite int8=true dynamic=true fails

Environment

Ultralytics YOLOv8.2.74 🚀 Python-3.9.12 torch-1.13.1 CUDA:0 (NVIDIA GeForce RTX 3070 Laptop GPU, 7967MiB) Setup complete ✅ (16 CPUs, 62.4 GB RAM, 209.5/245.0 GB disk)

OS Linux-6.5.0-45-generic-x86_64-with-glibc2.35 Environment Linux Python 3.9.12 Install git RAM 62.44 GB CPU 11th Gen Intel Core(TM) i7-11800H 2.30GHz CUDA 11.7

numpy ✅ 1.26.3<2.0.0,>=1.23.0 matplotlib ✅ 3.8.2>=3.3.0 opencv-python ✅ 4.9.0.80>=4.6.0 pillow ✅ 10.2.0>=7.1.2 pyyaml ✅ 6.0.1>=5.3.1 requests ✅ 2.27.1>=2.23.0 scipy ✅ 1.11.4>=1.4.1 torch ✅ 1.13.1>=1.8.0 torchvision ✅ 0.14.1>=0.9.0 tqdm ✅ 4.66.1>=4.64.0 psutil ✅ 5.9.7 py-cpuinfo ✅ 9.0.0 pandas ✅ 2.1.4>=1.1.4 seaborn ✅ 0.13.1>=0.11.0 ultralytics-thop ✅ 2.0.0>=2.0.0

Minimal Reproducible Example

Download yolov8n.pt and run yolo export model=yolov8n.pt format=tflite int8=true dynamic=true fails

Additional

No response

Are you willing to submit a PR?

pderrenger commented 2 months ago

@harufumigithub thank you for reporting this issue. To help us diagnose the problem, could you please ensure you are using the latest version of the Ultralytics package? You can update it using pip install --upgrade ultralytics. If the issue persists, please provide any error messages or logs generated during the export process. This information will be invaluable for us to investigate further.