I am using ultralytics version 8.0.20 5o train yolov8 model. I am done training and testing and I want to export my mode to use it on my server. in my server there is no ultralytics package I only have pytorch and tensorflow installed. when I use this line from office official document I get this outcome
!yolo export model={HOME}/runs/detect/train/weights/best.pt format=saved_model imgsz= 1024 # export custom trained model
2023-05-27 16:49:11.934911: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-05-27 16:49:12.893349: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
Ultralytics YOLOv8.0.20 Python-3.10.11 torch-2.0.1+cu118 CUDA:0 (Tesla T4, 15102MiB)
Model summary (fused): 168 layers, 11125971 parameters, 0 gradients, 28.4 GFLOPs
PyTorch: starting from /content/runs/detect/train/weights/best.pt with output shape (1, 5, 21504) (21.5 MB)
Traceback (most recent call last):
File "/usr/local/bin/yolo", line 8, in <module>
sys.exit(entrypoint())
File "/usr/local/lib/python3.10/dist-packages/ultralytics/yolo/cfg/__init__.py", line 249, in entrypoint
getattr(model, mode)(verbose=True, **overrides)
File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/ultralytics/yolo/engine/model.py", line 182, in export
exporter(model=self.model)
File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/ultralytics/yolo/engine/exporter.py", line 213, in __call__
raise NotImplementedError('YOLOv8 TensorFlow export support is still under development. '
NotImplementedError: YOLOv8 TensorFlow export support is still under development. Please consider contributing to the effort if you have TF expertise. Thank you!
It looks like there is not export feature for now. Is there any way that I could save my model as tf, keras or pytorch model and load them (only for inference) latter with out ultralytics pack.
thank you in advance
