Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Error on exporting to tflite #602

Open
rgyan619 opened this issue Oct 10, 2024 · 0 comments
Open

Error on exporting to tflite #602

rgyan619 opened this issue Oct 10, 2024 · 0 comments

Comments

@rgyan619
Copy link

--> python export.py --include tflite

########################################################################################
Output
########################################################################################

export: data=data/coco.yaml, weights=yolov9.pt, imgsz=[1024, 1024], batch_size=1, device=cpu, half=False, inplace=False, keras=False, optimize=False, int8=False, dynamic=False, simplify=False, opset=12, verbose=False, workspace=4, nms=False, agnostic_nms=False, topk_per_class=100, topk_all=100, iou_thres=0.45, conf_thres=0.25, include=['tflite']
YOLO 🚀 v0.1-104-g5b1ea9a Python-3.8.18 torch-1.8.0 CPU

Fusing layers...
yolov7-af-seg summary: 281 layers, 45877856 parameters, 0 gradients, 172.5 GFLOPs

PyTorch: starting from yolov9.pt with output shape (1, 84, 21504) (351.1 MB)
2024-10-10 15:22:09.625319: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used.
2024-10-10 15:22:09.689147: 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.
2024-10-10 15:22:10.649212: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
TensorFlow SavedModel: export failure ❌ 2.6s: cannot import name 'C3' from 'models.common' (/home/user/Convrting_pytorch_to_tflite/yolov9/models/common.py)

TensorFlow Lite: starting export with tensorflow 2.13.1...
TensorFlow Lite: export failure ❌ 0.0s: 'NoneType' object has no attribute 'call'
Traceback (most recent call last):
File "export.py", line 686, in
main(opt)
File "export.py", line 681, in main
run(**vars(opt))
File "/opt/miniconda3/envs/Yolo_V9_Parts/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "export.py", line 611, in run
add_tflite_metadata(f[8] or f[7], metadata, num_outputs=len(s_model.outputs))
AttributeError: 'NoneType' object has no attribute 'outputs'

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant