You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am trying to export *.pt model to tensorflow like this python export.py --weights yolov9-e-converted.pt --include saved_model
and I am getting this error
TensorFlow SavedModel: export failure ❌ 1.7s: cannot import name 'C3' from 'models.common' (/root/conversion/yolov9/models/common.py)
python export.py --weights yolov9-e-converted.pt --include pb
fails with another error
TensorFlow SavedModel: export failure ❌ 5.1s: cannot import name 'C3' from 'models.common' (/root/conversion/yolov9/models/common.py)
TensorFlow GraphDef: starting export with tensorflow 2.18.0...
TensorFlow GraphDef: export failure ❌ 0.0s: 'NoneType' object has no attribute 'inputs'
python export.py --weights yolov9-e-converted.pt --include tfjs
fails with this error
TensorFlow SavedModel: export failure ❌ 1.7s: cannot import name 'C3' from 'models.common' (/root/conversion/yolov9/models/common.py)
TensorFlow GraphDef: starting export with tensorflow 2.18.0...
TensorFlow GraphDef: export failure ❌ 0.0s: 'NoneType' object has no attribute 'inputs'
tensorflow.python.framework.errors_impl.NotFoundError: yolov9-e-converted.pb; No such file or directory
TensorFlow.js: export failure ❌ 4.5s: [Errno 2] No such file or directory: 'yolov9-e-converted_web_model/model.json'
But python export.py --weights yolov9-e-converted.pt --include onnx
works fine and produces file yolov9-e-converted.onnx file.
I do not need speed or GPU. I just need to convert it and if it takes 2 days to convert, I am fine. I need to do it once.
or maybe I am doing something completely wrong and using export.py in a wrong way?
The text was updated successfully, but these errors were encountered:
I am trying to export *.pt model to tensorflow like this
python export.py --weights yolov9-e-converted.pt --include saved_model
and I am getting this error
TensorFlow SavedModel: export failure ❌ 1.7s: cannot import name 'C3' from 'models.common' (/root/conversion/yolov9/models/common.py)
python export.py --weights yolov9-e-converted.pt --include pb
fails with another error
TensorFlow SavedModel: export failure ❌ 5.1s: cannot import name 'C3' from 'models.common' (/root/conversion/yolov9/models/common.py)
TensorFlow GraphDef: starting export with tensorflow 2.18.0...
TensorFlow GraphDef: export failure ❌ 0.0s: 'NoneType' object has no attribute 'inputs'
python export.py --weights yolov9-e-converted.pt --include tfjs
fails with this error
TensorFlow SavedModel: export failure ❌ 1.7s: cannot import name 'C3' from 'models.common' (/root/conversion/yolov9/models/common.py)
TensorFlow GraphDef: starting export with tensorflow 2.18.0...
TensorFlow GraphDef: export failure ❌ 0.0s: 'NoneType' object has no attribute 'inputs'
tensorflow.python.framework.errors_impl.NotFoundError: yolov9-e-converted.pb; No such file or directory
TensorFlow.js: export failure ❌ 4.5s: [Errno 2] No such file or directory: 'yolov9-e-converted_web_model/model.json'
But
python export.py --weights yolov9-e-converted.pt --include onnx
works fine and produces file yolov9-e-converted.onnx file.
I do not need speed or GPU. I just need to convert it and if it takes 2 days to convert, I am fine. I need to do it once.
or maybe I am doing something completely wrong and using export.py in a wrong way?
The text was updated successfully, but these errors were encountered: