Convert ONNX

[curtis18]

Running MIL backend_neuralnetwork pipeline: 100%|███████████████████████████████████████████████████████████████| 8/8 [00:00<00:00, 128.12 passes/s] Translating MIL ==> NeuralNetwork Ops: 100%|█████████████████████████████████████████████████████████████████| 1181/1181 [00:05<00:00, 215.95 ops/s] CoreML export success, saved as runs\train\yolov7-fine-train3\weights\best.mlmodel

Starting TorchScript-Lite export with torch 1.13.1... TorchScript-Lite export success, saved as runs\train\yolov7-fine-train3\weights\best.torchscript.ptl

Starting ONNX export with onnx 1.14.0... C:\Users\Jump\yolov7\models\yolo.py:582: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! if augment: C:\Users\Jump\yolov7\models\yolo.py:614: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! if profile: C:\Users\Jump\yolov7\models\yolo.py:629: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! if profile: ONNX export success, saved as runs\train\yolov7-fine-train3\weights\best.onnx

Export complete (33.50s). Visualize with https://github.com/lutzroeder/netron.

May I know what is the problem of those TracerWarning? How can it be resolved?

onnx 1.14.0 torch 1.13.1 coremltools 6.3.0

Thank you.

[thnak]

it's normal just ignore it

[curtis18]

@thnak Thank you.