--> Loading model
W load_onnx: It is recommended onnx opset 12, but your onnx model opset is 11!
W load_onnx: Model converted from pytorch, 'opset_version' should be set 12 in torch.onnx.export for successful convert!
More details can be found in examples/pytorch/resnet18_export_onnx
done
--> Building model
Analysing : 100%|██████████████████████████████████████████████| 164/164 [00:00<00:00, 11732.72it/s]
Quantizating : 100%|██████████████████████████████████████████████| 164/164 [00:02<00:00, 81.32it/s]
W build: The default input dtype of 'data' is changed from 'float32' to 'int8' in rknn model for performance!
Please take care of this change when deploy rknn model with Runtime API!
W build: The default output dtype of 'cls1' is changed from 'float32' to 'int8' in rknn model for performance!
Please take care of this change when deploy rknn model with Runtime API!
W build: The default output dtype of 'reg1' is changed from 'float32' to 'int8' in rknn model for performance!
Please take care of this change when deploy rknn model with Runtime API!
W build: The default output dtype of 'cls2' is changed from 'float32' to 'int8' in rknn model for performance!
Please take care of this change when deploy rknn model with Runtime API!
W build: The default output dtype of 'reg2' is changed from 'float32' to 'int8' in rknn model for performance!
Please take care of this change when deploy rknn model with Runtime API!
W build: The default output dtype of 'cls3' is changed from 'float32' to 'int8' in rknn model for performance!
Please take care of this change when deploy rknn model with Runtime API!
W build: The default output dtype of 'reg3' is changed from 'float32' to 'int8' in rknn model for performance!
Please take care of this change when deploy rknn model with Runtime API!
E RKNN: [11:25:47.739] REGTASK: The bit width of field value exceeds the limit, target: t3, offset: 0x4030, shift = 0, limit: 0x1fff, value: 0x31ff
已放弃 (核心已转储)
--> Loading model W load_onnx: It is recommended onnx opset 12, but your onnx model opset is 11! W load_onnx: Model converted from pytorch, 'opset_version' should be set 12 in torch.onnx.export for successful convert! More details can be found in examples/pytorch/resnet18_export_onnx done --> Building model Analysing : 100%|██████████████████████████████████████████████| 164/164 [00:00<00:00, 11732.72it/s] Quantizating : 100%|██████████████████████████████████████████████| 164/164 [00:02<00:00, 81.32it/s] W build: The default input dtype of 'data' is changed from 'float32' to 'int8' in rknn model for performance! Please take care of this change when deploy rknn model with Runtime API! W build: The default output dtype of 'cls1' is changed from 'float32' to 'int8' in rknn model for performance! Please take care of this change when deploy rknn model with Runtime API! W build: The default output dtype of 'reg1' is changed from 'float32' to 'int8' in rknn model for performance! Please take care of this change when deploy rknn model with Runtime API! W build: The default output dtype of 'cls2' is changed from 'float32' to 'int8' in rknn model for performance! Please take care of this change when deploy rknn model with Runtime API! W build: The default output dtype of 'reg2' is changed from 'float32' to 'int8' in rknn model for performance! Please take care of this change when deploy rknn model with Runtime API! W build: The default output dtype of 'cls3' is changed from 'float32' to 'int8' in rknn model for performance! Please take care of this change when deploy rknn model with Runtime API! W build: The default output dtype of 'reg3' is changed from 'float32' to 'int8' in rknn model for performance! Please take care of this change when deploy rknn model with Runtime API! E RKNN: [11:25:47.739] REGTASK: The bit width of field value exceeds the limit, target: t3, offset: 0x4030, shift = 0, limit: 0x1fff, value: 0x31ff 已放弃 (核心已转储)