|
沙发
楼主 |
发表于 2020-6-5 11:48:17
|
只看该作者
补充,当选择optimization_level=0 时候,模型居然build出错
###
- E Traceback (most recent call last):
- E File "rknn/api/rknn_base.py", line 737, in rknn.api.rknn_base.RKNNBase.build
- E File "rknn/api/rknn_base.py", line 1644, in rknn.api.rknn_base.RKNNBase._quantize2
- E File "rknn/base/RKNNlib/app/medusa/quantization.py", line 105, in rknn.base.RKNNlib.app.medusa.quantization.Quantization.run
- E File "rknn/base/RKNNlib/app/medusa/quantization.py", line 41, in rknn.base.RKNNlib.app.medusa.quantization.Quantization._run_quantization
- E File "rknn/base/RKNNlib/range/analyze_range.py", line 390, in rknn.base.RKNNlib.range.analyze_range.sparse_network
- E File "rknn/base/RKNNlib/range/analyze_range.py", line 288, in rknn.base.RKNNlib.range.analyze_range.analyze_operation
- E File "rknn/base/RKNNlib/range/analyze_range.py", line 187, in rknn.base.RKNNlib.range.analyze_range._a_bn
- E File "rknn/base/RKNNlib/range/analyze_range.py", line 30, in rknn.base.RKNNlib.range.analyze_range._bn_channel_range
- E TypeError: unsupported operand type(s) for /: 'NoneType' and 'float'
- Build pre-compile shufflenet_v2 failed!
- Process finished with exit code 255
|
|