caffe模型转换出错

错误 log 如下

1. --> Init runtime environment
   
2. done
   
3. --> Loading model
   
4. W Unhandle status: the input shape of reshape layer mbox_conf_reshape_109 is not 4-D
   
5. done
   
6. --> Building model
   
7. E Unsuport input tensor type "None" of layer "output_113".
   
8. E Catch exception when building RKNN model!
   
9. T Traceback (most recent call last):
   
10. T   File "rknn/api/rknn_base.py", line 459, in rknn.api.rknn_base.RKNNBase.build
    
11. T   File "rknn/api/rknn_base.py", line 950, in rknn.api.rknn_base.RKNNBase._quantize
    
12. T   File "rknn/base/RKNNlib/app/tensorzone/workspace.py", line 219, in rknn.base.RKNNlib.app.tensorzone.workspace.Workspace.load_net
    
13. T   File "rknn/base/RKNNlib/app/tensorzone/graph.py", line 26, in rknn.base.RKNNlib.app.tensorzone.graph.Graph.load_net
    
14. T   File "rknn/base/RKNNlib/RKNNnet.py", line 406, in rknn.base.RKNNlib.RKNNnet.RKNNNet.load
    
15. T   File "rknn/base/RKNNlib/RKNNnet.py", line 410, in rknn.base.RKNNlib.RKNNnet.RKNNNet.load
    
16. T   File "rknn/base/RKNNlib/RKNNnet.py", line 445, in rknn.base.RKNNlib.RKNNnet.RKNNNet.loads
    
17. T   File "rknn/base/RKNNlib/layer/RKNNlayer.py", line 150, in rknn.base.RKNNlib.layer.RKNNlayer.RKNNLayer.add_input
    
18. T   File "rknn/base/RKNNlib/RKNNlog.py", line 105, in rknn.base.RKNNlib.RKNNlog.RKNNLog.e
    
19. T ValueError: Unsuport input tensor type "None" of layer "output_113".
    
20. done
    
21. E RKNN model data is None, please load model first!
    

复制代码