caffemodel转rknn的问题

我的prototxt内容只有这些

1. name: "LeNet"
   
2. layer {
   
3.   name: "input"
   
4.   type: "Input"
   
5.   top: "data"
   
6.   input_param {
   
7.     shape {
   
8.         dim: 1
   
9.         dim: 3
   
10.         dim: 32
    
11.         dim: 32
    
12.     }
    
13.   }
    
14. }
    
15. layer {
    
16.   name: "conv1"
    
17.   type: "Convolution"
    
18.   bottom: "data"
    
19.   top: "conv1"
    
20.   param {
    
21.     lr_mult: 1
    
22.   }
    
23.   param {
    
24.     lr_mult: 2
    
25.   }
    
26.   convolution_param {
    
27.     num_output: 20
    
28.     kernel_size: 5
    
29.     stride: 1
    
30.     weight_filler {
    
31.       type: "xavier"
    
32.     }
    
33.     bias_filler {
    
34.       type: "constant"
    
35.     }
    
36.   }
    
37. }

复制代码执行rknn.load_caffe(model='./lenet_train_test.prototxt', proto='caffe', blobs='./lenet_iter_10000.caffemodel')
报错

1. E Catch exception when loading caffe model: /home/lwd/bak/model/lenet_train_test.prototxt!
   
2. E Traceback (most recent call last):
   
3. E   File "rknn/api/rknn_base.py", line 404, in rknn.api.rknn_base.RKNNBase.load_caffe
   
4. E   File "rknn/base/RKNNlib/converter/caffeloader.py", line 1042, in rknn.base.RKNNlib.converter.caffeloader.CaffeLoader.load_blobs
   
5. E   File "rknn/base/RKNNlib/converter/caffeloader.py", line 935, in rknn.base.RKNNlib.converter.caffeloader.CaffeLoader.parse_blobs
   
6. E   File "rknn/base/RKNNlib/converter/caffeloader.py", line 358, in rknn.base.RKNNlib.converter.caffeloader.proc_blobs_convolution
   
7. E   File "/home/lwd/.local/lib/python3.5/site-packages/numpy/core/fromnumeric.py", line 292, in reshape
   
8. E     return _wrapfunc(a, 'reshape', newshape, order=order)
   
9. E   File "/home/lwd/.local/lib/python3.5/site-packages/numpy/core/fromnumeric.py", line 56, in _wrapfunc
   
10. E     return getattr(obj, method)(*args, **kwds)
    
11. E ValueError: cannot reshape array of size 500 into shape (20,3,5,5)

复制代码这个500是哪里出来的？caffemodel转rknn有教程吗？给个链接，感谢！

应该是caffemodel有问题