caffemodel转rknn的问题

[复制链接] · 发表于 2020-12-24 14:37:25

我的prototxt内容只有这些

name: "LeNet"

layer {

  name: "input"

  type: "Input"

  top: "data"

  input_param {

    shape {

        dim: 1

        dim: 3

        dim: 32

        dim: 32

    }

  }

}

layer {

  name: "conv1"

  type: "Convolution"

  bottom: "data"

  top: "conv1"

  param {

    lr_mult: 1

  }

  param {

    lr_mult: 2

  }

  convolution_param {

    num_output: 20

    kernel_size: 5

    stride: 1

    weight_filler {

      type: "xavier"

    }

    bias_filler {

      type: "constant"

    }

  }

}
复制代码

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

E Catch exception when loading caffe model: /home/lwd/bak/model/lenet_train_test.prototxt!

E Traceback (most recent call last):

E   File "rknn/api/rknn_base.py", line 404, in rknn.api.rknn_base.RKNNBase.load_caffe

E   File "rknn/base/RKNNlib/converter/caffeloader.py", line 1042, in rknn.base.RKNNlib.converter.caffeloader.CaffeLoader.load_blobs

E   File "rknn/base/RKNNlib/converter/caffeloader.py", line 935, in rknn.base.RKNNlib.converter.caffeloader.CaffeLoader.parse_blobs

E   File "rknn/base/RKNNlib/converter/caffeloader.py", line 358, in rknn.base.RKNNlib.converter.caffeloader.proc_blobs_convolution

E   File "/home/lwd/.local/lib/python3.5/site-packages/numpy/core/fromnumeric.py", line 292, in reshape

E     return _wrapfunc(a, 'reshape', newshape, order=order)

E   File "/home/lwd/.local/lib/python3.5/site-packages/numpy/core/fromnumeric.py", line 56, in _wrapfunc

E     return getattr(obj, method)(*args, **kwds)

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！

只看该作者 · 发表于 2020-12-28 14:23:50

应该是caffemodel有问题