Unknown bottom blob 'data' (layer 'conv1', bottom index 0)

来源：互联网发布：金凯度知乎编辑：程序博客网时间：2024/05/16 02:52

caffe训练的时候，出现错误Unknown bottom blob 'data' (layer 'conv1', bottom index 0)

原因1：

data layer中的top名称与conv1 bottom的名称不一致。

比如：（下方红色字内容应该统一，否则报错）

name: "Test_net"layer {  name: "data"  type: "HDF5Data"  top: "Inputdata"  top: "label"  hdf5_data_param {    source:"~/*_hdf5_train.txt"    batch_size: 32  }  include{phase: TRAIN}}layer {  name: "data2"  type: "HDF5Data"  top: "Inputdata"  top: "label"  hdf5_data_param {    source:"~/*_hdf5_test.txt"    batch_size: 32  }  include{phase: TEST}}layer {  name: "conv1"  type: "convolution"  bottom: "data"  top: "conv1"  param {lr_mult:1}  param {lr_mult:2}  convolution_param{    num_output: 20    kernel_h: 1    kernel_w: 5    stride_h: 1    stride_w: 1    weight_filler {      type: "xavier"         }    bias_filler {      type: "xavier"    }  }}

原因2：

没有单独的测试数据，在网络中却使用了phrase：TRAIN 或TEST的定义。

比如：（不该有下方红色字的部分，否则报错）

name: "Test_net"layer {  name: "data"  type: "HDF5Data"  top: "data"  top: "label"  hdf5_data_param {    source:"~/*_hdf5_train.txt"    batch_size: 32  }  include{phase: TRAIN}}layer {  name: "conv1"  type: "convolution"  bottom: "data"  top: "conv1"  param {lr_mult:1}  param {lr_mult:2}  convolution_param{    num_output: 20    kernel_h: 1    kernel_w: 5    stride_h: 1    stride_w: 1    weight_filler {      type: "xavier"         }    bias_filler {      type: "xavier"    }  }}

阅读全文

0 0