Caffe：检查失败：shape[i] >= 0 (-1 vs. 0) 错误

Question

我正在尝试设计一个采用 IMAGE (224x224x3) 和 3 个参数 (X,Y,R) 来学习关系的网络。

我的输入是一个 HDF5 数据集。我收到以下错误：

"创建层conv1 I0612 17:17:38.315083 9991 net.cpp:406] conv1 conv1 F0612 17:17:38.352540 9991 blob.cpp:32] 检查失败：shape[i] >= 0 (-1 vs. 0)"

我创建了一个 HDF5 数据集，用于输入到 caffe。我的 create_dataset 代码如下：-

import h5py, os
import caffe
import numpy as np

SIZE = 224
with open( 'val.txt', 'r' ) as T :
    lines = T.readlines()


count_files = 0
split_after = 199
count = -1

# If you do not have enough memory split data into
# multiple batches and generate multiple separate h5 files
data = np.zeros( (split_after,SIZE, SIZE,3), dtype='f4' )
label = np.zeros( (split_after,3, 1), dtype='f4' )

for i,l in enumerate(lines):
    count += 1
    sp = l.split(' ')
    img = caffe.io.load_image( sp[0] )
    data[count] = img
    label[count][0] = float(sp[1])
    label[count][1] = float(sp[2])
    label[count][2] = float(sp[3])
    #print y1[count]
    if (count+1) == split_after:
    with h5py.File('val_' + str(count_files) +  '.h5','w') as H:
        H.create_dataset( 'data', data=data ) # note the name X given to the dataset!
        H.create_dataset( 'label', data=label )
        data = np.zeros( (split_after, SIZE, SIZE, 3), dtype='f4' )
        label = np.zeros( (split_after,3, 1), dtype='f4' )
    with open('val1.txt','a') as L:
        L.write( 'val_' + str(count_files) + '.h5') # list all h5 files you are going to use
    count_files += 1
    count = 0

我正在 HDF5 数据集中创建一个数据 (224,224,3) 字段和一个标签 (3,1)。

现在我的caffe模型如下：

name: "CaffeNet"
layer {
  name: "data"
  type: "HDF5Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  hdf5_data_param {
    source: "/home/arijit/Downloads/caffe/Circle/test1.txt"
    batch_size: 256
    shuffle: true
  }
}
layer {
  name: "data"
  type: "HDF5Data"
  top: "data"
  top: "label"
  include {
    phase: TEST
  }
  hdf5_data_param {
    source: "/home/arijit/Downloads/caffe/Circle/val1.txt"
    batch_size: 16
  }
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 96
    kernel_size: 11
    stride: 4
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "conv1"
  top: "conv1"
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "norm1"
  type: "LRN"
  bottom: "pool1"
  top: "norm1"
  lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
  }
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "norm1"
  top: "conv2"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    pad: 2
    kernel_size: 5
    group: 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layer {
  name: "relu2"
  type: "ReLU"
  bottom: "conv2"
  top: "conv2"
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "norm2"
  type: "LRN"
  bottom: "pool2"
  top: "norm2"
  lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
  }
}
layer {
  name: "conv3"
  type: "Convolution"
  bottom: "norm2"
  top: "conv3"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu3"
  type: "ReLU"
  bottom: "conv3"
  top: "conv3"
}
layer {
  name: "conv4"
  type: "Convolution"
  bottom: "conv3"
  top: "conv4"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
    group: 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layer {
  name: "relu4"
  type: "ReLU"
  bottom: "conv4"
  top: "conv4"
}
layer {
  name: "conv5"
  type: "Convolution"
  bottom: "conv4"
  top: "conv5"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
    group: 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layer {
  name: "relu5"
  type: "ReLU"
  bottom: "conv5"
  top: "conv5"
}
layer {
  name: "pool5"
  type: "Pooling"
  bottom: "conv5"
  top: "pool5"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "fc6"
  type: "InnerProduct"
  bottom: "pool5"
  top: "fc6"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 4096
    weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layer {
  name: "relu6"
  type: "ReLU"
  bottom: "fc6"
  top: "fc6"
}
layer {
  name: "drop6"
  type: "Dropout"
  bottom: "fc6"
  top: "fc6"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layer {
  name: "fc7"
  type: "InnerProduct"
  bottom: "fc6"
  top: "fc7"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 4096
    weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layer {
  name: "relu7"
  type: "ReLU"
  bottom: "fc7"
  top: "fc7"
}
layer {
  name: "drop7"
  type: "Dropout"
  bottom: "fc7"
  top: "fc7"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layer {
  name: "fc8ft"
  type: "InnerProduct"
  bottom: "fc7"
  top: "fc8ft"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 3
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}

layer {
  name: "loss"
  type: "EuclideanLoss"
  bottom: "fc8ft"
  bottom: "label"
  top: "loss"
}

详细错误如下：-

"创建层conv1 I0612 17:17:38.315083 9991 net.cpp:406] conv1 conv1 F0612 17:17:38.352540 9991 blob.cpp:32] 检查失败：shape[i] >= 0 (-1 vs. 0)"

谁能帮忙？

Answer 1

我收到了同样的错误信息。不过好像我的情况和提问者不一样。

我遇到这个错误是因为我在我的网络中添加了太多的卷积层和池化层，最终图像缩小到1x1，在这种情况下，如果我继续添加卷积层，则无法进行卷积，并且出现了这个错误.

如果其他人遇到我的问题，我会在这里发布。

Answer 2

你得到了输入图像的形状：。 而不是HxWx3，caffe 期望它是3xWxH。
有关在 hdf5 文件中为 caffe 安排数组的更多详细信息，请参阅this answer。

PS，
您不需要 label 数组中的 Singleton 维度。