[Caffe]：检查失败：ShapeEquals(proto) 形状不匹配（未设置重塑）

Question

我有这个错误，我试图在互联网上查看，但我什么都不清楚。

我用 Caffe 成功地训练了我的网络，准确率约为 82%。

现在我尝试通过以下代码用图像来尝试：

python python/classify.py --model_def examples/imagenet/imagenet_deploy.prototxt --pretrained_model caffe_mycaffe_train_iter_10000.caffemodel --images_dim 64,64 data/mycaffe/testingset/cat1/113.png foo --mean_file data/mycaffe/mycaffe_train_mean.binaryproto

是的，我的图片是 64x64，

这些是我得到的最后几行：

I0610 15:33:44.868100 28657 net.cpp:194] conv3 does not need backward computation. I0610 15:33:44.868110 28657 net.cpp:194] norm2 does not need backward computation. I0610 15:33:44.868120 28657 net.cpp:194] pool2 does not need backward computation. I0610 15:33:44.868130 28657 net.cpp:194] relu2 does not need backward computation. I0610 15:33:44.868142 28657 net.cpp:194] conv2 does not need backward computation. I0610 15:33:44.868152 28657 net.cpp:194] norm1 does not need backward computation. I0610 15:33:44.868162 28657 net.cpp:194] pool1 does not need backward computation. I0610 15:33:44.868173 28657 net.cpp:194] relu1 does not need backward computation. I0610 15:33:44.868182 28657 net.cpp:194] conv1 does not need backward computation. I0610 15:33:44.868192 28657 net.cpp:235] This network produces output fc8_pascal I0610 15:33:44.868214 28657 net.cpp:482] Collecting Learning Rate and Weight Decay. I0610 15:33:44.868238 28657 net.cpp:247] Network initialization done. I0610 15:33:44.868249 28657 net.cpp:248] Memory required for data: 3136120 F0610 15:33:45.025965 28657 blob.cpp:458] Check failed: ShapeEquals(proto) shape mismatch (reshape not set) * Check failure stack trace: * Aborted (core dumped)

我试过不设置 --mean_file 和更多东西，但我的拍摄结束了。

这是我的imagenet_deploy.prototxt，我修改了一些参数进行调试，但没有任何效果。

name: "MyCaffe"
input: "data"
input_dim: 10
input_dim: 3
input_dim: 64
input_dim: 64
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  convolution_param {
    num_output: 64
    kernel_size: 11
    stride: 4
  }
}
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"
  convolution_param {
    num_output: 64 
    pad: 2
    kernel_size: 5
    group: 2
  }
}
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"
  convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
  }
}
layer {
  name: "relu3"
  type: "ReLU"
  bottom: "conv3"
  top: "conv3"
}
layer {
  name: "conv4"
  type: "Convolution"
  bottom: "conv3"
  top: "conv4"
  convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
    group: 2
  }
}
layer {
  name: "relu4"
  type: "ReLU"
  bottom: "conv4"
  top: "conv4"
}
layer {
  name: "conv5"
  type: "Convolution"
  bottom: "conv4"
  top: "conv5"
  convolution_param {
    num_output: 64
    pad: 1
    kernel_size: 3
    group: 2
  }
}
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"
  inner_product_param {
    num_output: 4096
  }
}
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"
  inner_product_param {
    num_output: 4096
  }
}
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: "fc8_pascal"
  type: "InnerProduct"
  bottom: "fc7"
  top: "fc8_pascal"
  inner_product_param {
    num_output: 3
  }
}

有谁能给我一个线索吗？非常感谢。

C++ 和 classification bin 他们提供了同样的情况：

F0610 18:06:14.975601 7906 blob.cpp:455] Check failed: ShapeEquals(proto) shape mismatch (reshape not set) * Check failure stack trace: * @ 0x7f0e3c50761c google::LogMessage::Fail() @ 0x7f0e3c507568 google::LogMessage::SendToLog() @ 0x7f0e3c506f6a google::LogMessage::Flush() @ 0x7f0e3c509f01 google::LogMessageFatal::~LogMessageFatal() @ 0x7f0e3c964a80 caffe::Blob<>::FromProto() @ 0x7f0e3c89576e caffe::Net<>::CopyTrainedLayersFrom() @ 0x7f0e3c8a10d2 caffe::Net<>::CopyTrainedLayersFrom() @ 0x406c32 Classifier::Classifier() @ 0x403d2b main @ 0x7f0e3b124ec5 (unknown) @ 0x4041ce (unknown) Aborted (core dumped)

Answer 1

让我确认基本步骤是否正确。

input_dim: 10
input_dim: 3
input_dim: 64
input_dim: 64

您是否尝试过将第一个参数更改为 1，因为您只传递了一张图片。

当顶部或底部斑点的尺寸不正确时，会出现上述错误。除了输入 blob 之外，没有其他地方可能出错。

编辑 2：

ShapeEquals(proto) shape mismatch (reshape not set) 当 'reshape' 参数为 fromproto function call.

设置为 false 时出现错误消息

我在库中快速搜索了 fromproto 函数调用，如图 here 所示。除了 'CopyTrainedLayersFrom' 函数没有其他函数实际将上述参数设置为 false.

这实际上令人困惑。我建议的两种方法是：

检查是否从存储库更新了caffe源代码。
尝试运行在 /build/tools/ 中找到的 caffe.bin 可执行文件的 test 部分。

Answer 2

我刚刚遇到了同样的错误。在我的例子中，我最后一层的输出参数不正确：切换数据集，我在 train.prototxt 中更改了类的数量，但在 test.prototxt 中没有这样做（或 deploy.prototxt).纠正这个错误解决了我的问题。

Answer 3

在我的例子中，我的求解器文件中第二个卷积层的内核大小与训练文件中的不同。更改解算器文件中的大小解决了问题。

[Caffe]：检查失败：ShapeEquals(proto) 形状不匹配（未设置重塑）

[Caffe]: Check failed: ShapeEquals(proto) shape mismatch (reshape not set)

c++

python

deep-learning

caffe