我正在使用Alexnet并尝试部署我的网络。但是当我这样做时，我收到以下错误：
I0109 15:16:56.645679 4240 net.cpp:100] Creating Layer fc6
I0109 15:16:56.645681 4240 net.cpp:434] fc6 <- pool5
I0109 15:16:56.645684 4240 net.cpp:408] fc6 -> fc6
I0109 15:16:56.712829 4240 net.cpp:150] Setting up fc6
I0109 15:16:56.712869 4240 net.cpp:157] Top shape: 1 4096 (4096)
I0109 15:16:56.712873 4240 net.cpp:165] Memory required for data: 6778220
I0109 15:16:56.712882 4240 layer_factory.hpp:77] Creating layer relu6
I0109 15:16:56.712890 4240 net.cpp:100] Creating Layer relu6
I0109 15:16:56.712893 4240 net.cpp:434] relu6 <- fc6
I0109 15:16:56.712915 4240 net.cpp:395] relu6 -> fc6 (in-place)
F0109 15:16:56.713158 4240 blob.hpp:122] Check failed: axis_index < num_axes() (2 vs. 2) axis 2 out of range for 2-D Blob with shape 1 4096 (4096)
*** Check failure stack trace: ***
我不知道为什么。它一直对我有用，现在发生了这个错误。
修改
layer {
name: "data"
type: "Input"
top: "data"
input_param { shape: { dim: 1 dim: 3 dim: 227 dim: 227 } }
}
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
param {
lr_mult: 1.0
decay_mult: 1.0
}
param {
lr_mult: 2.0
decay_mult: 0.0
}
convolution_param {
num_output: 96
kernel_size: 11
stride: 4
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.0
}
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "norm1"
type: "LRN"
bottom: "conv1"
top: "norm1"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "pool1"
type: "Pooling"
bottom: "norm1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "pool1"
top: "conv2"
param {
lr_mult: 1.0
decay_mult: 1.0
}
param {
lr_mult: 2.0
decay_mult: 0.0
}
convolution_param {
num_output: 256
pad: 2
kernel_size: 5
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu2"
type: "ReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "norm2"
type: "LRN"
bottom: "conv2"
top: "norm2"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "pool2"
type: "Pooling"
bottom: "norm2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv3"
type: "Convolution"
bottom: "pool2"
top: "conv3"
param {
lr_mult: 1.0
decay_mult: 1.0
}
param {
lr_mult: 2.0
decay_mult: 0.0
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.0
}
}
}
layer {
name: "relu3"
type: "ReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "conv4"
type: "Convolution"
bottom: "conv3"
top: "conv4"
param {
lr_mult: 1.0
decay_mult: 1.0
}
param {
lr_mult: 2.0
decay_mult: 0.0
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu4"
type: "ReLU"
bottom: "conv4"
top: "conv4"
}
layer {
name: "conv5"
type: "Convolution"
bottom: "conv4"
top: "conv5"
param {
lr_mult: 1.0
decay_mult: 1.0
}
param {
lr_mult: 2.0
decay_mult: 0.0
}
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
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: 1.0
decay_mult: 1.0
}
param {
lr_mult: 2.0
decay_mult: 0.0
}
inner_product_param {
num_output: 4096
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu6"
type: "ReLU"
bottom: "fc6"
top: "fc6l"
}
layer {
name: "drop6"
type: "Dropout"
bottom: "fc6l"
top: "fc6d"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc7"
type: "InnerProduct"
bottom: "fc6d"
top: "fc7"
param {
lr_mult: 1.0
decay_mult: 1.0
}
param {
lr_mult: 2.0
decay_mult: 0.0
}
inner_product_param {
num_output: 4096
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
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: "fc8"
type: "InnerProduct"
bottom: "fc7"
top: "fc8"
param {
lr_mult: 1.0
decay_mult: 1.0
}
param {
lr_mult: 2.0
decay_mult: 0.0
}
inner_product_param {
num_output: 612
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.0
}
}
}
layer {
name: "softmax"
type: "Softmax"
bottom: "fc8"
top: "softmax"
}
上面是我的.prototxt（应该与Alexnet相同）
Check failed: axis_index < num_axes() (2 vs. 2) axis 2 out of range for 2-D Blob with shape 1 4096 (4096)
*** Check failure stack trace: ***
@ 0x7f8b8e3125cd google::LogMessage::Fail()
@ 0x7f8b8e314433 google::LogMessage::SendToLog()
@ 0x7f8b8e31215b google::LogMessage::Flush()
@ 0x7f8b8e314e1e google::LogMessageFatal::~LogMessageFatal()
@ 0x7f8b8e92c86a caffe::Blob<>::CanonicalAxisIndex()
@ 0x7f8b8eaa09c2 caffe::CuDNNReLULayer<>::Reshape()
@ 0x7f8b8e97f481 caffe::Net<>::Init()
@ 0x7f8b8e980d01 caffe::Net<>::Net()
@ 0x7f8b8eac7c5a caffe::Solver<>::InitTrainNet()
@ 0x7f8b8eac8fc7 caffe::Solver<>::Init()
@ 0x7f8b8eac936a caffe::Solver<>::Solver()
@ 0x7f8b8e960c53 caffe::Creator_SGDSolver<>()
@ 0x40ac89 train()
@ 0x407590 main
@ 0x7f8b8d283830 __libc_start_main
@ 0x407db9 _start
@ (nil) (unknown)
Aborted (core dumped)
示例2：
I0228 13:03:22.875816 4395 layer_factory.hpp:77] Creating layer relu6
I0228 13:03:22.875828 4395 net.cpp:100] Creating Layer relu6
I0228 13:03:22.875831 4395 net.cpp:434] relu6 <- fc-main
I0228 13:03:22.875855 4395 net.cpp:395] relu6 -> fc-main (in-place)
F0228 13:03:22.876565 4395 blob.hpp:122] Check failed: axis_index < num_axes() (2 vs. 2) axis 2 out of range for 2-D Blob with shape 4 4096 (16384)
*** Check failure stack trace: ***
@ 0x7fe1271d85cd google::LogMessage::Fail()
@ 0x7fe1271da433 google::LogMessage::SendToLog()
@ 0x7fe1271d815b google::LogMessage::Flush()
@ 0x7fe1271dae1e google::LogMessageFatal::~LogMessageFatal()
@ 0x7fe1277f286a caffe::Blob<>::CanonicalAxisIndex()
@ 0x7fe1279669c2 caffe::CuDNNReLULayer<>::Reshape()
@ 0x7fe127845481 caffe::Net<>::Init()
@ 0x7fe127846d01 caffe::Net<>::Net()
@ 0x7fe12798dc5a caffe::Solver<>::InitTrainNet()
@ 0x7fe12798efc7 caffe::Solver<>::Init()
@ 0x7fe12798f36a caffe::Solver<>::Solver()
@ 0x7fe127826c53 caffe::Creator_SGDSolver<>()
@ 0x40ac89 train()
@ 0x407590 main
@ 0x7fe126149830 __libc_start_main
@ 0x407db9 _start
@ (nil) (unknown)
Aborted (core dumped)
layer {
name: "fc-main"
type: "InnerProduct"
bottom: "pool5"
top: "fc-main"
param {
decay_mult: 1
}
param {
decay_mult: 0
}
inner_product_param {
num_output: 4096
weight_filler {
type: "xavier"
std: 0.005
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu6"
type: "ReLU"
bottom: "fc-main"
top: "fc-main"
}
layer {
name: "drop6"
type: "Dropout"
bottom: "fc-main"
top: "fc-main"
dropout_param {
dropout_ratio: 0.5
}
}