【发布时间】：2015-11-09 06:19:36
【问题描述】：
我训练了 caffe 的 Alexnet 模型，以便使用更高效的模型进行测试。因为我的训练是针对行人的，所以我的图像尺寸是 64 x 80 图像。我对 prototxt 文件进行了更改以匹配我训练过的图像大小。根据这个tutorial，最好设置卷积滤波器大小与输入图像大小相匹配。所以我的过滤器大小与原始 Alexnet 提供的 prototxt 文件略有不同（我使用 Alexnet 的原始 prototxt 文件进行训练和测试，并在下面提到的同一行得到相同的错误）。
根据我的计算，通过每一层后的图像大小将是
80x64x3 -> 转化 1 -> 38x30x96
38x30x96 -> 水池 -> 18x14x96
18x14x96 -> 转换 2 -> 19x15x256
19x15x256 -> 池 2 -> 9x7x256
9x7x256 -> 转化 3 -> 9x7x384
9x7x384 -> Conv4 -> 9x7x384
9x7x384 -> 转化 5 -> 9x7x256
9x7x256 -> 池 5 -> 4x3x256
错误出现在 fc6 层和test_predict_imagenet.cpp 的第 714 行。我使用test_predict_imagenet.cpp文件来测试模型。
CHECK_EQ(target_blobs[j]->width(), source_layer.blobs(j).width());
错误是
F0816 22:58:28.328047 3432 net.cpp:714] Check failed: target_blobs[j]->width()
== source_layer.blobs(j).width() (5120 vs. 1024)
我不明白为什么会这样。
我的两个prototxt文件如下所示。
train_val.prototxt
name: "AlexNet"
layers {
name: "data"
type: DATA
top: "data"
top: "label"
data_param {
source: "../../examples/Alexnet/Alexnet_train_leveldb"
batch_size: 200
}
transform_param {
crop_size: 48
mean_file: "../../examples/Alexnet/mean.binaryproto"
mirror: true
}
include: { phase: TRAIN }
}
layers {
name: "data"
type: DATA
top: "data"
top: "label"
data_param {
source: "../../examples/Alexnet/Alexnet_test_leveldb"
batch_size: 200
}
transform_param {
crop_size: 48
mean_file: "../../examples/Alexnet/mean.binaryproto"
mirror: false
}
include: { phase: TEST }
}
layers {
name: "conv1"
type: CONVOLUTION
bottom: "data"
top: "conv1"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 96
kernel_size: 6
stride: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layers {
name: "relu1"
type: RELU
bottom: "conv1"
top: "conv1"
}
layers {
name: "norm1"
type: LRN
bottom: "conv1"
top: "norm1"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layers {
name: "pool1"
type: POOLING
bottom: "norm1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 4
stride: 2
}
}
layers {
name: "conv2"
type: CONVOLUTION
bottom: "pool1"
top: "conv2"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 256
pad: 2
kernel_size: 4
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layers {
name: "relu2"
type: RELU
bottom: "conv2"
top: "conv2"
}
layers {
name: "norm2"
type: LRN
bottom: "conv2"
top: "norm2"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layers {
name: "pool2"
type: POOLING
bottom: "norm2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layers {
name: "conv3"
type: CONVOLUTION
bottom: "pool2"
top: "conv3"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layers {
name: "relu3"
type: RELU
bottom: "conv3"
top: "conv3"
}
layers {
name: "conv4"
type: CONVOLUTION
bottom: "conv3"
top: "conv4"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 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
}
}
}
layers {
name: "relu4"
type: RELU
bottom: "conv4"
top: "conv4"
}
layers {
name: "conv5"
type: CONVOLUTION
bottom: "conv4"
top: "conv5"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 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
}
}
}
layers {
name: "relu5"
type: RELU
bottom: "conv5"
top: "conv5"
}
layers {
name: "pool5"
type: POOLING
bottom: "conv5"
top: "pool5"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layers {
name: "fc6"
type: INNER_PRODUCT
bottom: "pool5"
top: "fc6"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
inner_product_param {
num_output: 4096
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layers {
name: "relu6"
type: RELU
bottom: "fc6"
top: "fc6"
}
layers {
name: "drop6"
type: DROPOUT
bottom: "fc6"
top: "fc6"
dropout_param {
dropout_ratio: 0.5
}
}
layers {
name: "fc7"
type: INNER_PRODUCT
bottom: "fc6"
top: "fc7"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
inner_product_param {
num_output: 4096
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layers {
name: "relu7"
type: RELU
bottom: "fc7"
top: "fc7"
}
layers {
name: "drop7"
type: DROPOUT
bottom: "fc7"
top: "fc7"
dropout_param {
dropout_ratio: 0.5
}
}
layers {
name: "fc8"
type: INNER_PRODUCT
bottom: "fc7"
top: "fc8"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
inner_product_param {
num_output: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layers {
name: "accuracy"
type: ACCURACY
bottom: "fc8"
bottom: "label"
top: "accuracy"
include: { phase: TEST }
}
layers {
name: "loss"
type: SOFTMAX_LOSS
bottom: "fc8"
bottom: "label"
top: "loss"
}
这是模型的测试文件。
deploy.txt
name: "AlexNet"
layers
{
name: "data"
type: MEMORY_DATA
top: "data"
top: "label"
memory_data_param
{
batch_size: 1
channels: 3
height: 80
width: 64
}
transform_param
{
crop_size: 64
mirror: false
mean_file: "../../examples/Alexnet/mean.binaryproto"
}
}
layers {
name: "conv1"
type: CONVOLUTION
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 96
kernel_size: 6
stride: 2
}
bottom: "data"
top: "conv1"
}
layers {
name: "relu1"
type: RELU
bottom: "conv1"
top: "conv1"
}
layers {
name: "norm1"
type: LRN
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
bottom: "conv1"
top: "norm1"
}
layers {
name: "pool1"
type: POOLING
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
bottom: "norm1"
top: "pool1"
}
layers {
name: "conv2"
type: CONVOLUTION
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 256
pad: 2
kernel_size: 4
group: 2
}
bottom: "pool1"
top: "conv2"
}
layers {
name: "relu2"
type: RELU
bottom: "conv2"
top: "conv2"
}
layers {
name: "norm2"
type: LRN
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
bottom: "conv2"
top: "norm2"
}
layers {
name: "pool2"
type: POOLING
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
bottom: "norm2"
top: "pool2"
}
layers {
name: "conv3"
type: CONVOLUTION
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
}
bottom: "pool2"
top: "conv3"
}
layers {
name: "relu3"
type: RELU
bottom: "conv3"
top: "conv3"
}
layers {
name: "conv4"
type: CONVOLUTION
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
group: 2
}
bottom: "conv3"
top: "conv4"
}
layers {
name: "relu4"
type: RELU
bottom: "conv4"
top: "conv4"
}
layers {
name: "conv5"
type: CONVOLUTION
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
group: 2
}
bottom: "conv4"
top: "conv5"
}
layers {
name: "relu5"
type: RELU
bottom: "conv5"
top: "conv5"
}
layers {
name: "pool5"
type: POOLING
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
bottom: "conv5"
top: "pool5"
}
layers {
name: "fc6"
type: INNER_PRODUCT
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
inner_product_param {
num_output: 4096
}
bottom: "pool5"
top: "fc6"
}
layers {
name: "relu6"
type: RELU
bottom: "fc6"
top: "fc6"
}
layers {
name: "drop6"
type: DROPOUT
dropout_param {
dropout_ratio: 0.5
}
bottom: "fc6"
top: "fc6"
}
layers {
name: "fc7"
type: INNER_PRODUCT
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
inner_product_param {
num_output: 4096
}
bottom: "fc6"
top: "fc7"
}
layers {
name: "relu7"
type: RELU
bottom: "fc7"
top: "fc7"
}
layers {
name: "drop7"
type: DROPOUT
dropout_param {
dropout_ratio: 0.5
}
bottom: "fc7"
top: "fc7"
}
layers {
name: "fc8"
type: INNER_PRODUCT
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
inner_product_param {
num_output: 2
}
bottom: "fc7"
top: "fc8"
}
layers {
name: "prob"
type: SOFTMAX
bottom: "fc8"
top: "prob"
}
这个错误有什么问题？
【问题讨论】：
标签： deep-learning caffe conv-neural-network