先放出二者的完整例子文件,然后分析:
train_val.prototxt文件如下:
name: "CaffeNet"
layer {
name: "data"
type: "Data"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
mirror: true
crop_size: 227
mean_file: "data/ilsvrc12/imagenet_mean.binaryproto"
}
# mean pixel / channel-wise mean instead of mean image
# transform_param {
# crop_size: 227
# mean_value: 104
# mean_value: 117
# mean_value: 123
# mirror: true
# }
data_param {
source: "examples/imagenet/ilsvrc12_train_lmdb"
batch_size: 256
backend: LMDB
}
}
layer {
name: "data"
type: "Data"
top: "data"
top: "label"
include {
phase: TEST
}
transform_param {
mirror: false
crop_size: 227
mean_file: "data/ilsvrc12/imagenet_mean.binaryproto"
}
# mean pixel / channel-wise mean instead of mean image
# transform_param {
# crop_size: 227
# mean_value: 104
# mean_value: 117
# mean_value: 123
# mirror: false
# }
data_param {
source: "examples/imagenet/ilsvrc12_val_lmdb"
batch_size: 50
backend: LMDB
}
}
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
}
}
}
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
}
m {
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: "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: "relu7"
type: "ReLU"
bottom: "fc7"
top: "fc7"
}
}
layer {
name: "fc8"
type: "InnerProduct"
bottom: "fc7"
top: "fc8"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 1000
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "accuracy"
type: "Accuracy"
bottom: "fc8"
bottom: "label"
top: "accuracy"
include {
phase: TEST
}
}
layer {
name: "loss"
type: "SoftmaxWithLoss"
bottom: "fc8"
bottom: "label"
top: "loss"
}
修改后的deploy.prototxt文件:
name: "CaffeNet"
layer {
name: "data"
type: "Input"
top: "data"
input_param { shape: { dim: 10 dim: 3 dim: 227 dim: 227 } }
}
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
convolution_param {
num_output: 96
kernel_size: 11
stride: 4
}
。。。。。。。。。。。。。。
layer {
name: "fc8"
type: "InnerProduct"
bottom: "fc7"
top: "fc8"
inner_product_param {
num_output: 1000
}
}
layer {
name: "prob"
type: "Softmax"
bottom: "fc8"
top: "prob"
}
变化的有几个地方:
1:输入数据层data层:将原来的train和test输入数据参数完全删除,
删除的部分:
layer {
name: "data"
type: "Data"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
mirror: true
crop_size: 227
mean_file: "data/ilsvrc12/imagenet_mean.binaryproto"
}
# mean pixel / channel-wise mean instead of mean image
# transform_param {
# crop_size: 227
# mean_value: 104
# mean_value: 117
# mean_value: 123
# mirror: true
# }
data_param {
source: "examples/imagenet/ilsvrc12_train_lmdb"
batch_size: 256
backend: LMDB
}
}
layer {
name: "data"
type: "Data"
top: "data"
top: "label"
include {
phase: TEST
}
transform_param {
mirror: false
crop_size: 227
mean_file: "data/ilsvrc12/imagenet_mean.binaryproto"
}
# mean pixel / channel-wise mean instead of mean image
# transform_param {
# crop_size: 227
# mean_value: 104
# mean_value: 117
# mean_value: 123
# mirror: false
# }
data_param {
source: "examples/imagenet/ilsvrc12_val_lmdb"
batch_size: 50
backend: LMDB
}
}
用这样的代替
layer {
name: "data"
type: "Input"
top: "data"
input_param { shape: { dim: 10 dim: 3 dim: 227 dim: 227 } }
}
shape: { dim: 10 dim: 3 dim: 227 dim: 227 }中第一个dim代表卷积核个数10个,第二个dim代表channel个数3个(对于图片是RGB三通道),第三第四个分别是width和height图片的。
2:卷积层中对应参数:
**weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}**
完全删除,可以用关键字weight_filler和bias_filler来删除,他们是指定学习的参数的,deploy时用model中的参数,而不用自己更新,故删去。
3:最后的
layer {
name: "accuracy"
type: "Accuracy"
bottom: "fc8"
bottom: "label"
top: "accuracy"
include {
phase: TEST
}
完全删除,不需要test
4:原来的最后一层loss层改为pro层
layer {
name: "loss"
type: "SoftmaxWithLoss"
bottom: "fc8"
bottom: "label"
top: "loss"
}
A:将其中的SoftmaxWithLoss替换为Softmax
B:删除其中的bottom:”label”行,因为测试时需要预测label而不是给你一个已知label。
C:同时将最后一层loss层改为pro层
因此改完之后最后一层就是这样的:
layer {
name: "prob"
type: "Softmax"
bottom: "fc8"
top: "prob"
}
这里的name: “prob”就是你在用python预测时读取的layer的name,一定要对应上