windows10 conda2 使用caffe訓練訓練自己的數據
阿新 • • 發佈：2018-08-22
caffe lex cond www mom nal shuff sna nor
首先得到了https://blog.csdn.net/gybheroin/article/details/72581318系列博客的幫助。表示感激。
關於安裝caffe已在之前的博客介紹，自用可行，https://www.cnblogs.com/MY0213/p/9225310.html
1.數據源
首先使用的數據集為人臉數據集,可在百度雲自行下載：
鏈接：https://pan.baidu.com/s/156DiOuB46wKrM0cEaAgfMw 密碼：1ap0
將train.zip解壓可得數據源，label文件是val.txt和train.txt。
2.將圖片數據做成lmdb數據源
SET GLOG_logtostderr=1 SET RESIZE_HEIGHT=227 SET RESIZE_WIDTH=227 "convert_imageset" --resize_height=227 --resize_width=227 --shuffle "train/" "train.txt" "mtraindb" "convert_imageset" --resize_height=227 --resize_width=227 --shuffle "val/" "val.txt" "mvaldb" pause
詳見face_lmdb.bat,將數據做成同等大小的數據。
3. 得到圖像均值
SET GLOG_logtostderr=1 "compute_image_mean" "mtraindb" "train_mean.binaryproto" pause
詳見mean_face.bat
訓練時先做減均值的操作，可能對訓練效果有好處
這裏可以用固定的圖片均值，是多少可以直接百度谷歌，這一步也可以不做，唐宇迪大神說影響不大。
4. 圖像訓練
SET GLOG_logostderr=1 caffe train --solver=solver.prototxt pause
詳見train.bat
net: "train.prototxt" test_iter: 100 test_interval: 1000 # lr for fine-tuning should be lower than when starting from scratch base_lr: 0.001 lr_policy: "step" gamma: 0.1 # stepsize should also be lower, as we‘re closer to being done stepsize: 1000 display: 50 max_iter: 10000 momentum: 0.9 weight_decay: 0.0005 snapshot: 1000 snapshot_prefix: "model" # uncomment the following to default to CPU mode solving # solver_mode: CPU
詳見solver.prototxt
關於solver.prototxt的內涵可查看
https://blog.csdn.net/qq_27923041/article/details/55211808
############################# DATA Layer #############################
name: "face_train_val"
layer {
top: "data"
top: "label"
name: "data"
type: "Data"
data_param {
source: "mtraindb"
backend:LMDB
batch_size: 64
}
transform_param {
mean_file: "train_mean.binaryproto"
mirror: true
}
include: { phase: TRAIN }
}
layer {
top: "data"
top: "label"
name: "data"
type: "Data"
data_param {
source: "mvaldb"
backend:LMDB
batch_size: 64
}
transform_param {
mean_file: "train_mean.binaryproto"
mirror: true
}
include: {
phase: TEST
}
}
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: "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
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: 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
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: 0.1
}
}
}
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: 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
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: 0.1
}
}
}
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: 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-expr"
type: "InnerProduct"
bottom: "fc7"
top: "fc8-expr"
param {
lr_mult: 10
decay_mult: 1
}
param {
lr_mult: 20
decay_mult: 0
}
inner_product_param {
num_output: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "accuracy"
type: "Accuracy"
bottom: "fc8-expr"
bottom: "label"
top: "accuracy"
include {
phase: TEST
}
}
layer {
name: "loss"
type: "SoftmaxWithLoss"
bottom: "fc8-expr"
bottom: "label"
top: "loss"
}
詳見train.prototxt，也就是將alexnet中最後的1000變為2就可以了。
這個過程需要5天左右（我用的cpu）,可以直接用已有模型alexnet_iter_50000_full_conv.caffemodel
5. 測試
可用run_face_detect_batch.py測試人臉檢測效果。
6. 總結
這個網絡測試時特別慢，用的是slipping window的方法。下面的文章再介紹快速一點的faster rcnn 及FPN。
slipping window中用了Casting a Classifier into a Fully Convolutional Network 的方法。這一方法在其他網絡中也可用。
關於rcnn的演進，可見https://www.cnblogs.com/MY0213/p/9460562.html
歡迎批評指正。
windows10 conda2 使用caffe訓練訓練自己的數據