CAFFE -FCN訓練配置過程

轉載自 http://blog.csdn.net/jiongnima/article/details/78549326?locationNum=3&fps=1

   在2015年發表於計算機視覺頂會CVPR上的Fully Convolutional Networks for Semantic Segmentation 論文(下文中簡稱FCN)開創了圖像語義分割的新流派。在後來的科研工作者發表學術論文做實驗的時候，還常常把自己的實驗結果與FCN相比較。筆者在做實驗的時候，也去改動並跑了跑FCN的代碼，可是問題出現了，筆者的訓練並不收斂。

   下面是筆者最初的訓練prototxt文件：

 name: "fcn8snet"
 layer {
   name: "data"
   type: "ImageData"
   top: "data"
   top: "fake-dlabel"
   include {
     phase: TRAIN
   }
   transform_param {
     mean_file: "fcn8s_cityscapes/fcn_mean.binaryproto"
     #scale: 0.00390625
   }
   image_data_param {
     source: "fcn8s_cityscapes/data/train_img.txt"
     batch_size: 1
     root_folder: "fcn8s_cityscapes/data/train/image/"
   }
 }
 layer {
   name: "label"
   type: "ImageData"
   top: "label"
   top: "fake_llabel"
   include {
     phase: TRAIN
   }
   image_data_param {
     source: "fcn8s_cityscapes/data/train_label.txt"
     batch_size: 1
     root_folder: "fcn8s_cityscapes/data/train/label/"
     is_color: false
   }
 }
 layer {
   name: "conv1_1"
   type: "Convolution"
   bottom: "data"
   top: "conv1_1"
   param {
     lr_mult: 1
     decay_mult: 1
   }
   param {
     lr_mult: 2
     decay_mult: 0
   }
   convolution_param {
     num_output: 64
     pad: 100
     kernel_size: 3
     stride: 1
   }
 }
 layer {
   name: "relu1_1"
   type: "ReLU"
   bottom: "conv1_1"
   top: "conv1_1"
 }
 layer {
   name: "conv1_2"
   type: "Convolution"
   bottom: "conv1_1"
   top: "conv1_2"
   param {
     lr_mult: 1
     decay_mult: 1
   }
   param {
     lr_mult: 2
     decay_mult: 0
   }
   convolution_param {
     num_output: 64
     pad: 1
     kernel_size: 3
     stride: 1
   }
 }
 layer {
   name: "relu1_2"
   type: "ReLU"
   bottom: "conv1_2"
   top: "conv1_2"
 }
 layer {
   name: "pool1"
   type: "Pooling"
   bottom: "conv1_2"
   top: "pool1"
   pooling_param {
     pool: MAX
     kernel_size: 2
     stride: 2
   }
 }
 layer {
   name: "conv2_1"
   type: "Convolution"
   bottom: "pool1"
   top: "conv2_1"
   param {
     lr_mult: 1
     decay_mult: 1
   }
   param {
     lr_mult: 2
     decay_mult: 0
   }
   convolution_param {
     num_output: 128
     pad: 1
     kernel_size: 3
     stride: 1
   }
 }
 layer {
   name: "relu2_1"
   type: "ReLU"
   bottom: "conv2_1"
   top: "conv2_1"
 }
 layer {
   name: "conv2_2"
   type: "Convolution"
   bottom: "conv2_1"
   top: "conv2_2"
   param {
     lr_mult: 1
     decay_mult: 1
   }
   param {
     lr_mult: 2
     decay_mult: 0
   }
   convolution_param {
     num_output: 128
     pad: 1
     kernel_size: 3
     stride: 1
   }
 }
 layer {
   name: "relu2_2"
   type: "ReLU"
   bottom: "conv2_2"
   top: "conv2_2"
 }
 layer {
   name: "pool2"
   type: "Pooling"
   bottom: "conv2_2"
   top: "pool2"
   pooling_param {
     pool: MAX
     kernel_size: 2
     stride: 2
   }
 }
 layer {
   name: "conv3_1"
   type: "Convolution"
   bottom: "pool2"
   top: "conv3_1"
   param {
     lr_mult: 1
     decay_mult: 1
   }
   param {
     lr_mult: 2
     decay_mult: 0
   }
   convolution_param {
     num_output: 256
     pad: 1
     kernel_size: 3
     stride: 1
   }
 }
 layer {
   name: "relu3_1"
   type: "ReLU"
   bottom: "conv3_1"
   top: "conv3_1"
 }
 layer {
   name: "conv3_2"
   type: "Convolution"
   bottom: "conv3_1"
   top: "conv3_2"
   param {
     lr_mult: 1
     decay_mult: 1
   }
   param {
     lr_mult: 2
     decay_mult: 0
   }
   convolution_param {
     num_output: 256
     pad: 1
     kernel_size: 3
     stride: 1
   }
 }
 layer {
   name: "relu3_2"
   type: "ReLU"
   bottom: "conv3_2"
   top: "conv3_2"
 }
 layer {
   name: "conv3_3"
   type: "Convolution"
   bottom: "conv3_2"
   top: "conv3_3"
   param {
     lr_mult: 1
     decay_mult: 1
   }
   param {
     lr_mult: 2
     decay_mult: 0
   }
   convolution_param {
     num_output: 256
     pad: 1
     kernel_size: 3
     stride: 1
   }
 }
 layer {
   name: "relu3_3"
   type: "ReLU"
   bottom: "conv3_3"
   top: "conv3_3"
 }
 layer {
   name: "pool3"
   type: "Pooling"
   bottom: "conv3_3"
   top: "pool3"
   pooling_param {
     pool: MAX
     kernel_size: 2
     stride: 2
   }
 }
 layer {
   name: "conv4_1"
   type: "Convolution"
   bottom: "pool3"
   top: "conv4_1"
   param {
     lr_mult: 1
     decay_mult: 1
   }
   param {
     lr_mult: 2
     decay_mult: 0
   }
   convolution_param {
     num_output: 512
     pad: 1
     kernel_size: 3
     stride: 1
   }
 }
 layer {
   name: "relu4_1"
   type: "ReLU"
   bottom: "conv4_1"
   top: "conv4_1"
 }
 layer {
   name: "conv4_2"
   type: "Convolution"
   bottom: "conv4_1"
   top: "conv4_2"
   param {
     lr_mult: 1
     decay_mult: 1
   }
   param {
     lr_mult: 2
     decay_mult: 0
   }
   convolution_param {
     num_output: 512
     pad: 1
     kernel_size: 3
     stride: 1
   }
 }
 layer {
   name: "relu4_2"
   type: "ReLU"
   bottom: "conv4_2"
   top: "conv4_2"
 }
 layer {
   name: "conv4_3"
   type: "Convolution"
   bottom: "conv4_2"
   top: "conv4_3"
   param {
     lr_mult: 1
     decay_mult: 1
   }
   param {
     lr_mult: 2
     decay_mult: 0
   }
   convolution_param {
     num_output: 512
     pad: 1
     kernel_size: 3
     stride: 1
   }
 }
 layer {
   name: "relu4_3"
   type: "ReLU"
   bottom: "conv4_3"
   top: "conv4_3"
 }
 layer {
   name: "pool4"
   type: "Pooling"
   bottom: "conv4_3"
   top: "pool4"
   pooling_param {
     pool: MAX
     kernel_size: 2
     stride: 2
   }
 }
 layer {
   name: "conv5_1"
   type: "Convolution"
   bottom: "pool4"
   top: "conv5_1"
   param {
     lr_mult: 1
     decay_mult: 1
   }
   param {
     lr_mult: 2
     decay_mult: 0
   }
   convolution_param {
     num_output: 512
     pad: 1
     kernel_size: 3
     stride: 1
   }
 }
 layer {
   name: "relu5_1"
   type: "ReLU"
   bottom: "conv5_1"
   top: "conv5_1"
 }
 layer {
   name: "conv5_2"
   type: "Convolution"
   bottom: "conv5_1"
   top: "conv5_2"
   param {
     lr_mult: 1
     decay_mult: 1
   }
   param {
     lr_mult: 2
     decay_mult: 0
   }
   convolution_param {
     num_output: 512
     pad: 1
     kernel_size: 3
     stride: 1
   }
 }
 layer {
   name: "relu5_2"
   type: "ReLU"
   bottom: "conv5_2"
   top: "conv5_2"
 }
 layer {
   name: "conv5_3"
   type: "Convolution"
   bottom: "conv5_2"
   top: "conv5_3"
   param {
     lr_mult: 1
     decay_mult: 1
   }
   param {
     lr_mult: 2
     decay_mult: 0
   }
   convolution_param {
     num_output: 512
     pad: 1
     kernel_size: 3
     stride: 1
   }
 }
 layer {
   name: "relu5_3"
   type: "ReLU"
   bottom: "conv5_3"
   top: "conv5_3"
 }
 layer {
   name: "pool5"
   type: "Pooling"
   bottom: "conv5_3"
   top: "pool5"
   pooling_param {
     pool: MAX
     kernel_size: 2
     stride: 2
   }
 }
 layer {
   name: "fc6"
   type: "Convolution"
   bottom: "pool5"
   top: "fc6"
   param {
     lr_mult: 1
     decay_mult: 1
   }
   param {
     lr_mult: 2
     decay_mult: 0
   }
   convolution_param {
     num_output: 4096
     pad: 0
     kernel_size: 7
     stride: 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: "Convolution"
   bottom: "fc6"
   top: "fc7"
   param {
     lr_mult: 1
     decay_mult: 1
   }
   param {
     lr_mult: 2
     decay_mult: 0
   }
   convolution_param {
     num_output: 4096
     pad: 0
     kernel_size: 1
     stride: 1
   }
 }
 layer {
   name: "relu7"
   type: "ReLU"
     kernel_size: 1
     stride: 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    dropout_ratio: 0.5
   }
 }
 layer {
   name: "score_fr_cityscapes"
   type: "Convolution"
   bottom: "fc7"
   top: "score_fr"
   param {
     lr_mult: 1
     decay_mult: 1
   }
   param {
     lr_mult: 2
     decay_mult: 0
   }
   }
 }