當我在PASCAL VOC 2012數據集測試Deeplab-VER2,測試淨產生僅記錄巨大大小的文件與輸出[見下面的日誌],但它不產生任何.MAT文件在features/deeplab_largeFOV/val/fc8文件夾中。我的網絡運行時沒有任何錯誤,即使在運行超過24小時後也不會終止。任何幫助將不勝感激。沒有.MAT文件生成的deeplab
PS。我看着由run_pascal.sh腳本生成的test_val.prototxt文件,所有路徑和一切看起來都很好。
`Log file created at: 2016/09/20 12:57:35
Running on machine: CECS50P7PJ1
Log line format: [IWEF]mmdd hh:mm:ss.uuuuuu threadid file:line] msg
I0920 12:57:35.378067 12793 caffe.cpp:237] Use GPU with device ID 0
I0920 12:57:35.460089 12793 caffe.cpp:241] GPU device name: GeForce GTX TITAN X
I0920 12:57:35.947268 12793 net.cpp:49] Initializing net from parameters:
name: "deeplab_largeFOV"
state {
phase: TEST
}
layer {
name: "data"
type: "ImageSegData"
top: "data"
top: "label"
include {
phase: TEST
}
transform_param {
mirror: false
crop_size: 513
mean_value: 104.008
mean_value: 116.669
mean_value: 122.675
}
image_data_param {
source: "voc12/list/val.txt"
batch_size: 1
root_folder: "/home/aisha/VOCdevkit/VOC2012"
label_type: NONE
}
}
layer {
name: "conv1_1"
type: "Convolution"
bottom: "data"
top: "conv1_1"
convolution_param {
num_output: 64
pad: 1
kernel_size: 3
}
}
layer {
name: "relu1_1"
type: "ReLU"
bottom: "conv1_1"
top: "conv1_1"
}
layer {
name: "conv1_2"
type: "Convolution"
bottom: "conv1_1"
top: "conv1_2"
convolution_param {
num_output: 64
pad: 1
kernel_size: 3
}
}
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: 3
stride: 2
pad: 1
}
}
layer {
name: "conv2_1"
type: "Convolution"
bottom: "pool1"
top: "conv2_1"
convolution_param {
num_output: 128
pad: 1
kernel_size: 3
}
}
layer {
name: "relu2_1"
type: "ReLU"
bottom: "conv2_1"
top: "conv2_1"
}
layer {
name: "conv2_2"
type: "Convolution"
bottom: "conv2_1"
top: "conv2_2"
convolution_param {
num_output: 128
pad: 1
kernel_size: 3
}
}
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: 3
stride: 2
pad: 1
}
}
layer {
name: "conv3_1"
type: "Convolution"
bottom: "pool2"
top: "conv3_1"
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
}
}
layer {
name: "relu3_1"
type: "ReLU"
bottom: "conv3_1"
top: "conv3_1"
}
layer {
name: "conv3_2"
type: "Convolution"
bottom: "conv3_1"
top: "conv3_2"
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
}
}
layer {
name: "relu3_2"
type: "ReLU"
bottom: "conv3_2"
top: "conv3_2"
}
layer {
name: "conv3_3"
type: "Convolution"
bottom: "conv3_2"
top: "conv3_3"
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
}
}
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: 3
stride: 2
pad: 1
}
}
layer {
name: "conv4_1"
type: "Convolution"
bottom: "pool3"
top: "conv4_1"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
name: "relu4_1"
type: "ReLU"
bottom: "conv4_1"
top: "conv4_1"
}
layer {
name: "conv4_2"
type: "Convolution"
bottom: "conv4_1"
top: "conv4_2"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
name: "relu4_2"
type: "ReLU"
bottom: "conv4_2"
top: "conv4_2"
}
layer {
name: "conv4_3"
type: "Convolution"
bottom: "conv4_2"
top: "conv4_3"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
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: 3
stride: 1
pad: 1
}
}
layer {
name: "conv5_1"
type: "Convolution"
bottom: "pool4"
top: "conv5_1"
convolution_param {
num_output: 512
pad: 2
kernel_size: 3
dilation: 2
}
}
layer {
name: "relu5_1"
type: "ReLU"
bottom: "conv5_1"
top: "conv5_1"
}
layer {
name: "conv5_2"
type: "Convolution"
bottom: "conv5_1"
top: "conv5_2"
convolution_param {
num_output: 512
pad: 2
kernel_size: 3
dilation: 2
}
}
layer {
name: "relu5_2"
type: "ReLU"
bottom: "conv5_2"
top: "conv5_2"
}
layer {
name: "conv5_3"
type: "Convolution"
bottom: "conv5_2"
top: "conv5_3"
convolution_param {
num_output: 512
pad: 2
kernel_size: 3
dilation: 2
}
}
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: 3
stride: 1
pad: 1
}
}
layer {
name: "pool5a"
type: "Pooling"
bottom: "pool5"
top: "pool5a"
pooling_param {
pool: AVE
kernel_size: 3
stride: 1
pad: 1
}
}
layer {
name: "fc6"
type: "Convolution"
bottom: "pool5a"
top: "fc6"
param {
name: "fc6_w"
lr_mult: 1
decay_mult: 1
}
param {
name: "fc6_b"
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 1024
pad: 12
kernel_size: 3
dilation: 12
}
}
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 {
name: "fc7_w"
lr_mult: 1
decay_mult: 1
}
param {
name: "fc7_b"
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 1024
kernel_size: 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_voc12"
type: "Convolution"
bottom: "fc7"
top: "fc8_voc12"
param {
name: "fc8_w"
lr_mult: 10
decay_mult: 1
}
param {
name: "fc8_b"
lr_mult: 20
decay_mult: 0
}
convolution_param {
num_output: 21
kernel_size: 1
}
}
layer {
name: "fc8_interp"
type: "Interp"
bottom: "fc8_voc12"
top: "fc8_interp"
interp_param {
zoom_factor: 8
}
}
layer {
name: "fc8_mat"
type: "MatWrite"
include {
phase: TEST
}
mat_write_param {
prefix: "voc12/features/deeplab_largeFOV/val/fc8/"
source: "voc12/list/val_id.txt"
strip: 0
period: 1
}
}
layer {
name: "silence"
type: "Silence"
bottom: "label"
include {
phase: TEST
}
}
I0920 12:57:35.947854 12793 layer_factory.hpp:77] Creating layer data
I0920 12:57:35.947927 12793 net.cpp:106] Creating Layer data
I0920 12:57:35.947945 12793 net.cpp:411] data -> data
I0920 12:57:35.947999 12793 net.cpp:411] data -> label
I0920 12:57:35.948024 12793 net.cpp:411] data -> (automatic)
I0920 12:57:35.948052 12793 image_seg_data_layer.cpp:46] Opening file voc12/list/val.txt
I0920 12:57:35.950197 12793 image_seg_data_layer.cpp:68] A total of 1449 images.
I0920 12:57:35.971616 12793 image_seg_data_layer.cpp:137] output data size: 1,3,513,513
I0920 12:57:35.971668 12793 image_seg_data_layer.cpp:141] output label size: 1,1,513,513
`
我想通了這個問題,這是一個使用的問題。 MatWrite圖層沒有任何其他圖層的輸入,因此無法寫入.mat文件。 – AUKhan