问题
I'm always getting the same accuracy. When i run the classification, its always showing 1 label. I went through many articles and everyone recommending to shuffle the data. I did that using random.shuffle and also tried convert_imageset script as well but no help. Please find my solver.protoxt and caffenet_train.prototxt below. I have 1000 images in my dataset. 833 images in train_lmdb and rest of them in validation_lmdb.
Training logs:
I1112 22:41:26.373661 10633 solver.cpp:347] Iteration 1184, Testing net (#0)
I1112 22:41:26.828955 10633 solver.cpp:414] Test net output #0: accuracy = 1
I1112 22:41:26.829105 10633 solver.cpp:414] Test net output #1: loss = 4.05117e-05 (* 1 = 4.05117e-05 loss)
I1112 22:41:26.952340 10656 data_layer.cpp:73] Restarting data prefetching from start.
I1112 22:41:28.697041 10655 data_layer.cpp:73] Restarting data prefetching from start.
I1112 22:41:30.889508 10655 data_layer.cpp:73] Restarting data prefetching from start.
I1112 22:41:32.288192 10633 solver.cpp:347] Iteration 1200, Testing net (#0)
I1112 22:41:32.716845 10633 solver.cpp:414] Test net output #0: accuracy = 1
I1112 22:41:32.716941 10633 solver.cpp:414] Test net output #1: loss = 4.08e-05 (* 1 = 4.08e-05 loss)
I1112 22:41:32.861697 10655 data_layer.cpp:73] Restarting data prefetching from start.
I1112 22:41:33.050954 10633 solver.cpp:239] Iteration 1200 (2.6885 iter/s, 18.5978s/50 iters), loss = 0.000119432
I1112 22:41:33.051054 10633 solver.cpp:258] Train net output #0: loss = 0.000119432 (* 1 = 0.000119432 loss)
I1112 22:41:33.051067 10633 sgd_solver.cpp:112] Iteration 1200, lr = 1e-15
I1112 22:41:35.700759 10655 data_layer.cpp:73] Restarting data prefetching from start.
I1112 22:41:37.869782 10655 data_layer.cpp:73] Restarting data prefetching from start.
I1112 22:41:38.169018 10633 solver.cpp:347] Iteration 1216, Testing net (#0)
I1112 22:41:38.396162 10656 data_layer.cpp:73] Restarting data prefetching from start.
I1112 22:41:38.613301 10633 solver.cpp:414] Test net output #0: accuracy = 1
I1112 22:41:38.613348 10633 solver.cpp:414] Test net output #1: loss = 4.09327e-05 (* 1 = 4.09327e-05 loss)
solver.prototxt:
net: "caffenet_train.prototxt"
test_iter: 16
test_interval: 16
base_lr: 0.001
lr_policy: "step"
gamma: 0.1
stepsize: 100
display: 50
max_iter: 2000
momentum: 0.9
weight_decay: 0.0005
snapshot: 500
snapshot_prefix: "output/caffe_model"
solver_mode: GPU
caffenet_train.prototxt
name: "CaffeNet"
layer {
name: "data"
type: "Data"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
mirror: true
crop_size: 227
mean_file: "output/mean.binaryproto"
}
data_param {
source: "output/train_lmdb"
batch_size: 128
backend: LMDB
}
}
layer {
name: "data"
type: "Data"
top: "data"
top: "label"
include {
phase: TEST
}
transform_param {
mirror: false
crop_size: 227
mean_file: "output/mean.binaryproto"
}
data_param {
source: "output/validation_lmdb"
batch_size: 10
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
}
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "pool1"
type: "Pooling"
bottom: "conv1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "norm1"
type: "LRN"
bottom: "pool1"
top: "norm1"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "norm1"
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: 1
}
}
}
layer {
name: "relu2"
type: "ReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "pool2"
type: "Pooling"
bottom: "conv2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "norm2"
type: "LRN"
bottom: "pool2"
top: "norm2"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "conv3"
type: "Convolution"
bottom: "norm2"
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: 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: "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: 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: 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"
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: 2
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"
}
回答1:
Try finetuning with CaffeNet's original caffemodel. Then it will be solved.
来源：https://stackoverflow.com/questions/58830041/test-net-output-0-accuracy-1-always-caffe