Caffe - num_output in prototxt 给出了奇怪的行为
Caffe - num_output in prototxt gives strange behaviour
我正在做一些实验，将 Cifar-10 数据集分成两半，这样每一半包含五个随机 类。我用 bvlc_alexnet 架构训练了一半。因此，我将 num_output 更改为 5 并对网络进行了一些其他小调整。当我检查日志文件时，我发现损失增加到 80 左右，测试精度为 0.
然而，当我将 num_output 更改为 10 时，训练似乎变得正常，即损失稳步下降，结果测试准确率约为 70%.
这怎么解释？
train_val.prototxt
name: "AlexNet"
layer {
name: "data"
type: "Data"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
mirror: true
crop_size: 25
}
data_param {
source: "/home/apples/caffe/cifar/cifarA/cifar_A_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: 25
}
data_param {
source: "/home/apples/caffe/cifar/cifarA/cifar_A_val_lmdb"
batch_size: 100
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: 2
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_mnist"
type: "InnerProduct"
bottom: "fc7"
top: "fc8_mnist"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 5
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "accuracy"
type: "Accuracy"
bottom: "fc8_mnist"
bottom: "label"
top: "accuracy"
include {
phase: TEST
}
}
layer {
name: "loss"
type: "SoftmaxWithLoss"
bottom: "fc8_mnist"
bottom: "label"
top: "loss"
}
此拆分包含 类 0、4、5、6 和 8。我使用 create_imagenet.sh 脚本创建 lmdb 文件。
train.txt
的示例
0/attack_aircraft_s_001759.png 0
0/propeller_plane_s_001689.png 0
4/fallow_deer_s_000021.png 4
4/alces_alces_s_000686.png 4
5/toy_spaniel_s_000327.png 5
5/toy_spaniel_s_000511.png 5
6/bufo_viridis_s_000502.png 6
6/bufo_viridis_s_001005.png 6
8/passenger_ship_s_000236.png 8
8/passenger_ship_s_000853.png 8
样本 val.txt
0/attack_aircraft_s_000002.png 0
0/propeller_plane_s_000006.png 0
4/fallow_deer_s_000001.png 4
4/alces_alces_s_000012.png 4
5/toy_spaniel_s_000020.png 5
6/bufo_viridis_s_000016.png 6
8/passenger_ship_s_000060.png 8
正如评论中指出的那样，Caffe 期望标签是 0 到 num_classes - 1 之间的整数。在您的例子中，当您将标签数量设置为 5 时，Caffe 将在最后一层创建五个输出神经元。当你要求它预测 class 6 或 8 时，你是在要求它最大化一个不存在的神经元的输出，而 Caffe 显然做不到。
现在，当您重新标记数据并将 num_classes 设置为 5 时，您做了正确的事情，因此它起作用了。当你将 num_classes 设置为 10 时，网络仍然可以工作，因为现在它有 10 个输出神经元，足以 class 化五个 classes。它会了解到从 5 到 9 的 classes 永远不会出现，因此永远不应该被预测，它只会以一种总是会导致非常小的值的方式调整权重 returned那些输出神经元。然而，重要的是要注意，神经网络自然是随机的，因此它可能偶尔 return 一个从未呈现给它的 class，所以我希望 NN 具有 num_classes大于 classes 的实际数量，比正确 num_classes.
的表现更差
我正在做一些实验，将 Cifar-10 数据集分成两半，这样每一半包含五个随机 类。我用 bvlc_alexnet 架构训练了一半。因此，我将 num_output 更改为 5 并对网络进行了一些其他小调整。当我检查日志文件时，我发现损失增加到 80 左右，测试精度为 0.
然而，当我将 num_output 更改为 10 时，训练似乎变得正常，即损失稳步下降，结果测试准确率约为 70%.
这怎么解释？
train_val.prototxt
name: "AlexNet"
layer {
name: "data"
type: "Data"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
mirror: true
crop_size: 25
}
data_param {
source: "/home/apples/caffe/cifar/cifarA/cifar_A_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: 25
}
data_param {
source: "/home/apples/caffe/cifar/cifarA/cifar_A_val_lmdb"
batch_size: 100
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: 2
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_mnist"
type: "InnerProduct"
bottom: "fc7"
top: "fc8_mnist"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 5
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "accuracy"
type: "Accuracy"
bottom: "fc8_mnist"
bottom: "label"
top: "accuracy"
include {
phase: TEST
}
}
layer {
name: "loss"
type: "SoftmaxWithLoss"
bottom: "fc8_mnist"
bottom: "label"
top: "loss"
}
此拆分包含 类 0、4、5、6 和 8。我使用 create_imagenet.sh 脚本创建 lmdb 文件。
train.txt
的示例0/attack_aircraft_s_001759.png 0
0/propeller_plane_s_001689.png 0
4/fallow_deer_s_000021.png 4
4/alces_alces_s_000686.png 4
5/toy_spaniel_s_000327.png 5
5/toy_spaniel_s_000511.png 5
6/bufo_viridis_s_000502.png 6
6/bufo_viridis_s_001005.png 6
8/passenger_ship_s_000236.png 8
8/passenger_ship_s_000853.png 8
样本 val.txt
0/attack_aircraft_s_000002.png 0
0/propeller_plane_s_000006.png 0
4/fallow_deer_s_000001.png 4
4/alces_alces_s_000012.png 4
5/toy_spaniel_s_000020.png 5
6/bufo_viridis_s_000016.png 6
8/passenger_ship_s_000060.png 8
正如评论中指出的那样，Caffe 期望标签是 0 到 num_classes - 1 之间的整数。在您的例子中，当您将标签数量设置为 5 时，Caffe 将在最后一层创建五个输出神经元。当你要求它预测 class 6 或 8 时，你是在要求它最大化一个不存在的神经元的输出，而 Caffe 显然做不到。
现在，当您重新标记数据并将 num_classes 设置为 5 时，您做了正确的事情，因此它起作用了。当你将 num_classes 设置为 10 时，网络仍然可以工作，因为现在它有 10 个输出神经元，足以 class 化五个 classes。它会了解到从 5 到 9 的 classes 永远不会出现，因此永远不应该被预测，它只会以一种总是会导致非常小的值的方式调整权重 returned那些输出神经元。然而，重要的是要注意，神经网络自然是随机的，因此它可能偶尔 return 一个从未呈现给它的 class，所以我希望 NN 具有 num_classes大于 classes 的实际数量，比正确 num_classes.