зеркало из https://github.com/microsoft/caffe.git
Use unified train/test nets in examples.
This commit is contained in:
Jeff Donahue
Родитель
cb4555c052
Коммит
e526e2ddd7
|
|
@ -1,10 +1,8 @@
|
|||
# reduce learning rate after 120 epochs (60000 iters) by factor 0f 10
|
||||
# then another factor of 10 after 10 more epochs (5000 iters)
|
||||
|
||||
# The training protocol buffer definition
|
||||
train_net: "cifar10_full_train.prototxt"
|
||||
# The testing protocol buffer definition
|
||||
test_net: "cifar10_full_test.prototxt"
|
||||
# The train/test net protocol buffer definition
|
||||
net: "cifar10_full_train_test.prototxt"
|
||||
# test_iter specifies how many forward passes the test should carry out.
|
||||
# In the case of CIFAR10, we have test batch size 100 and 100 test iterations,
|
||||
# covering the full 10,000 testing images.
|
||||
|
|
|
|||
|
|
@ -1,10 +1,8 @@
|
|||
# reduce learning rate after 120 epochs (60000 iters) by factor 0f 10
|
||||
# then another factor of 10 after 10 more epochs (5000 iters)
|
||||
|
||||
# The training protocol buffer definition
|
||||
train_net: "cifar10_full_train.prototxt"
|
||||
# The testing protocol buffer definition
|
||||
test_net: "cifar10_full_test.prototxt"
|
||||
# The train/test net protocol buffer definition
|
||||
net: "cifar10_full_train_test.prototxt"
|
||||
# test_iter specifies how many forward passes the test should carry out.
|
||||
# In the case of CIFAR10, we have test batch size 100 and 100 test iterations,
|
||||
# covering the full 10,000 testing images.
|
||||
|
|
|
|||
|
|
@ -1,10 +1,8 @@
|
|||
# reduce learning rate after 120 epochs (60000 iters) by factor 0f 10
|
||||
# then another factor of 10 after 10 more epochs (5000 iters)
|
||||
|
||||
# The training protocol buffer definition
|
||||
train_net: "cifar10_full_train.prototxt"
|
||||
# The testing protocol buffer definition
|
||||
test_net: "cifar10_full_test.prototxt"
|
||||
# The train/test net protocol buffer definition
|
||||
net: "cifar10_full_train_test.prototxt"
|
||||
# test_iter specifies how many forward passes the test should carry out.
|
||||
# In the case of CIFAR10, we have test batch size 100 and 100 test iterations,
|
||||
# covering the full 10,000 testing images.
|
||||
|
|
|
|||
|
|
@ -1,174 +0,0 @@
|
|||
name: "CIFAR10_full_train"
|
||||
layers {
|
||||
name: "cifar"
|
||||
type: DATA
|
||||
top: "data"
|
||||
top: "label"
|
||||
data_param {
|
||||
source: "cifar10-leveldb/cifar-train-leveldb"
|
||||
mean_file: "mean.binaryproto"
|
||||
batch_size: 100
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "conv1"
|
||||
type: CONVOLUTION
|
||||
bottom: "data"
|
||||
top: "conv1"
|
||||
blobs_lr: 1
|
||||
blobs_lr: 2
|
||||
convolution_param {
|
||||
num_output: 32
|
||||
pad: 2
|
||||
kernel_size: 5
|
||||
stride: 1
|
||||
weight_filler {
|
||||
type: "gaussian"
|
||||
std: 0.0001
|
||||
}
|
||||
bias_filler {
|
||||
type: "constant"
|
||||
}
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "pool1"
|
||||
type: POOLING
|
||||
bottom: "conv1"
|
||||
top: "pool1"
|
||||
pooling_param {
|
||||
pool: MAX
|
||||
kernel_size: 3
|
||||
stride: 2
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "relu1"
|
||||
type: RELU
|
||||
bottom: "pool1"
|
||||
top: "pool1"
|
||||
}
|
||||
layers {
|
||||
name: "norm1"
|
||||
type: LRN
|
||||
bottom: "pool1"
|
||||
top: "norm1"
|
||||
lrn_param {
|
||||
norm_region: WITHIN_CHANNEL
|
||||
local_size: 3
|
||||
alpha: 5e-05
|
||||
beta: 0.75
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "conv2"
|
||||
type: CONVOLUTION
|
||||
bottom: "norm1"
|
||||
top: "conv2"
|
||||
blobs_lr: 1
|
||||
blobs_lr: 2
|
||||
convolution_param {
|
||||
num_output: 32
|
||||
pad: 2
|
||||
kernel_size: 5
|
||||
stride: 1
|
||||
weight_filler {
|
||||
type: "gaussian"
|
||||
std: 0.01
|
||||
}
|
||||
bias_filler {
|
||||
type: "constant"
|
||||
}
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "relu2"
|
||||
type: RELU
|
||||
bottom: "conv2"
|
||||
top: "conv2"
|
||||
}
|
||||
layers {
|
||||
name: "pool2"
|
||||
type: POOLING
|
||||
bottom: "conv2"
|
||||
top: "pool2"
|
||||
pooling_param {
|
||||
pool: AVE
|
||||
kernel_size: 3
|
||||
stride: 2
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "norm2"
|
||||
type: LRN
|
||||
bottom: "pool2"
|
||||
top: "norm2"
|
||||
lrn_param {
|
||||
norm_region: WITHIN_CHANNEL
|
||||
local_size: 3
|
||||
alpha: 5e-05
|
||||
beta: 0.75
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "conv3"
|
||||
type: CONVOLUTION
|
||||
bottom: "norm2"
|
||||
top: "conv3"
|
||||
convolution_param {
|
||||
num_output: 64
|
||||
pad: 2
|
||||
kernel_size: 5
|
||||
stride: 1
|
||||
weight_filler {
|
||||
type: "gaussian"
|
||||
std: 0.01
|
||||
}
|
||||
bias_filler {
|
||||
type: "constant"
|
||||
}
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "relu3"
|
||||
type: RELU
|
||||
bottom: "conv3"
|
||||
top: "conv3"
|
||||
}
|
||||
layers {
|
||||
name: "pool3"
|
||||
type: POOLING
|
||||
bottom: "conv3"
|
||||
top: "pool3"
|
||||
pooling_param {
|
||||
pool: AVE
|
||||
kernel_size: 3
|
||||
stride: 2
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "ip1"
|
||||
type: INNER_PRODUCT
|
||||
bottom: "pool3"
|
||||
top: "ip1"
|
||||
blobs_lr: 1
|
||||
blobs_lr: 2
|
||||
weight_decay: 250
|
||||
weight_decay: 0
|
||||
inner_product_param {
|
||||
num_output: 10
|
||||
weight_filler {
|
||||
type: "gaussian"
|
||||
std: 0.01
|
||||
}
|
||||
bias_filler {
|
||||
type: "constant"
|
||||
}
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "loss"
|
||||
type: SOFTMAX_LOSS
|
||||
bottom: "ip1"
|
||||
bottom: "label"
|
||||
}
|
||||
|
|
@ -1,4 +1,16 @@
|
|||
name: "CIFAR10_full_test"
|
||||
name: "CIFAR10_full"
|
||||
layers {
|
||||
name: "cifar"
|
||||
type: DATA
|
||||
top: "data"
|
||||
top: "label"
|
||||
data_param {
|
||||
source: "cifar10-leveldb/cifar-train-leveldb"
|
||||
mean_file: "mean.binaryproto"
|
||||
batch_size: 100
|
||||
}
|
||||
include: { phase: TRAIN }
|
||||
}
|
||||
layers {
|
||||
name: "cifar"
|
||||
type: DATA
|
||||
|
|
@ -9,6 +21,7 @@ layers {
|
|||
mean_file: "mean.binaryproto"
|
||||
batch_size: 100
|
||||
}
|
||||
include: { phase: TEST }
|
||||
}
|
||||
layers {
|
||||
name: "conv1"
|
||||
|
|
@ -172,6 +185,7 @@ layers {
|
|||
bottom: "ip1"
|
||||
bottom: "label"
|
||||
top: "accuracy"
|
||||
include: { phase: TEST }
|
||||
}
|
||||
layers {
|
||||
name: "loss"
|
||||
|
|
@ -1,9 +1,7 @@
|
|||
# reduce the learning rate after 8 epochs (4000 iters) by a factor of 10
|
||||
|
||||
# The training protocol buffer definition
|
||||
train_net: "cifar10_quick_train.prototxt"
|
||||
# The testing protocol buffer definition
|
||||
test_net: "cifar10_quick_test.prototxt"
|
||||
# The train/test net protocol buffer definition
|
||||
net: "cifar10_quick_train_test.prototxt"
|
||||
# test_iter specifies how many forward passes the test should carry out.
|
||||
# In the case of MNIST, we have test batch size 100 and 100 test iterations,
|
||||
# covering the full 10,000 testing images.
|
||||
|
|
|
|||
|
|
@ -1,9 +1,7 @@
|
|||
# reduce the learning rate after 8 epochs (4000 iters) by a factor of 10
|
||||
|
||||
# The training protocol buffer definition
|
||||
train_net: "cifar10_quick_train.prototxt"
|
||||
# The testing protocol buffer definition
|
||||
test_net: "cifar10_quick_test.prototxt"
|
||||
# The train/test net protocol buffer definition
|
||||
net: "cifar10_quick_train_test.prototxt"
|
||||
# test_iter specifies how many forward passes the test should carry out.
|
||||
# In the case of MNIST, we have test batch size 100 and 100 test iterations,
|
||||
# covering the full 10,000 testing images.
|
||||
|
|
|
|||
|
|
@ -1,168 +0,0 @@
|
|||
name: "CIFAR10_quick_train"
|
||||
layers {
|
||||
name: "cifar"
|
||||
type: DATA
|
||||
top: "data"
|
||||
top: "label"
|
||||
data_param {
|
||||
source: "cifar10-leveldb/cifar-train-leveldb"
|
||||
mean_file: "mean.binaryproto"
|
||||
batch_size: 100
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "conv1"
|
||||
type: CONVOLUTION
|
||||
bottom: "data"
|
||||
top: "conv1"
|
||||
blobs_lr: 1
|
||||
blobs_lr: 2
|
||||
convolution_param {
|
||||
num_output: 32
|
||||
pad: 2
|
||||
kernel_size: 5
|
||||
stride: 1
|
||||
weight_filler {
|
||||
type: "gaussian"
|
||||
std: 0.0001
|
||||
}
|
||||
bias_filler {
|
||||
type: "constant"
|
||||
}
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "pool1"
|
||||
type: POOLING
|
||||
bottom: "conv1"
|
||||
top: "pool1"
|
||||
pooling_param {
|
||||
pool: MAX
|
||||
kernel_size: 3
|
||||
stride: 2
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "relu1"
|
||||
type: RELU
|
||||
bottom: "pool1"
|
||||
top: "pool1"
|
||||
}
|
||||
layers {
|
||||
name: "conv2"
|
||||
type: CONVOLUTION
|
||||
bottom: "pool1"
|
||||
top: "conv2"
|
||||
blobs_lr: 1
|
||||
blobs_lr: 2
|
||||
convolution_param {
|
||||
num_output: 32
|
||||
pad: 2
|
||||
kernel_size: 5
|
||||
stride: 1
|
||||
weight_filler {
|
||||
type: "gaussian"
|
||||
std: 0.01
|
||||
}
|
||||
bias_filler {
|
||||
type: "constant"
|
||||
}
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "relu2"
|
||||
type: RELU
|
||||
bottom: "conv2"
|
||||
top: "conv2"
|
||||
}
|
||||
layers {
|
||||
name: "pool2"
|
||||
type: POOLING
|
||||
bottom: "conv2"
|
||||
top: "pool2"
|
||||
pooling_param {
|
||||
pool: AVE
|
||||
kernel_size: 3
|
||||
stride: 2
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "conv3"
|
||||
type: CONVOLUTION
|
||||
bottom: "pool2"
|
||||
top: "conv3"
|
||||
blobs_lr: 1
|
||||
blobs_lr: 2
|
||||
convolution_param {
|
||||
num_output: 64
|
||||
pad: 2
|
||||
kernel_size: 5
|
||||
stride: 1
|
||||
weight_filler {
|
||||
type: "gaussian"
|
||||
std: 0.01
|
||||
}
|
||||
bias_filler {
|
||||
type: "constant"
|
||||
}
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "relu3"
|
||||
type: RELU
|
||||
bottom: "conv3"
|
||||
top: "conv3"
|
||||
}
|
||||
layers {
|
||||
name: "pool3"
|
||||
type: POOLING
|
||||
bottom: "conv3"
|
||||
top: "pool3"
|
||||
pooling_param {
|
||||
pool: AVE
|
||||
kernel_size: 3
|
||||
stride: 2
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "ip1"
|
||||
type: INNER_PRODUCT
|
||||
bottom: "pool3"
|
||||
top: "ip1"
|
||||
blobs_lr: 1
|
||||
blobs_lr: 2
|
||||
inner_product_param {
|
||||
num_output: 64
|
||||
weight_filler {
|
||||
type: "gaussian"
|
||||
std: 0.1
|
||||
}
|
||||
bias_filler {
|
||||
type: "constant"
|
||||
}
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "ip2"
|
||||
type: INNER_PRODUCT
|
||||
bottom: "ip1"
|
||||
top: "ip2"
|
||||
blobs_lr: 1
|
||||
blobs_lr: 2
|
||||
inner_product_param {
|
||||
num_output: 10
|
||||
weight_filler {
|
||||
type: "gaussian"
|
||||
std: 0.1
|
||||
}
|
||||
bias_filler {
|
||||
type: "constant"
|
||||
}
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "loss"
|
||||
type: SOFTMAX_LOSS
|
||||
bottom: "ip2"
|
||||
bottom: "label"
|
||||
}
|
||||
|
|
@ -1,4 +1,16 @@
|
|||
name: "CIFAR10_quick_test"
|
||||
name: "CIFAR10_quick"
|
||||
layers {
|
||||
name: "cifar"
|
||||
type: DATA
|
||||
top: "data"
|
||||
top: "label"
|
||||
data_param {
|
||||
source: "cifar10-leveldb/cifar-train-leveldb"
|
||||
mean_file: "mean.binaryproto"
|
||||
batch_size: 100
|
||||
}
|
||||
include: { phase: TRAIN }
|
||||
}
|
||||
layers {
|
||||
name: "cifar"
|
||||
type: DATA
|
||||
|
|
@ -9,6 +21,7 @@ layers {
|
|||
mean_file: "mean.binaryproto"
|
||||
batch_size: 100
|
||||
}
|
||||
include: { phase: TEST }
|
||||
}
|
||||
layers {
|
||||
name: "conv1"
|
||||
|
|
@ -166,6 +179,7 @@ layers {
|
|||
bottom: "ip2"
|
||||
bottom: "label"
|
||||
top: "accuracy"
|
||||
include: { phase: TEST }
|
||||
}
|
||||
layers {
|
||||
name: "loss"
|
||||
|
|
@ -1,5 +1,4 @@
|
|||
train_net: "alexnet_train.prototxt"
|
||||
test_net: "alexnet_val.prototxt"
|
||||
net: "alexnet_train_val.prototxt"
|
||||
test_iter: 1000
|
||||
test_interval: 1000
|
||||
base_lr: 0.01
|
||||
|
|
|
|||
|
|
@ -2,6 +2,8 @@ name: "AlexNet"
|
|||
layers {
|
||||
name: "data"
|
||||
type: DATA
|
||||
top: "data"
|
||||
top: "label"
|
||||
data_param {
|
||||
source: "ilsvrc12_train_leveldb"
|
||||
mean_file: "../../data/ilsvrc12/imagenet_mean.binaryproto"
|
||||
|
|
@ -9,8 +11,21 @@ layers {
|
|||
crop_size: 227
|
||||
mirror: true
|
||||
}
|
||||
include: { phase: TRAIN }
|
||||
}
|
||||
layers {
|
||||
name: "data"
|
||||
type: DATA
|
||||
top: "data"
|
||||
top: "label"
|
||||
data_param {
|
||||
source: "ilsvrc12_val_leveldb"
|
||||
mean_file: "../../data/ilsvrc12/imagenet_mean.binaryproto"
|
||||
batch_size: 50
|
||||
crop_size: 227
|
||||
mirror: false
|
||||
}
|
||||
include: { phase: TEST }
|
||||
}
|
||||
layers {
|
||||
name: "conv1"
|
||||
|
|
@ -308,6 +323,14 @@ layers {
|
|||
bottom: "fc7"
|
||||
top: "fc8"
|
||||
}
|
||||
layers {
|
||||
name: "accuracy"
|
||||
type: ACCURACY
|
||||
bottom: "fc8"
|
||||
bottom: "label"
|
||||
top: "accuracy"
|
||||
include: { phase: TEST }
|
||||
}
|
||||
layers {
|
||||
name: "loss"
|
||||
type: SOFTMAX_LOSS
|
||||
|
|
@ -1,228 +0,0 @@
|
|||
name: "AlexNet"
|
||||
layers {
|
||||
name: "data"
|
||||
type: DATA
|
||||
data_param {
|
||||
source: "ilsvrc12_val_leveldb"
|
||||
mean_file: "../../data/ilsvrc12/imagenet_mean.binaryproto"
|
||||
batch_size: 50
|
||||
crop_size: 227
|
||||
mirror: false
|
||||
}
|
||||
top: "data"
|
||||
top: "label"
|
||||
}
|
||||
layers {
|
||||
name: "conv1"
|
||||
type: CONVOLUTION
|
||||
convolution_param {
|
||||
num_output: 96
|
||||
kernel_size: 11
|
||||
stride: 4
|
||||
}
|
||||
bottom: "data"
|
||||
top: "conv1"
|
||||
}
|
||||
layers {
|
||||
name: "relu1"
|
||||
type: RELU
|
||||
bottom: "conv1"
|
||||
top: "conv1"
|
||||
}
|
||||
layers {
|
||||
name: "norm1"
|
||||
type: LRN
|
||||
lrn_param {
|
||||
local_size: 5
|
||||
alpha: 0.0001
|
||||
beta: 0.75
|
||||
}
|
||||
bottom: "conv1"
|
||||
top: "norm1"
|
||||
}
|
||||
layers {
|
||||
name: "pool1"
|
||||
type: POOLING
|
||||
pooling_param {
|
||||
pool: MAX
|
||||
kernel_size: 3
|
||||
stride: 2
|
||||
}
|
||||
bottom: "norm1"
|
||||
top: "pool1"
|
||||
}
|
||||
layers {
|
||||
name: "conv2"
|
||||
type: CONVOLUTION
|
||||
convolution_param {
|
||||
num_output: 256
|
||||
pad: 2
|
||||
kernel_size: 5
|
||||
group: 2
|
||||
}
|
||||
bottom: "pool1"
|
||||
top: "conv2"
|
||||
}
|
||||
layers {
|
||||
name: "relu2"
|
||||
type: RELU
|
||||
bottom: "conv2"
|
||||
top: "conv2"
|
||||
}
|
||||
layers {
|
||||
name: "norm2"
|
||||
type: LRN
|
||||
lrn_param {
|
||||
local_size: 5
|
||||
alpha: 0.0001
|
||||
beta: 0.75
|
||||
}
|
||||
bottom: "conv2"
|
||||
top: "norm2"
|
||||
}
|
||||
layers {
|
||||
name: "pool2"
|
||||
type: POOLING
|
||||
pooling_param {
|
||||
pool: MAX
|
||||
kernel_size: 3
|
||||
stride: 2
|
||||
}
|
||||
bottom: "norm2"
|
||||
top: "pool2"
|
||||
}
|
||||
layers {
|
||||
name: "conv3"
|
||||
type: CONVOLUTION
|
||||
convolution_param {
|
||||
num_output: 384
|
||||
pad: 1
|
||||
kernel_size: 3
|
||||
}
|
||||
bottom: "pool2"
|
||||
top: "conv3"
|
||||
}
|
||||
layers {
|
||||
name: "relu3"
|
||||
type: RELU
|
||||
bottom: "conv3"
|
||||
top: "conv3"
|
||||
}
|
||||
layers {
|
||||
name: "conv4"
|
||||
type: CONVOLUTION
|
||||
convolution_param {
|
||||
num_output: 384
|
||||
pad: 1
|
||||
kernel_size: 3
|
||||
group: 2
|
||||
}
|
||||
bottom: "conv3"
|
||||
top: "conv4"
|
||||
}
|
||||
layers {
|
||||
name: "relu4"
|
||||
type: RELU
|
||||
bottom: "conv4"
|
||||
top: "conv4"
|
||||
}
|
||||
layers {
|
||||
name: "conv5"
|
||||
type: CONVOLUTION
|
||||
convolution_param {
|
||||
num_output: 256
|
||||
pad: 1
|
||||
kernel_size: 3
|
||||
group: 2
|
||||
}
|
||||
bottom: "conv4"
|
||||
top: "conv5"
|
||||
}
|
||||
layers {
|
||||
name: "relu5"
|
||||
type: RELU
|
||||
bottom: "conv5"
|
||||
top: "conv5"
|
||||
}
|
||||
layers {
|
||||
name: "pool5"
|
||||
type: POOLING
|
||||
pooling_param {
|
||||
pool: MAX
|
||||
kernel_size: 3
|
||||
stride: 2
|
||||
}
|
||||
bottom: "conv5"
|
||||
top: "pool5"
|
||||
}
|
||||
layers {
|
||||
name: "fc6"
|
||||
type: INNER_PRODUCT
|
||||
inner_product_param {
|
||||
num_output: 4096
|
||||
}
|
||||
bottom: "pool5"
|
||||
top: "fc6"
|
||||
}
|
||||
layers {
|
||||
name: "relu6"
|
||||
type: RELU
|
||||
bottom: "fc6"
|
||||
top: "fc6"
|
||||
}
|
||||
layers {
|
||||
name: "drop6"
|
||||
type: DROPOUT
|
||||
dropout_param {
|
||||
dropout_ratio: 0.5
|
||||
}
|
||||
bottom: "fc6"
|
||||
top: "fc6"
|
||||
}
|
||||
layers {
|
||||
name: "fc7"
|
||||
type: INNER_PRODUCT
|
||||
inner_product_param {
|
||||
num_output: 4096
|
||||
}
|
||||
bottom: "fc6"
|
||||
top: "fc7"
|
||||
}
|
||||
layers {
|
||||
name: "relu7"
|
||||
type: RELU
|
||||
bottom: "fc7"
|
||||
top: "fc7"
|
||||
}
|
||||
layers {
|
||||
name: "drop7"
|
||||
type: DROPOUT
|
||||
dropout_param {
|
||||
dropout_ratio: 0.5
|
||||
}
|
||||
bottom: "fc7"
|
||||
top: "fc7"
|
||||
}
|
||||
layers {
|
||||
name: "fc8"
|
||||
type: INNER_PRODUCT
|
||||
inner_product_param {
|
||||
num_output: 1000
|
||||
}
|
||||
bottom: "fc7"
|
||||
top: "fc8"
|
||||
}
|
||||
layers {
|
||||
name: "accuracy"
|
||||
type: ACCURACY
|
||||
bottom: "fc8"
|
||||
bottom: "label"
|
||||
top: "accuracy"
|
||||
}
|
||||
layers {
|
||||
name: "loss"
|
||||
type: SOFTMAX_LOSS
|
||||
bottom: "fc8"
|
||||
bottom: "label"
|
||||
top: "loss"
|
||||
}
|
||||
|
|
@ -1,5 +1,4 @@
|
|||
train_net: "imagenet_train.prototxt"
|
||||
test_net: "imagenet_val.prototxt"
|
||||
net: "imagenet_train_val.prototxt"
|
||||
test_iter: 1000
|
||||
test_interval: 1000
|
||||
base_lr: 0.01
|
||||
|
|
|
|||
|
|
@ -11,6 +11,21 @@ layers {
|
|||
crop_size: 227
|
||||
mirror: true
|
||||
}
|
||||
include: { phase: TRAIN }
|
||||
}
|
||||
layers {
|
||||
name: "data"
|
||||
type: DATA
|
||||
top: "data"
|
||||
top: "label"
|
||||
data_param {
|
||||
source: "ilsvrc12_val_leveldb"
|
||||
mean_file: "../../data/ilsvrc12/imagenet_mean.binaryproto"
|
||||
batch_size: 50
|
||||
crop_size: 227
|
||||
mirror: false
|
||||
}
|
||||
include: { phase: TEST }
|
||||
}
|
||||
layers {
|
||||
name: "conv1"
|
||||
|
|
@ -308,6 +323,14 @@ layers {
|
|||
}
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "accuracy"
|
||||
type: ACCURACY
|
||||
bottom: "fc8"
|
||||
bottom: "label"
|
||||
top: "accuracy"
|
||||
include: { phase: TEST }
|
||||
}
|
||||
layers {
|
||||
name: "loss"
|
||||
type: SOFTMAX_LOSS
|
||||
|
|
@ -1,228 +0,0 @@
|
|||
name: "CaffeNet"
|
||||
layers {
|
||||
name: "data"
|
||||
type: DATA
|
||||
top: "data"
|
||||
top: "label"
|
||||
data_param {
|
||||
source: "ilsvrc12_val_leveldb"
|
||||
mean_file: "../../data/ilsvrc12/imagenet_mean.binaryproto"
|
||||
batch_size: 50
|
||||
crop_size: 227
|
||||
mirror: false
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "conv1"
|
||||
type: CONVOLUTION
|
||||
bottom: "data"
|
||||
top: "conv1"
|
||||
convolution_param {
|
||||
num_output: 96
|
||||
kernel_size: 11
|
||||
stride: 4
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "relu1"
|
||||
type: RELU
|
||||
bottom: "conv1"
|
||||
top: "conv1"
|
||||
}
|
||||
layers {
|
||||
name: "pool1"
|
||||
type: POOLING
|
||||
bottom: "conv1"
|
||||
top: "pool1"
|
||||
pooling_param {
|
||||
pool: MAX
|
||||
kernel_size: 3
|
||||
stride: 2
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "norm1"
|
||||
type: LRN
|
||||
bottom: "pool1"
|
||||
top: "norm1"
|
||||
lrn_param {
|
||||
local_size: 5
|
||||
alpha: 0.0001
|
||||
beta: 0.75
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "conv2"
|
||||
type: CONVOLUTION
|
||||
bottom: "norm1"
|
||||
top: "conv2"
|
||||
convolution_param {
|
||||
num_output: 256
|
||||
pad: 2
|
||||
kernel_size: 5
|
||||
group: 2
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "relu2"
|
||||
type: RELU
|
||||
bottom: "conv2"
|
||||
top: "conv2"
|
||||
}
|
||||
layers {
|
||||
name: "pool2"
|
||||
type: POOLING
|
||||
bottom: "conv2"
|
||||
top: "pool2"
|
||||
pooling_param {
|
||||
pool: MAX
|
||||
kernel_size: 3
|
||||
stride: 2
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "norm2"
|
||||
type: LRN
|
||||
bottom: "pool2"
|
||||
top: "norm2"
|
||||
lrn_param {
|
||||
local_size: 5
|
||||
alpha: 0.0001
|
||||
beta: 0.75
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "conv3"
|
||||
type: CONVOLUTION
|
||||
bottom: "norm2"
|
||||
top: "conv3"
|
||||
convolution_param {
|
||||
num_output: 384
|
||||
pad: 1
|
||||
kernel_size: 3
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "relu3"
|
||||
type: RELU
|
||||
bottom: "conv3"
|
||||
top: "conv3"
|
||||
}
|
||||
layers {
|
||||
name: "conv4"
|
||||
type: CONVOLUTION
|
||||
bottom: "conv3"
|
||||
top: "conv4"
|
||||
convolution_param {
|
||||
num_output: 384
|
||||
pad: 1
|
||||
kernel_size: 3
|
||||
group: 2
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "relu4"
|
||||
type: RELU
|
||||
bottom: "conv4"
|
||||
top: "conv4"
|
||||
}
|
||||
layers {
|
||||
name: "conv5"
|
||||
type: CONVOLUTION
|
||||
bottom: "conv4"
|
||||
top: "conv5"
|
||||
convolution_param {
|
||||
num_output: 256
|
||||
pad: 1
|
||||
kernel_size: 3
|
||||
group: 2
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "relu5"
|
||||
type: RELU
|
||||
bottom: "conv5"
|
||||
top: "conv5"
|
||||
}
|
||||
layers {
|
||||
name: "pool5"
|
||||
type: POOLING
|
||||
bottom: "conv5"
|
||||
top: "pool5"
|
||||
pooling_param {
|
||||
pool: MAX
|
||||
kernel_size: 3
|
||||
stride: 2
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "fc6"
|
||||
type: INNER_PRODUCT
|
||||
bottom: "pool5"
|
||||
top: "fc6"
|
||||
inner_product_param {
|
||||
num_output: 4096
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "relu6"
|
||||
type: RELU
|
||||
bottom: "fc6"
|
||||
top: "fc6"
|
||||
}
|
||||
layers {
|
||||
name: "drop6"
|
||||
type: DROPOUT
|
||||
bottom: "fc6"
|
||||
top: "fc6"
|
||||
dropout_param {
|
||||
dropout_ratio: 0.5
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "fc7"
|
||||
type: INNER_PRODUCT
|
||||
bottom: "fc6"
|
||||
top: "fc7"
|
||||
inner_product_param {
|
||||
num_output: 4096
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "relu7"
|
||||
type: RELU
|
||||
bottom: "fc7"
|
||||
top: "fc7"
|
||||
}
|
||||
layers {
|
||||
name: "drop7"
|
||||
type: DROPOUT
|
||||
bottom: "fc7"
|
||||
top: "fc7"
|
||||
dropout_param {
|
||||
dropout_ratio: 0.5
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "fc8"
|
||||
type: INNER_PRODUCT
|
||||
bottom: "fc7"
|
||||
top: "fc8"
|
||||
inner_product_param {
|
||||
num_output: 1000
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "accuracy"
|
||||
type: ACCURACY
|
||||
bottom: "fc8"
|
||||
bottom: "label"
|
||||
top: "accuracy"
|
||||
}
|
||||
layers {
|
||||
name: "loss"
|
||||
type: SOFTMAX_LOSS
|
||||
bottom: "fc8"
|
||||
bottom: "label"
|
||||
top: "loss"
|
||||
}
|
||||
|
|
@ -72,12 +72,11 @@ We will also lay out a protocol buffer for running the solver. Let's make a few
|
|||
* The network will be trained with momentum 0.9 and a weight decay of 0.0005.
|
||||
* For every 10,000 iterations, we will take a snapshot of the current status.
|
||||
|
||||
Sound good? This is implemented in `examples/imagenet/imagenet_solver.prototxt`. Again, you will need to change the first two lines:
|
||||
Sound good? This is implemented in `examples/imagenet/imagenet_solver.prototxt`. Again, you will need to change the first line:
|
||||
|
||||
train_net: "imagenet_train.prototxt"
|
||||
test_net: "imagenet_val.prototxt"
|
||||
net: "imagenet_train_val.prototxt"
|
||||
|
||||
to point to the actual path if you have changed them.
|
||||
to point to the actual path if you have changed it.
|
||||
|
||||
Training ImageNet
|
||||
-----------------
|
||||
|
|
|
|||
|
|
@ -30,8 +30,19 @@ random_seed: 1701
|
|||
# solver mode: CPU or GPU
|
||||
solver_mode: GPU
|
||||
|
||||
# The training protocol buffer definition
|
||||
train_net_param {
|
||||
# We test on both the test and train set using "stages". The TEST DATA layers
|
||||
# each have a stage, either 'test-on-train-set' or 'test-on-test-set'.
|
||||
# test_iter specifies how many forward passes the test should carry out.
|
||||
# In the case of MNIST, we have test batch size 100 and 100 test iterations,
|
||||
# covering the full 10,000 testing images.
|
||||
test_iter: 100
|
||||
test_state: { stage: "test-on-test-set" }
|
||||
# The train set has 60K images, so we run 600 test iters (600 * 100 = 60K).
|
||||
test_iter: 600
|
||||
test_state: { stage: "test-on-train-set" }
|
||||
|
||||
# The net protocol buffer definition
|
||||
net_param {
|
||||
name: "LeNet"
|
||||
layers {
|
||||
name: "mnist"
|
||||
|
|
@ -43,122 +54,8 @@ train_net_param {
|
|||
scale: 0.00390625
|
||||
batch_size: 64
|
||||
}
|
||||
include: { phase: TRAIN }
|
||||
}
|
||||
layers {
|
||||
name: "conv1"
|
||||
type: CONVOLUTION
|
||||
bottom: "data"
|
||||
top: "conv1"
|
||||
blobs_lr: 1
|
||||
blobs_lr: 2
|
||||
convolution_param {
|
||||
num_output: 20
|
||||
kernel_size: 5
|
||||
stride: 1
|
||||
weight_filler {
|
||||
type: "xavier"
|
||||
}
|
||||
bias_filler {
|
||||
type: "constant"
|
||||
}
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "pool1"
|
||||
type: POOLING
|
||||
bottom: "conv1"
|
||||
top: "pool1"
|
||||
pooling_param {
|
||||
pool: MAX
|
||||
kernel_size: 2
|
||||
stride: 2
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "conv2"
|
||||
type: CONVOLUTION
|
||||
bottom: "pool1"
|
||||
top: "conv2"
|
||||
blobs_lr: 1
|
||||
blobs_lr: 2
|
||||
convolution_param {
|
||||
num_output: 50
|
||||
kernel_size: 5
|
||||
stride: 1
|
||||
weight_filler {
|
||||
type: "xavier"
|
||||
}
|
||||
bias_filler {
|
||||
type: "constant"
|
||||
}
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "pool2"
|
||||
type: POOLING
|
||||
bottom: "conv2"
|
||||
top: "pool2"
|
||||
pooling_param {
|
||||
pool: MAX
|
||||
kernel_size: 2
|
||||
stride: 2
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "ip1"
|
||||
type: INNER_PRODUCT
|
||||
bottom: "pool2"
|
||||
top: "ip1"
|
||||
blobs_lr: 1
|
||||
blobs_lr: 2
|
||||
inner_product_param {
|
||||
num_output: 500
|
||||
weight_filler {
|
||||
type: "xavier"
|
||||
}
|
||||
bias_filler {
|
||||
type: "constant"
|
||||
}
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "relu1"
|
||||
type: RELU
|
||||
bottom: "ip1"
|
||||
top: "ip1"
|
||||
}
|
||||
layers {
|
||||
name: "ip2"
|
||||
type: INNER_PRODUCT
|
||||
bottom: "ip1"
|
||||
top: "ip2"
|
||||
blobs_lr: 1
|
||||
blobs_lr: 2
|
||||
inner_product_param {
|
||||
num_output: 10
|
||||
weight_filler {
|
||||
type: "xavier"
|
||||
}
|
||||
bias_filler {
|
||||
type: "constant"
|
||||
}
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "loss"
|
||||
type: SOFTMAX_LOSS
|
||||
bottom: "ip2"
|
||||
bottom: "label"
|
||||
}
|
||||
}
|
||||
|
||||
# test_iter specifies how many forward passes the test should carry out.
|
||||
# In the case of MNIST, we have test batch size 100 and 100 test iterations,
|
||||
# covering the full 10,000 testing images.
|
||||
test_iter: 100
|
||||
# The testing protocol buffer definition
|
||||
test_net_param {
|
||||
name: "LeNet-test"
|
||||
layers {
|
||||
name: "mnist"
|
||||
type: DATA
|
||||
|
|
@ -169,120 +66,11 @@ test_net_param {
|
|||
scale: 0.00390625
|
||||
batch_size: 100
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "conv1"
|
||||
type: CONVOLUTION
|
||||
bottom: "data"
|
||||
top: "conv1"
|
||||
convolution_param {
|
||||
num_output: 20
|
||||
kernel_size: 5
|
||||
stride: 1
|
||||
weight_filler {
|
||||
type: "xavier"
|
||||
}
|
||||
bias_filler {
|
||||
type: "constant"
|
||||
}
|
||||
include: {
|
||||
phase: TEST
|
||||
stage: "test-on-test-set"
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "pool1"
|
||||
type: POOLING
|
||||
bottom: "conv1"
|
||||
top: "pool1"
|
||||
pooling_param {
|
||||
pool: MAX
|
||||
kernel_size: 2
|
||||
stride: 2
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "conv2"
|
||||
type: CONVOLUTION
|
||||
bottom: "pool1"
|
||||
top: "conv2"
|
||||
convolution_param {
|
||||
num_output: 50
|
||||
kernel_size: 5
|
||||
stride: 1
|
||||
weight_filler {
|
||||
type: "xavier"
|
||||
}
|
||||
bias_filler {
|
||||
type: "constant"
|
||||
}
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "pool2"
|
||||
type: POOLING
|
||||
bottom: "conv2"
|
||||
top: "pool2"
|
||||
pooling_param {
|
||||
pool: MAX
|
||||
kernel_size: 2
|
||||
stride: 2
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "ip1"
|
||||
type: INNER_PRODUCT
|
||||
bottom: "pool2"
|
||||
top: "ip1"
|
||||
inner_product_param {
|
||||
num_output: 500
|
||||
weight_filler {
|
||||
type: "xavier"
|
||||
}
|
||||
bias_filler {
|
||||
type: "constant"
|
||||
}
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "relu1"
|
||||
type: RELU
|
||||
bottom: "ip1"
|
||||
top: "ip1"
|
||||
}
|
||||
layers {
|
||||
name: "ip2"
|
||||
type: INNER_PRODUCT
|
||||
bottom: "ip1"
|
||||
top: "ip2"
|
||||
inner_product_param {
|
||||
num_output: 10
|
||||
weight_filler {
|
||||
type: "xavier"
|
||||
}
|
||||
bias_filler {
|
||||
type: "constant"
|
||||
}
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "accuracy"
|
||||
type: ACCURACY
|
||||
bottom: "ip2"
|
||||
bottom: "label"
|
||||
top: "accuracy"
|
||||
}
|
||||
layers {
|
||||
name: "loss"
|
||||
type: SOFTMAX_LOSS
|
||||
bottom: "ip2"
|
||||
bottom: "label"
|
||||
top: "loss"
|
||||
}
|
||||
}
|
||||
|
||||
# The train set has 60K images, so we run 600 test iters (600 * 100 = 60K).
|
||||
test_iter: 600
|
||||
# The protocol buffer definition to test on the train set
|
||||
test_net_param {
|
||||
name: "LeNet-test-on-train"
|
||||
layers {
|
||||
name: "mnist"
|
||||
type: DATA
|
||||
|
|
@ -293,12 +81,18 @@ test_net_param {
|
|||
scale: 0.00390625
|
||||
batch_size: 100
|
||||
}
|
||||
include: {
|
||||
phase: TEST
|
||||
stage: "test-on-train-set"
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "conv1"
|
||||
type: CONVOLUTION
|
||||
bottom: "data"
|
||||
top: "conv1"
|
||||
blobs_lr: 1
|
||||
blobs_lr: 2
|
||||
convolution_param {
|
||||
num_output: 20
|
||||
kernel_size: 5
|
||||
|
|
@ -327,6 +121,8 @@ test_net_param {
|
|||
type: CONVOLUTION
|
||||
bottom: "pool1"
|
||||
top: "conv2"
|
||||
blobs_lr: 1
|
||||
blobs_lr: 2
|
||||
convolution_param {
|
||||
num_output: 50
|
||||
kernel_size: 5
|
||||
|
|
@ -355,6 +151,8 @@ test_net_param {
|
|||
type: INNER_PRODUCT
|
||||
bottom: "pool2"
|
||||
top: "ip1"
|
||||
blobs_lr: 1
|
||||
blobs_lr: 2
|
||||
inner_product_param {
|
||||
num_output: 500
|
||||
weight_filler {
|
||||
|
|
@ -376,6 +174,8 @@ test_net_param {
|
|||
type: INNER_PRODUCT
|
||||
bottom: "ip1"
|
||||
top: "ip2"
|
||||
blobs_lr: 1
|
||||
blobs_lr: 2
|
||||
inner_product_param {
|
||||
num_output: 10
|
||||
weight_filler {
|
||||
|
|
@ -392,6 +192,7 @@ test_net_param {
|
|||
bottom: "ip2"
|
||||
bottom: "label"
|
||||
top: "accuracy"
|
||||
include: { phase: TEST }
|
||||
}
|
||||
layers {
|
||||
name: "loss"
|
||||
|
|
|
|||
|
|
@ -1,7 +1,5 @@
|
|||
# The training protocol buffer definition
|
||||
train_net: "lenet_train.prototxt"
|
||||
# The testing protocol buffer definition
|
||||
test_net: "lenet_test.prototxt"
|
||||
# The train/test net protocol buffer definition
|
||||
net: "lenet_train_test.prototxt"
|
||||
# test_iter specifies how many forward passes the test should carry out.
|
||||
# In the case of MNIST, we have test batch size 100 and 100 test iterations,
|
||||
# covering the full 10,000 testing images.
|
||||
|
|
|
|||
|
|
@ -1,118 +0,0 @@
|
|||
name: "LeNet-test"
|
||||
layers {
|
||||
name: "mnist"
|
||||
type: DATA
|
||||
top: "data"
|
||||
top: "label"
|
||||
data_param {
|
||||
source: "mnist-test-leveldb"
|
||||
scale: 0.00390625
|
||||
batch_size: 100
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "conv1"
|
||||
type: CONVOLUTION
|
||||
bottom: "data"
|
||||
top: "conv1"
|
||||
convolution_param {
|
||||
num_output: 20
|
||||
kernel_size: 5
|
||||
stride: 1
|
||||
weight_filler {
|
||||
type: "xavier"
|
||||
}
|
||||
bias_filler {
|
||||
type: "constant"
|
||||
}
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "pool1"
|
||||
type: POOLING
|
||||
bottom: "conv1"
|
||||
top: "pool1"
|
||||
pooling_param {
|
||||
pool: MAX
|
||||
kernel_size: 2
|
||||
stride: 2
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "conv2"
|
||||
type: CONVOLUTION
|
||||
bottom: "pool1"
|
||||
top: "conv2"
|
||||
convolution_param {
|
||||
num_output: 50
|
||||
kernel_size: 5
|
||||
stride: 1
|
||||
weight_filler {
|
||||
type: "xavier"
|
||||
}
|
||||
bias_filler {
|
||||
type: "constant"
|
||||
}
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "pool2"
|
||||
type: POOLING
|
||||
bottom: "conv2"
|
||||
top: "pool2"
|
||||
pooling_param {
|
||||
pool: MAX
|
||||
kernel_size: 2
|
||||
stride: 2
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "ip1"
|
||||
type: INNER_PRODUCT
|
||||
bottom: "pool2"
|
||||
top: "ip1"
|
||||
inner_product_param {
|
||||
num_output: 500
|
||||
weight_filler {
|
||||
type: "xavier"
|
||||
}
|
||||
bias_filler {
|
||||
type: "constant"
|
||||
}
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "relu1"
|
||||
type: RELU
|
||||
bottom: "ip1"
|
||||
top: "ip1"
|
||||
}
|
||||
layers {
|
||||
name: "ip2"
|
||||
type: INNER_PRODUCT
|
||||
bottom: "ip1"
|
||||
top: "ip2"
|
||||
inner_product_param {
|
||||
num_output: 10
|
||||
weight_filler {
|
||||
type: "xavier"
|
||||
}
|
||||
bias_filler {
|
||||
type: "constant"
|
||||
}
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "accuracy"
|
||||
type: ACCURACY
|
||||
bottom: "ip2"
|
||||
bottom: "label"
|
||||
top: "accuracy"
|
||||
}
|
||||
layers {
|
||||
name: "loss"
|
||||
type: SOFTMAX_LOSS
|
||||
bottom: "ip2"
|
||||
bottom: "label"
|
||||
top: "loss"
|
||||
}
|
||||
|
|
@ -9,7 +9,21 @@ layers {
|
|||
scale: 0.00390625
|
||||
batch_size: 64
|
||||
}
|
||||
include: { phase: TRAIN }
|
||||
}
|
||||
layers {
|
||||
name: "mnist"
|
||||
type: DATA
|
||||
top: "data"
|
||||
top: "label"
|
||||
data_param {
|
||||
source: "mnist-test-leveldb"
|
||||
scale: 0.00390625
|
||||
batch_size: 100
|
||||
}
|
||||
include: { phase: TEST }
|
||||
}
|
||||
|
||||
layers {
|
||||
name: "conv1"
|
||||
type: CONVOLUTION
|
||||
|
|
@ -110,9 +124,18 @@ layers {
|
|||
}
|
||||
}
|
||||
}
|
||||
layers {
|
||||
name: "accuracy"
|
||||
type: ACCURACY
|
||||
bottom: "ip2"
|
||||
bottom: "label"
|
||||
top: "accuracy"
|
||||
include: { phase: TEST }
|
||||
}
|
||||
layers {
|
||||
name: "loss"
|
||||
type: SOFTMAX_LOSS
|
||||
bottom: "ip2"
|
||||
bottom: "label"
|
||||
top: "loss"
|
||||
}
|
||||
|
|
@ -8,6 +8,18 @@ layers {
|
|||
scale: 0.0039215684
|
||||
batch_size: 100
|
||||
}
|
||||
include: { phase: TRAIN }
|
||||
}
|
||||
layers {
|
||||
top: "data"
|
||||
name: "data"
|
||||
type: DATA
|
||||
data_param {
|
||||
source: "mnist-test-leveldb"
|
||||
scale: 0.0039215684
|
||||
batch_size: 100
|
||||
}
|
||||
include: { phase: TEST }
|
||||
}
|
||||
layers {
|
||||
bottom: "data"
|
||||
|
|
@ -232,4 +244,20 @@ layers {
|
|||
bottom: "flatdata"
|
||||
name: "loss"
|
||||
type: SIGMOID_CROSS_ENTROPY_LOSS
|
||||
include: { phase: TRAIN }
|
||||
}
|
||||
layers {
|
||||
bottom: "decode1"
|
||||
top: "decode1neuron"
|
||||
name: "decode1neuron"
|
||||
type: SIGMOID
|
||||
include: { phase: TEST }
|
||||
}
|
||||
layers {
|
||||
bottom: "decode1neuron"
|
||||
bottom: "flatdata"
|
||||
name: "loss"
|
||||
type: EUCLIDEAN_LOSS
|
||||
top: "loss"
|
||||
include: { phase: TEST }
|
||||
}
|
||||
|
|
@ -1,5 +1,4 @@
|
|||
train_net: "mnist_autoencoder_train.prototxt"
|
||||
test_net: "mnist_autoencoder_test.prototxt"
|
||||
net: "mnist_autoencoder.prototxt"
|
||||
test_iter: 50
|
||||
test_interval: 100
|
||||
test_compute_loss: true
|
||||
|
|
|
|||
|
|
@ -1,146 +0,0 @@
|
|||
name: "MNISTAutoencoder"
|
||||
layers {
|
||||
top: "data"
|
||||
name: "data"
|
||||
type: DATA
|
||||
data_param {
|
||||
source: "mnist-test-leveldb"
|
||||
scale: 0.0039215684
|
||||
batch_size: 100
|
||||
}
|
||||
}
|
||||
layers {
|
||||
bottom: "data"
|
||||
top: "flatdata"
|
||||
name: "flatdata"
|
||||
type: FLATTEN
|
||||
}
|
||||
layers {
|
||||
bottom: "data"
|
||||
top: "encode1"
|
||||
name: "encode1"
|
||||
type: INNER_PRODUCT
|
||||
inner_product_param {
|
||||
num_output: 1000
|
||||
}
|
||||
}
|
||||
layers {
|
||||
bottom: "encode1"
|
||||
top: "encode1neuron"
|
||||
name: "encode1neuron"
|
||||
type: SIGMOID
|
||||
}
|
||||
layers {
|
||||
bottom: "encode1neuron"
|
||||
top: "encode2"
|
||||
name: "encode2"
|
||||
type: INNER_PRODUCT
|
||||
inner_product_param {
|
||||
num_output: 500
|
||||
}
|
||||
}
|
||||
layers {
|
||||
bottom: "encode2"
|
||||
top: "encode2neuron"
|
||||
name: "encode2neuron"
|
||||
type: SIGMOID
|
||||
}
|
||||
layers {
|
||||
bottom: "encode2neuron"
|
||||
top: "encode3"
|
||||
name: "encode3"
|
||||
type: INNER_PRODUCT
|
||||
inner_product_param {
|
||||
num_output: 250
|
||||
}
|
||||
}
|
||||
layers {
|
||||
bottom: "encode3"
|
||||
top: "encode3neuron"
|
||||
name: "encode3neuron"
|
||||
type: SIGMOID
|
||||
}
|
||||
layers {
|
||||
bottom: "encode3neuron"
|
||||
top: "encode4"
|
||||
name: "encode4"
|
||||
type: INNER_PRODUCT
|
||||
blobs_lr: 1
|
||||
blobs_lr: 1
|
||||
weight_decay: 1
|
||||
weight_decay: 0
|
||||
inner_product_param {
|
||||
num_output: 30
|
||||
}
|
||||
}
|
||||
layers {
|
||||
bottom: "encode4"
|
||||
top: "decode4"
|
||||
name: "decode4"
|
||||
type: INNER_PRODUCT
|
||||
blobs_lr: 1
|
||||
blobs_lr: 1
|
||||
weight_decay: 1
|
||||
weight_decay: 0
|
||||
inner_product_param {
|
||||
num_output: 250
|
||||
}
|
||||
}
|
||||
layers {
|
||||
bottom: "decode4"
|
||||
top: "decode4neuron"
|
||||
name: "decode4neuron"
|
||||
type: SIGMOID
|
||||
}
|
||||
layers {
|
||||
bottom: "decode4neuron"
|
||||
top: "decode3"
|
||||
name: "decode3"
|
||||
type: INNER_PRODUCT
|
||||
inner_product_param {
|
||||
num_output: 500
|
||||
}
|
||||
}
|
||||
layers {
|
||||
bottom: "decode3"
|
||||
top: "decode3neuron"
|
||||
name: "decode3neuron"
|
||||
type: SIGMOID
|
||||
}
|
||||
layers {
|
||||
bottom: "decode3neuron"
|
||||
top: "decode2"
|
||||
name: "decode2"
|
||||
type: INNER_PRODUCT
|
||||
inner_product_param {
|
||||
num_output: 1000
|
||||
}
|
||||
}
|
||||
layers {
|
||||
bottom: "decode2"
|
||||
top: "decode2neuron"
|
||||
name: "decode2neuron"
|
||||
type: SIGMOID
|
||||
}
|
||||
layers {
|
||||
bottom: "decode2neuron"
|
||||
top: "decode1"
|
||||
name: "decode1"
|
||||
type: INNER_PRODUCT
|
||||
inner_product_param {
|
||||
num_output: 784
|
||||
}
|
||||
}
|
||||
layers {
|
||||
bottom: "decode1"
|
||||
top: "decode1neuron"
|
||||
name: "decode1neuron"
|
||||
type: SIGMOID
|
||||
}
|
||||
layers {
|
||||
bottom: "decode1neuron"
|
||||
bottom: "flatdata"
|
||||
name: "loss"
|
||||
type: EUCLIDEAN_LOSS
|
||||
top: "loss"
|
||||
}
|
||||
|
|
@ -177,10 +177,8 @@ The `softmax_loss` layer implements both the softmax and the multinomial logisti
|
|||
|
||||
Check out the comments explaining each line in the prototxt:
|
||||
|
||||
# The training protocol buffer definition
|
||||
train_net: "lenet_train.prototxt"
|
||||
# The testing protocol buffer definition
|
||||
test_net: "lenet_test.prototxt"
|
||||
# The train/test net protocol buffer definition
|
||||
net: "lenet_train_test.prototxt"
|
||||
# test_iter specifies how many forward passes the test should carry out.
|
||||
# In the case of MNIST, we have test batch size 100 and 100 test iterations,
|
||||
# covering the full 10,000 testing images.
|
||||
|
|
|
|||
Загрузка…
Ссылка в новой задаче