-
-
Save ProGamerGov/2bdf7659ee14dac03269a3ec3a7f1fcd to your computer and use it in GitHub Desktop.
Solver.prototxt and Train_Val.prototxt used alongside my "rough faces" data set to improve style transfer results.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
female 0 | |
male 1 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
net: "/home/ubuntu/caffe/models/vgg16_finetune/vgg16_train_val.prototxt" | |
test_iter: 50 | |
test_interval: 100 | |
# lr for fine-tuning should be lower than when starting from scratch | |
base_lr: 0.00003 | |
lr_policy: "step" | |
#gamma: 0.1 | |
gamma: 0.1 | |
# decrease lr each 20000 iterations | |
#stepsize: 20000 | |
stepsize: 5000 | |
display: 10 | |
max_iter: 600000 | |
momentum: 0.9 | |
weight_decay: 0.000005 | |
snapshot: 1000 | |
snapshot_prefix: "examples/imagenet/VGG16_SOD_finetune_rough_faces" | |
solver_mode: GPU | |
#debug_info: true |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
name: "VGG16_SOD_finetune" | |
layers { | |
top: "data" | |
top: "label" | |
name: "data" | |
type: DATA | |
data_param { | |
source: "/home/ubuntu/caffe/examples/imagenet/faces_train_lmdb" | |
backend: LMDB | |
batch_size: 64 | |
} | |
transform_param { | |
crop_size: 224 | |
#mirror: true | |
mean_file: "/home/ubuntu/caffe/examples/imagenet/faces_train_mean.binaryproto" | |
} | |
include: { phase: TRAIN } | |
} | |
layers { | |
top: "data" | |
top: "label" | |
name: "data" | |
type: DATA | |
data_param { | |
source: "/home/ubuntu/caffe/examples/imagenet/faces_val_lmdb" | |
backend: LMDB | |
batch_size: 8 | |
} | |
transform_param { | |
crop_size: 224 | |
#mirror: false | |
mean_file: "/home/ubuntu/caffe/examples/imagenet/faces_val_mean.binaryproto" | |
} | |
include: { phase: TEST } | |
} | |
layers { | |
bottom: "data" | |
top: "conv1_1" | |
name: "conv1_1" | |
type: CONVOLUTION | |
blobs_lr: 1 | |
blobs_lr: 2 | |
weight_decay: 1 | |
weight_decay: 0 | |
convolution_param { | |
num_output: 64 | |
pad: 1 | |
kernel_size: 3 | |
weight_filler { | |
type: "gaussian" | |
mean: 0 | |
std: 0.01 | |
} | |
bias_filler { | |
type: "constant" | |
value: 0 | |
} | |
} | |
} | |
layers { | |
bottom: "conv1_1" | |
top: "conv1_1" | |
name: "relu1_1" | |
type: RELU | |
} | |
layers { | |
bottom: "conv1_1" | |
top: "conv1_2" | |
name: "conv1_2" | |
type: CONVOLUTION | |
blobs_lr: 1 | |
blobs_lr: 2 | |
weight_decay: 1 | |
weight_decay: 0 | |
convolution_param { | |
num_output: 64 | |
pad: 1 | |
kernel_size: 3 | |
weight_filler { | |
type: "gaussian" | |
mean: 0 | |
std: 0.01 | |
} | |
bias_filler { | |
type: "constant" | |
value: 0 | |
} | |
} | |
} | |
layers { | |
bottom: "conv1_2" | |
top: "conv1_2" | |
name: "relu1_2" | |
type: RELU | |
} | |
layers { | |
bottom: "conv1_2" | |
top: "pool1" | |
name: "pool1" | |
type: POOLING | |
pooling_param { | |
pool: MAX | |
kernel_size: 2 | |
stride: 2 | |
} | |
} | |
layers { | |
bottom: "pool1" | |
top: "conv2_1" | |
name: "conv2_1" | |
type: CONVOLUTION | |
blobs_lr: 1 | |
blobs_lr: 2 | |
weight_decay: 1 | |
weight_decay: 0 | |
convolution_param { | |
num_output: 128 | |
pad: 1 | |
kernel_size: 3 | |
weight_filler { | |
type: "gaussian" | |
mean: 0 | |
std: 0.01 | |
} | |
bias_filler { | |
type: "constant" | |
value: 0 | |
} | |
} | |
} | |
layers { | |
bottom: "conv2_1" | |
top: "conv2_1" | |
name: "relu2_1" | |
type: RELU | |
} | |
layers { | |
bottom: "conv2_1" | |
top: "conv2_2" | |
name: "conv2_2" | |
type: CONVOLUTION | |
convolution_param { | |
num_output: 128 | |
pad: 1 | |
kernel_size: 3 | |
weight_filler { | |
type: "gaussian" | |
mean: 0 | |
std: 0.01 | |
} | |
bias_filler { | |
type: "constant" | |
value: 0 | |
} | |
} | |
} | |
layers { | |
bottom: "conv2_2" | |
top: "conv2_2" | |
name: "relu2_2" | |
type: RELU | |
} | |
layers { | |
bottom: "conv2_2" | |
top: "pool2" | |
name: "pool2" | |
type: POOLING | |
pooling_param { | |
pool: MAX | |
kernel_size: 2 | |
stride: 2 | |
} | |
} | |
layers { | |
bottom: "pool2" | |
top: "conv3_1" | |
name: "conv3_1" | |
type: CONVOLUTION | |
blobs_lr: 1 | |
blobs_lr: 2 | |
weight_decay: 1 | |
weight_decay: 0 | |
convolution_param { | |
num_output: 256 | |
pad: 1 | |
kernel_size: 3 | |
weight_filler { | |
type: "gaussian" | |
mean: 0 | |
std: 0.01 | |
} | |
bias_filler { | |
type: "constant" | |
value: 0 | |
} | |
} | |
} | |
layers { | |
bottom: "conv3_1" | |
top: "conv3_1" | |
name: "relu3_1" | |
type: RELU | |
} | |
layers { | |
bottom: "conv3_1" | |
top: "conv3_2" | |
name: "conv3_2" | |
type: CONVOLUTION | |
blobs_lr: 1 | |
blobs_lr: 2 | |
weight_decay: 1 | |
weight_decay: 0 | |
convolution_param { | |
num_output: 256 | |
pad: 1 | |
kernel_size: 3 | |
weight_filler { | |
type: "gaussian" | |
mean: 0 | |
std: 0.01 | |
} | |
bias_filler { | |
type: "constant" | |
value: 0 | |
} | |
} | |
} | |
layers { | |
bottom: "conv3_2" | |
top: "conv3_2" | |
name: "relu3_2" | |
type: RELU | |
} | |
layers { | |
bottom: "conv3_2" | |
top: "conv3_3" | |
name: "conv3_3" | |
type: CONVOLUTION | |
blobs_lr: 1 | |
blobs_lr: 2 | |
weight_decay: 1 | |
weight_decay: 0 | |
convolution_param { | |
num_output: 256 | |
pad: 1 | |
kernel_size: 3 | |
weight_filler { | |
type: "gaussian" | |
mean: 0 | |
std: 0.01 | |
} | |
bias_filler { | |
type: "constant" | |
value: 0 | |
} | |
} | |
} | |
layers { | |
bottom: "conv3_3" | |
top: "conv3_3" | |
name: "relu3_3" | |
type: RELU | |
} | |
layers { | |
bottom: "conv3_3" | |
top: "pool3" | |
name: "pool3" | |
type: POOLING | |
pooling_param { | |
pool: MAX | |
kernel_size: 2 | |
stride: 2 | |
} | |
} | |
layers { | |
bottom: "pool3" | |
top: "conv4_1" | |
name: "conv4_1" | |
type: CONVOLUTION | |
blobs_lr: 1 | |
blobs_lr: 2 | |
weight_decay: 1 | |
weight_decay: 0 | |
convolution_param { | |
num_output: 512 | |
pad: 1 | |
kernel_size: 3 | |
weight_filler { | |
type: "gaussian" | |
mean: 0 | |
std: 0.01 | |
} | |
bias_filler { | |
type: "constant" | |
value: 0 | |
} | |
} | |
} | |
layers { | |
bottom: "conv4_1" | |
top: "conv4_1" | |
name: "relu4_1" | |
type: RELU | |
} | |
layers { | |
bottom: "conv4_1" | |
top: "conv4_2" | |
name: "conv4_2" | |
type: CONVOLUTION | |
blobs_lr: 1 | |
blobs_lr: 2 | |
weight_decay: 1 | |
weight_decay: 0 | |
convolution_param { | |
num_output: 512 | |
pad: 1 | |
kernel_size: 3 | |
weight_filler { | |
type: "gaussian" | |
mean: 0 | |
std: 0.01 | |
} | |
bias_filler { | |
type: "constant" | |
value: 0 | |
} | |
} | |
} | |
layers { | |
bottom: "conv4_2" | |
top: "conv4_2" | |
name: "relu4_2" | |
type: RELU | |
} | |
layers { | |
bottom: "conv4_2" | |
top: "conv4_3" | |
name: "conv4_3" | |
type: CONVOLUTION | |
blobs_lr: 1 | |
blobs_lr: 2 | |
weight_decay: 1 | |
weight_decay: 0 | |
convolution_param { | |
num_output: 512 | |
pad: 1 | |
kernel_size: 3 | |
weight_filler { | |
type: "gaussian" | |
mean: 0 | |
std: 0.01 | |
} | |
bias_filler { | |
type: "constant" | |
value: 0 | |
} | |
} | |
} | |
layers { | |
bottom: "conv4_3" | |
top: "conv4_3" | |
name: "relu4_3" | |
type: RELU | |
} | |
layers { | |
bottom: "conv4_3" | |
top: "pool4" | |
name: "pool4" | |
type: POOLING | |
pooling_param { | |
pool: MAX | |
kernel_size: 2 | |
stride: 2 | |
} | |
} | |
layers { | |
bottom: "pool4" | |
top: "conv5_1" | |
name: "conv5_1" | |
type: CONVOLUTION | |
blobs_lr: 1 | |
blobs_lr: 2 | |
weight_decay: 1 | |
weight_decay: 0 | |
convolution_param { | |
num_output: 512 | |
pad: 1 | |
kernel_size: 3 | |
weight_filler { | |
type: "gaussian" | |
mean: 0 | |
std: 0.01 | |
} | |
bias_filler { | |
type: "constant" | |
value: 0 | |
} | |
} | |
} | |
layers { | |
bottom: "conv5_1" | |
top: "conv5_1" | |
name: "relu5_1" | |
type: RELU | |
} | |
layers { | |
bottom: "conv5_1" | |
top: "conv5_2" | |
name: "conv5_2" | |
type: CONVOLUTION | |
blobs_lr: 1 | |
blobs_lr: 2 | |
weight_decay: 1 | |
weight_decay: 0 | |
convolution_param { | |
num_output: 512 | |
pad: 1 | |
kernel_size: 3 | |
weight_filler { | |
type: "gaussian" | |
mean: 0 | |
std: 0.01 | |
} | |
bias_filler { | |
type: "constant" | |
value: 0 | |
} | |
} | |
} | |
layers { | |
bottom: "conv5_2" | |
top: "conv5_2" | |
name: "relu5_2" | |
type: RELU | |
} | |
layers { | |
bottom: "conv5_2" | |
top: "conv5_3" | |
name: "conv5_3" | |
type: CONVOLUTION | |
blobs_lr: 1 | |
blobs_lr: 2 | |
weight_decay: 1 | |
weight_decay: 0 | |
convolution_param { | |
num_output: 512 | |
pad: 1 | |
kernel_size: 3 | |
weight_filler { | |
type: "gaussian" | |
mean: 0 | |
std: 0.01 | |
} | |
bias_filler { | |
type: "constant" | |
value: 0 | |
} | |
} | |
} | |
layers { | |
bottom: "conv5_3" | |
top: "conv5_3" | |
name: "relu5_3" | |
type: RELU | |
} | |
layers { | |
bottom: "conv5_3" | |
top: "pool5" | |
name: "pool5" | |
type: POOLING | |
pooling_param { | |
pool: MAX | |
kernel_size: 2 | |
stride: 2 | |
} | |
} | |
layers { | |
name: "fc6" | |
type: INNER_PRODUCT | |
bottom: "pool5" | |
top: "fc6" | |
blobs_lr: 1 | |
blobs_lr: 2 | |
weight_decay: 1 | |
weight_decay: 0 | |
inner_product_param { | |
num_output: 4096 | |
weight_filler { | |
type: "gaussian" | |
std: 0.01 | |
} | |
bias_filler { | |
type: "constant" | |
value: 0.0 | |
} | |
} | |
} | |
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" | |
blobs_lr: 1 | |
blobs_lr: 2 | |
weight_decay: 1 | |
weight_decay: 0 | |
inner_product_param { | |
num_output: 4096 | |
weight_filler { | |
type: "gaussian" | |
std: 0.01 | |
} | |
bias_filler { | |
type: "constant" | |
value: 0.0 | |
} | |
} | |
} | |
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 { | |
bottom: "fc7" | |
top: "fc8_faces" | |
name: "fc8_faces" | |
type: INNER_PRODUCT | |
blobs_lr: 1 | |
blobs_lr: 2 | |
weight_decay: 1 | |
weight_decay: 0 | |
inner_product_param { | |
num_output: 2 | |
weight_filler { | |
type: "gaussian" | |
mean: 0 | |
std: 0.05 | |
} | |
bias_filler { | |
type: "constant" | |
value: 0 | |
} | |
} | |
} | |
#layers { | |
# bottom: "fc8_faces" | |
# top: "prob" | |
# name: "prob" | |
# type: SOFTMAX | |
#} | |
layers { | |
name: "accuracy" | |
type: ACCURACY | |
bottom: "fc8_faces" | |
bottom: "label" | |
top: "accuracy" | |
include: { phase: TEST } | |
} | |
layers { | |
bottom: "fc8_faces" | |
bottom: "label" | |
name: "loss" | |
type: SOFTMAX_LOSS | |
include: { phase: TRAIN } | |
} | |
layers { | |
name: "accuracy/top1" | |
type: ACCURACY | |
bottom: "fc8_faces" | |
bottom: "label" | |
top: "accuracy@1" | |
include: { phase: TEST } | |
accuracy_param { | |
top_k: 1 | |
} | |
} | |
layers { | |
name: "accuracy/top5" | |
type: ACCURACY | |
bottom: "fc8_faces" | |
bottom: "label" | |
top: "accuracy@2" | |
include: { phase: TEST } | |
accuracy_param { | |
top_k: 2 | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment