Skip to content

Instantly share code, notes, and snippets.

@sunsided

sunsided/readme.md

Forked from ishay2b/readme.md
Created September 11, 2016 21:36
Show Gist options
  • Save sunsided/264990e45ae1cae32015b533f9c7787e to your computer and use it in GitHub Desktop.
Save sunsided/264990e45ae1cae32015b533f9c7787e to your computer and use it in GitHub Desktop.
Download ZIP
Vanilla CNN caffe model
Raw
readme.md
name caffemodel caffemodel_url license sha1 caffe_commit
Vanilla CNN Model
vanillaCNN.caffemodel
unrestricted
b5e34ce75d078025e07452cb47e65d198fe27912
9c9f94e18a8909580a6b94c44dbb1e46f0ee8eb8

Implementation of the Vanilla CNN described in the paper: Yue Wu and Tal Hassner, "Facial Landmark Detection with Tweaked Convolutional Neural Networks", arXiv preprint arXiv:1511.04031, 12 Nov. 2015. See project page for more information about this project. http://www.openu.ac.il/home/hassner/projects/tcnn_landmarks/

Written by Ishay Tubi: https://www.linkedin.com/in/ishay2b

This software is provided as is, without any warranty, with no legal constraints.

See github repository: http://bit.ly/1SbTqTf

The bundled model is the iteration 1,000,000 snapshot using vanilla_adam_solver.prototxt

Model was traind using AFLW train data, and obtains a 7.6% mean error for AFW benchmark and 8.3% for AFLW benchmark.

License

This model is released for unrestricted use.

Raw
vanilla_adam_solver.prototxt
# The train/test net protocol buffer definition
# this follows "ADAM: A METHOD FOR STOCHASTIC OPTIMIZATION"
net: "vanilla_train.prototxt"
type: "Adam"
test_iter: 1000
test_interval: 5000
base_lr: 0.00001
momentum: 0.9
momentum2: 0.999
# since Adam dynamically changes the learning rate, we set the base learning
# rate to a fixed value
lr_policy: "fixed"
# Display every 1000 iterations
display: 2500
# The maximum number of iterations
max_iter: 1400000
# snapshot intermediate results
snapshot: 5000
snapshot_prefix: "../caffeData/snapshots/snap"
# solver mode: CPU or GPU
solver_mode: CPU
Raw
vanilla_deploy.prototxt
name: "vanila"
input: "data"
input_dim: 1
input_dim: 3
input_dim: 40
input_dim: 40
########################################
# the actual net
# layer 1
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: 16
pad: 2
kernel_size: 5
stride: 1
weight_filler {
type: "xavier"
std: 0.1
}
bias_filler {
type: "constant"
value: 0.2
}
}
}
layer {
name: "ActivationTangH1"
bottom: "Conv1"
top: "ActivationTangH1"
type: "TanH"
}
layer {
name: "ActivationAbs1"
bottom: "ActivationTangH1"
top: "Abs1"
type: "AbsVal"
}
layer {
name: "Pool1"
type: "Pooling"
bottom: "Abs1"
top: "Pool1"
pooling_param {
pool: MAX
kernel_size: 2
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: 48
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
std: 0.1
}
bias_filler {
type: "constant"
value: 0.2
}
}
}
layer {
name: "ActivationTangH2"
bottom: "Conv2"
top: "ActivationTangH2"
type: "TanH"
}
layer {
name: "ActivationAbs2"
bottom: "ActivationTangH2"
top: "Abs2"
type: "AbsVal"
}
layer {
name: "Pool2"
type: "Pooling"
bottom: "Abs2"
top: "Pool2"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
# layer 3
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: 64
pad: 0
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
std: 0.1
}
bias_filler {
type: "constant"
value: 0.2
}
}
}
layer {
name: "ActivationTangH3"
bottom: "Conv3"
top: "ActivationTangH3"
type: "TanH"
}
layer {
name: "ActivationAbs3"
bottom: "ActivationTangH3"
top: "Abs3"
type: "AbsVal"
}
layer {
name: "Pool3"
type: "Pooling"
bottom: "Abs3"
top: "Pool3"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
# layer 4
layer {
name: "Conv4"
type: "Convolution"
bottom: "Pool3"
top: "Conv4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 64
pad: 0
kernel_size: 2
stride: 1
weight_filler {
type: "xavier"
std: 0.1
}
bias_filler {
type: "constant"
value: 0.2
}
}
}
layer {
name: "ActivationTangH4"
bottom: "Conv4"
top: "ActivationTangH4"
type: "TanH"
}
layer {
name: "ActivationAbs4"
bottom: "ActivationTangH4"
top: "Abs4"
type: "AbsVal"
}
########################################
layer {
name: "Dense1"
type: "InnerProduct"
bottom: "Abs4"
top: "Dense1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 100
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "ActivationTangH5"
bottom: "Dense1"
top: "ActivationTangH5"
type: "TanH"
}
layer {
name: "ActivationAbs5"
bottom: "ActivationTangH5"
top: "Abs5"
type: "AbsVal"
}
layer {
name: "Dense2"
type: "InnerProduct"
bottom: "Abs5"
top: "Dense2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 10
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
Raw
vanilla_train.prototxt
name: "vanila"
layer {
type: "HDF5Data"
top: "X" # same name as given in create_dataset!
top: "landmarks"
hdf5_data_param {
source: "/Users/ishay/Dev/VanilaCNN/caffeData/train.txt" # do not give the h5 files directly, but the list.
batch_size: 30
}
include { phase:TRAIN }
}
layer {
type: "HDF5Data"
top: "X" # same name as given in create_dataset!
top: "landmarks"
hdf5_data_param {
source: "/Users/ishay/Dev/VanilaCNN/caffeData/test.txt" # do not give the h5 files directly, but the list.
batch_size: 10
}
include { phase:TEST }
}
layer {
name: "Conv1"
type: "Convolution"
bottom: "X"
top: "Conv1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 16
pad: 2
kernel_size: 5
stride: 1
weight_filler {
type: "xavier"
std: 0.1
}
bias_filler {
type: "constant"
value: 0.2
}
}
}
layer {
name: "ActivationTangH1"
bottom: "Conv1"
top: "ActivationTangH1"
type: "TanH"
}
layer {
name: "ActivationAbs1"
bottom: "ActivationTangH1"
top: "Abs1"
type: "AbsVal"
}
layer {
name: "Pool1"
type: "Pooling"
bottom: "Abs1"
top: "Pool1"
pooling_param {
pool: MAX
kernel_size: 2
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: 48
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
std: 0.1
}
bias_filler {
type: "constant"
value: 0.2
}
}
}
layer {
name: "ActivationTangH2"
bottom: "Conv2"
top: "ActivationTangH2"
type: "TanH"
}
layer {
name: "ActivationAbs2"
bottom: "ActivationTangH2"
top: "Abs2"
type: "AbsVal"
}
layer {
name: "Pool2"
type: "Pooling"
bottom: "Abs2"
top: "Pool2"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
# layer 3
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: 64
pad: 0
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
std: 0.1
}
bias_filler {
type: "constant"
value: 0.2
}
}
}
layer {
name: "ActivationTangH3"
bottom: "Conv3"
top: "ActivationTangH3"
type: "TanH"
}
layer {
name: "ActivationAbs3"
bottom: "ActivationTangH3"
top: "Abs3"
type: "AbsVal"
}
layer {
name: "Pool3"
type: "Pooling"
bottom: "Abs3"
top: "Pool3"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
# layer 4
layer {
name: "Conv4"
type: "Convolution"
bottom: "Pool3"
top: "Conv4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 64
pad: 0
kernel_size: 2
stride: 1
weight_filler {
type: "xavier"
std: 0.1
}
bias_filler {
type: "constant"
value: 0.2
}
}
}
layer {
name: "ActivationTangH4"
bottom: "Conv4"
top: "ActivationTangH4"
type: "TanH"
}
layer {
name: "ActivationAbs4"
bottom: "ActivationTangH4"
top: "Abs4"
type: "AbsVal"
}
########################################
layer {
name: "Dense1"
type: "InnerProduct"
bottom: "Abs4"
top: "Dense1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 100
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "ActivationTangH5"
bottom: "Dense1"
top: "ActivationTangH5"
type: "TanH"
}
layer {
name: "ActivationAbs5"
bottom: "ActivationTangH5"
top: "Abs5"
type: "AbsVal"
}
layer {
name: "Dense2"
type: "InnerProduct"
bottom: "Abs5"
top: "Dense2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 10
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
type: 'Python'
name: 'loss'
top: 'loss'
bottom: 'Dense2'
bottom: 'landmarks'
python_param {
# the module name -- usually the filename -- that needs to be in $PYTHONPATH
module: 'python.NormlizedMSE'
# the layer name -- the class name in the module
layer: 'NormlizedMSE'
}
# set loss weight so Caffe knows this is a loss layer.
# since PythonLayer inherits directly from Layer, this isn't automatically
# known to Caffe
loss_weight: 1
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment