Implementing Deep Learning architecture with a given dataset - machine-learning

Question

I am quite new in caffe and in deep learning. I am just trying to implement deep learning architecture.
This is the architecture that i am trying to implement . The architecture and Parse27k dataset was created and constructed by Computer Vision Group at the Visual Computing Institute, RWTH Aachen University .
Below you can see my models that i need to improve :
Train_val.prototxt
name: "Parse27"
layer {
name: "data"
type: "HDF5Data"
top: "crops"
top: "labels"
include {
phase: TRAIN
}
hdf5_data_param {
source: "/home/nail/caffe/caffe/examples/hdf5_classification/data/train.txt"
batch_size: 256
}
}
layer {
name: "data"
type: "HDF5Data"
top: "crops"
top: "labels"
include {
phase: TEST
}
hdf5_data_param {
source: "/home/nail/caffe/caffe/examples/hdf5_classification/data/test.txt"
batch_size: 256
}
}
layer {
name: "conv1"
type: "Convolution"
bottom: "crops"
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: 1000
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "accuracy"
type: "Accuracy"
bottom: "fc8"
bottom: "labels"
top: "accuracy"
include {
phase: TEST
}
}
layer {
name: "loss"
type: "SoftmaxWithLoss"
bottom: "fc8"
bottom: "labels"
top: "loss"
}
Solver.prototxt
net: "models/Parse27/train_val.prototxt"
test_iter: 1000
test_interval: 1000
base_lr: 0.01
lr_policy: "step"
gamma: 0.1
stepsize: 100000
display: 20
max_iter: 450000
momentum: 0.9
weight_decay: 0.0005
snapshot: 10000
snapshot_prefix: "models/Parse27/Parse27_train"
solver_mode: GPU
I have 2 main hardships in implementing this architecture.
As seen above, my model does not include custom-loss layer. My model is almost caffeNet architecture. But i should replace my last layer which is inside the red box with custom loss layer (green box).
My train dataset has following structure.
crops Dataset {27482, 3, 128, 192}
labels Dataset {27482, 12}
mean Dataset {3, 128, 192}
pids Dataset {27482}
As seen here number of rows(examples) in crops and in labels are same 27482. However i have 12 columns in my label datasets. And my model works when there is only 1 label. How i can make it to train for all labels?
My model in the Train_val.prototxt is looking like this for now:
Any kind of help or suggestion will be highly appreciated.

Answer 1

If I understand you correctly, you are trying to predict 12 discrete labels (attributes) for each input example. In that case, you should "Slice" the labels:
layer {
type: "Slice"
name: "slice_labels"
bottom: "label"
top: "attr_00"
top: "attr_01"
top: "attr_02"
top: "attr_03"
top: "attr_04"
top: "attr_05"
top: "attr_06"
top: "attr_07"
top: "attr_08"
top: "attr_09"
top: "attr_10"
top: "attr_11"
slice_param {
axis: -1 # slice the last dimension
slice_point: 1
slice_point: 2
slice_point: 3
slice_point: 4
slice_point: 5
slice_point: 6
slice_point: 7
slice_point: 8
slice_point: 9
slice_point: 10
slice_point: 11
}
}
Now, you have a "scalar" label for each attribute. I believe you can take it from here.