ex_model.prototxt

name: "MNISTConvNet"
# train input layer
layer{
name:"mnist_data"
type:"Data"
transform_param {
scale: 0.00390625
}
include:{phase:TRAIN}
top:"data" # output 
top:"label" # output
data_param{
source: "/home/thushv89/gsoc2017/caffe-cpp-example/data/mnist/mnist_train_lmdb"
backend:LMDB
batch_size: 64
}
}

# test input layer
layer{
name:"mnist_data"
type:"Data"
transform_param {
scale: 0.00390625
}
include:{phase:TEST}
top:"data" # output 
top:"label" # output
data_param{
source: "/home/thushv89/gsoc2017/caffe-cpp-example/data/mnist/mnist_test_lmdb"
backend:LMDB
batch_size:100
}

}

layer {
name:"conv1"
type:"Convolution"
param{lr_mult:1}
param{lr_mult:2}
convolution_param{
num_output:20
kernel_size:5
stride:1
weight_filler{type:"xavier"}
bias_filler{type:"constant"}
}
bottom:"data"
top:"conv1"
}

layer {
name: "pool1"
type: "Pooling"
pooling_param {
kernel_size:2
stride: 2
pool:MAX
}
bottom: "conv1"
top: "pool1"
}

layer{
name: "fc1"
type:"InnerProduct"
param {lr_mult:1}
param {lr_mult:2}
inner_product_param {
num_output:500
weight_filler{type:"xavier"}
bias_filler{type:"constant"}
}
bottom:"pool1"
top:"fc1"
}

layer {
name:"relu1"
type:"ReLU"
bottom:"fc1"
top:"fc1"
}

layer {
name:"fc2"
type:"InnerProduct"
param {lr_mult:1}
param {lr_mult:2}
inner_product_param{
num_output:10
weight_filler{type:"xavier"}
bias_filler{type:"constant"}
}
bottom:"fc1"
top:"fc2"
}

layer{
name:"loss"
type:"SoftmaxWithLoss"
bottom:"fc2"
bottom:"label"
}

layer {
name: "accuracy"
type: "Accuracy"
bottom: "fc2"
bottom: "label"
top: "accuracy"
include {
  phase: TEST
}
}