Skip to content

D
dlib
Commit 7494f51d authored by Davis King's avatar Davis King
Browse files
Options

Added support for all the other dlib layers that make sense.

parent 99b06476
Hide whitespace changes
Inline Side-by-side
Showing with 114 additions and 46 deletions
tools/convert_dlib_nets_to_caffe/main.cpp
View file @ 7494f51d
......@@ -14,7 +14,7 @@ using namespace dlib;
// ----------------------------------------------------------------------------------------
// Only these computational layers have parameters
const std::set<string> comp_tags_with_params = {"fc", "fc_no_bias", "con", "bn_con", "bn_fc", "affine", "prelu"};
const std::set<string> comp_tags_with_params = {"fc", "fc_no_bias", "con", "affine_con", "affine_fc", "affine", "prelu"};
struct layer
{
......@@ -28,6 +28,15 @@ struct layer
long skip_id = -1; // If this isn't -1 then it means this layer draws its inputs from
// the most recent layer with tag_id==skip_id rather than its immediate predecessor.
double attribute (const string& key) const
{
auto i = attributes.find(key);
if (i != attributes.end())
return i->second;
else
throw dlib::error("Layer doesn't have the requested attribute '" + key + "'.");
}
string caffe_layer_name() const
{
if (type == "input")
......@@ -71,10 +80,10 @@ string find_layer_caffe_name (
{
i--;
// if we hit the end of the network before we found what we were looking for
if (i->type == "input")
throw dlib::error("Network definition is bad, a layer wanted to skip back to a non-existing layer.");
if (i->tag_id == tag_id)
return i->caffe_layer_name();
if (i->type == "input")
throw dlib::error("Network definition is bad, a layer wanted to skip back to a non-existing layer.");
}
}
}
......@@ -99,30 +108,30 @@ void convert_dlib_xml_to_cafffe_python_code(
const string& xml_filename
)
{
auto layers = parse_dlib_xml(xml_filename);
const auto layers = parse_dlib_xml(xml_filename);
cout << "import caffe " << endl;
cout << "from caffe import layers as L, params as P" << endl;
cout << "import numpy as np" << endl;
// dlib nets don't commit to a batch size, so just use 32 as the default
cout << "batch_size = 32;" << endl;
// dlib nets don't commit to a batch size, so just use 1 as the default
cout << "batch_size = 1;" << endl;
if (layers.back().detail_name == "input_rgb_image")
{
cout << "input_nr = 150; #WARNING, the source dlib network didn't commit to a specific input size, so we put 150 here as a default." << endl;
cout << "input_nc = 150; #WARNING, the source dlib network didn't commit to a specific input size, so we put 150 here as a default." << endl;
cout << "input_nr = 28; #WARNING, the source dlib network didn't commit to a specific input size, so we put 28 here as a default." << endl;
cout << "input_nc = 28; #WARNING, the source dlib network didn't commit to a specific input size, so we put 28 here as a default." << endl;
cout << "input_k = 3;" << endl;
}
else if (layers.back().detail_name == "input_rgb_image_sized")
{
cout << "input_nr = " << layers.back().attributes["nr"] << ";" << endl;
cout << "input_nc = " << layers.back().attributes["nc"] << ";" << endl;
cout << "input_nr = " << layers.back().attribute("nr") << ";" << endl;
cout << "input_nc = " << layers.back().attribute("nc") << ";" << endl;
cout << "input_k = 3;" << endl;
}
else if (layers.back().detail_name == "input")
{
cout << "input_nr = 150; #WARNING, the source dlib network didn't commit to a specific input size, so we put 150 here as a default." << endl;
cout << "input_nc = 150; #WARNING, the source dlib network didn't commit to a specific input size, so we put 150 here as a default." << endl;
cout << "input_nr = 28; #WARNING, the source dlib network didn't commit to a specific input size, so we put 28 here as a default." << endl;
cout << "input_nc = 28; #WARNING, the source dlib network didn't commit to a specific input size, so we put 28 here as a default." << endl;
cout << "input_k = 1;" << endl;
}
else
......@@ -131,6 +140,8 @@ void convert_dlib_xml_to_cafffe_python_code(
}
cout << "def make_netspec():" << endl;
cout << " # For reference, the only \"documentation\" about caffe layer parameters seems to be this page:\n";
cout << " # https://github.com/BVLC/caffe/blob/master/src/caffe/proto/caffe.proto\n" << endl;
cout << " n = caffe.NetSpec(); " << endl;
cout << " n.data,n.label = L.MemoryData(batch_size=batch_size, channels=input_k, height=input_nr, width=input_nc, ntop=2)" << endl;
// iterate the layers starting with the input layer
......@@ -144,13 +155,13 @@ void convert_dlib_xml_to_cafffe_python_code(
if (i->detail_name == "con")
{
cout << " n." << i->caffe_layer_name() << " = L.Convolution(n." << find_input_layer_caffe_name(i);
cout << ", num_output=" << i->attributes["num_filters"];
cout << ", kernel_w=" << i->attributes["nc"];
cout << ", kernel_h=" << i->attributes["nr"];
cout << ", stride_w=" << i->attributes["stride_x"];
cout << ", stride_h=" << i->attributes["stride_y"];
cout << ", pad_w=" << i->attributes["padding_x"];
cout << ", pad_h=" << i->attributes["padding_y"];
cout << ", num_output=" << i->attribute("num_filters");
cout << ", kernel_w=" << i->attribute("nc");
cout << ", kernel_h=" << i->attribute("nr");
cout << ", stride_w=" << i->attribute("stride_x");
cout << ", stride_h=" << i->attribute("stride_y");
cout << ", pad_w=" << i->attribute("padding_x");
cout << ", pad_h=" << i->attribute("padding_y");
cout << ");\n";
}
else if (i->detail_name == "relu")
......@@ -162,51 +173,91 @@ void convert_dlib_xml_to_cafffe_python_code(
{
cout << " n." << i->caffe_layer_name() << " = L.Pooling(n." << find_input_layer_caffe_name(i);
cout << ", pool=P.Pooling.MAX";
cout << ", kernel_w=" << i->attributes["nc"];
cout << ", kernel_h=" << i->attributes["nr"];
cout << ", stride_w=" << i->attributes["stride_x"];
cout << ", stride_h=" << i->attributes["stride_y"];
cout << ", pad_w=" << i->attributes["padding_x"];
cout << ", pad_h=" << i->attributes["padding_y"];
if (i->attribute("nc")==0)
{
cout << ", global_pooling=True";
}
else
{
cout << ", kernel_w=" << i->attribute("nc");
cout << ", kernel_h=" << i->attribute("nr");
}
if (i->attribute("padding_x") != 0 || i->attribute("padding_y") != 0)
{
throw dlib::error("dlib and caffe implement pooling with non-zero padding differently, so you can't convert a "
"network with such pooling layers.");
}
cout << ", stride_w=" << i->attribute("stride_x");
cout << ", stride_h=" << i->attribute("stride_y");
cout << ", pad_w=" << i->attribute("padding_x");
cout << ", pad_h=" << i->attribute("padding_y");
cout << ");\n";
}
else if (i->detail_name == "avg_pool")
{
cout << " n." << i->caffe_layer_name() << " = L.Pooling(n." << find_input_layer_caffe_name(i);
cout << ", pool=P.Pooling.MAX";
cout << ", kernel_w=" << i->attributes["nc"];
cout << ", kernel_h=" << i->attributes["nr"];
cout << ", stride_w=" << i->attributes["stride_x"];
cout << ", stride_h=" << i->attributes["stride_y"];
cout << ", pad_w=" << i->attributes["padding_x"];
cout << ", pad_h=" << i->attributes["padding_y"];
cout << ", pool=P.Pooling.AVE";
if (i->attribute("nc")==0)
{
cout << ", global_pooling=True";
}
else
{
cout << ", kernel_w=" << i->attribute("nc");
cout << ", kernel_h=" << i->attribute("nr");
}
if (i->attribute("padding_x") != 0 || i->attribute("padding_y") != 0)
{
throw dlib::error("dlib and caffe implement pooling with non-zero padding differently, so you can't convert a "
"network with such pooling layers.");
}
cout << ", stride_w=" << i->attribute("stride_x");
cout << ", stride_h=" << i->attribute("stride_y");
cout << ", pad_w=" << i->attribute("padding_x");
cout << ", pad_h=" << i->attribute("padding_y");
cout << ");\n";
}
else if (i->detail_name == "fc")
{
cout << " n." << i->caffe_layer_name() << " = L.InnerProduct(n." << find_input_layer_caffe_name(i);
cout << ", num_output=" << i->attributes["num_outputs"];
cout << ", num_output=" << i->attribute("num_outputs");
cout << ", bias_term=True";
cout << ");\n";
}
else if (i->detail_name == "fc_no_bias")
{
cout << " n." << i->caffe_layer_name() << " = L.InnerProduct(n." << find_input_layer_caffe_name(i);
cout << ", num_output=" << i->attributes["num_outputs"];
cout << ", num_output=" << i->attribute("num_outputs");
cout << ", bias_term=False";
cout << ");\n";
}
else if (i->detail_name == "bn_con")
else if (i->detail_name == "bn_con" || i->detail_name == "bn_fc")
{
// TODO
throw dlib::error("Conversion from dlib's batch norm layers to caffe's isn't supported. Instead, "
"you should put your network into 'test mode' by switching batch norm layers to affine layers.");
}
else if (i->detail_name == "bn_fc")
else if (i->detail_name == "affine_con")
{
// TODO
cout << " n." << i->caffe_layer_name() << " = L.Scale(n." << find_input_layer_caffe_name(i);
cout << ", axis=1";
cout << ", bias_term=True";
cout << ");\n";
}
else if (i->detail_name == "affine_fc")
{
cout << " n." << i->caffe_layer_name() << " = L.Scale(n." << find_input_layer_caffe_name(i);
cout << ", axis=3";
cout << ", bias_term=True";
cout << ");\n";
}
else if (i->detail_name == "add_prev")
{
// TODO
cout << " n." << i->caffe_layer_name() << " = L.Eltwise(n." << find_input_layer_caffe_name(i);
cout << ", n." << find_layer_caffe_name(i, i->attribute("tag"));
cout << ", operation=P.Eltwise.SUM";
cout << ");\n";
}
else
{
......@@ -215,6 +266,11 @@ void convert_dlib_xml_to_cafffe_python_code(
}
cout << " return n.to_proto();\n\n" << endl;
// -------------------------
// -------------------------
cout << "def save_as_caffe_model(def_file, weights_file):\n";
cout << " with open(def_file, 'w') as f: f.write(str(make_netspec()));\n";
cout << " net = caffe.Net(def_file, caffe.TEST);\n";
......@@ -222,6 +278,9 @@ void convert_dlib_xml_to_cafffe_python_code(
cout << " net.save(weights_file);\n\n";
// -------------------------
// -------------------------
cout << "def set_network_weights(net):\n";
cout << " # populate network parameters\n";
......@@ -235,7 +294,7 @@ void convert_dlib_xml_to_cafffe_python_code(
if (i->detail_name == "con")
{
const long num_filters = i->attributes["num_filters"];
const long num_filters = i->attribute("num_filters");
matrix<double> weights = trans(rowm(i->params,range(0,i->params.size()-num_filters-1)));
matrix<double> biases = trans(rowm(i->params,range(i->params.size()-num_filters, i->params.size()-1)));
......@@ -273,13 +332,21 @@ void convert_dlib_xml_to_cafffe_python_code(
cout << " p.shape = net.params['"<<i->caffe_layer_name()<<"'][0].data.shape;\n";
cout << " net.params['"<<i->caffe_layer_name()<<"'][0].data[:] = p;\n";
}
else if (i->detail_name == "bn_con")
else if (i->detail_name == "affine_con" || i->detail_name == "affine_fc")
{
// TODO
}
else if (i->detail_name == "bn_fc")
{
// TODO
const long dims = i->params.size()/2;
matrix<double> gamma = trans(rowm(i->params,range(0,dims-1)));
matrix<double> beta = trans(rowm(i->params,range(dims, 2*dims-1)));
// set gamma weights
cout << " p = "; print_as_np_array(cout,gamma); cout << ";\n";
cout << " p.shape = net.params['"<<i->caffe_layer_name()<<"'][0].data.shape;\n";
cout << " net.params['"<<i->caffe_layer_name()<<"'][0].data[:] = p;\n";
// set beta weights
cout << " p = "; print_as_np_array(cout,beta); cout << ";\n";
cout << " p.shape = net.params['"<<i->caffe_layer_name()<<"'][1].data.shape;\n";
cout << " net.params['"<<i->caffe_layer_name()<<"'][1].data[:] = p;\n";
}
}
......@@ -289,6 +356,7 @@ void convert_dlib_xml_to_cafffe_python_code(
int main(int argc, char** argv) try
{
cout.precision(9);
// TODO, write out to multiple files or just process one file at a time.
for (int i = 1; i < argc; ++i)
convert_dlib_xml_to_cafffe_python_code(argv[i]);
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment