Chiebot-Mirror
/
opencv_contrib
mirror of https://github.com/opencv/opencv_contrib.git
8
0
Fork 0
Code Issues Projects Releases Wiki Activity

Updated Halide tests. Simplified batch norm using Halide. Bug fix in convolutional layer.

Browse Source
pull/1249/head
dkurt 8 years ago
parent e551d15c2b
commit 37cf4974a4
4 changed files with 16 additions and 39 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 4
      modules/dnn/perf/perf_halide_net.cpp
  2. 29
      modules/dnn/src/layers/batch_norm_layer.cpp
  3. 2
      modules/dnn/src/layers/convolution_layer.cpp
  4. 20
      modules/dnn/test/test_halide_nets.cpp

4
modules/dnn/perf/perf_halide_net.cpp
Unescape View File

@ -39,7 +39,7 @@ static void loadNet(std::string weights, std::string proto, std::string schedule
else
CV_Error(Error::StsNotImplemented, "Unknown framework " + framework);
net->setInput(blobFromImage(input, 1.0, false));
net->setInput(blobFromImage(input, 1.0, Size(), Scalar(), false));
net->setPreferableBackend(DNN_BACKEND_HALIDE);
net->setPreferableTarget(targetId);
net->setHalideScheduler(scheduler);
@ -52,7 +52,7 @@ static void loadNet(std::string weights, std::string proto, std::string schedule
PERF_TEST(GoogLeNet, HalidePerfTest)
{
Net net;
loadNet("dnn/bvlc_googlenet2.caffemodel", "dnn/bvlc_googlenet.prototxt",
loadNet("dnn/bvlc_googlenet.caffemodel", "dnn/bvlc_googlenet.prototxt",
"", 227, 227, "prob", "caffe", DNN_TARGET_CPU, &net);
TEST_CYCLE() net.forward();
SANITY_CHECK_NOTHING();

29
modules/dnn/src/layers/batch_norm_layer.cpp
Unescape View File

@ -167,32 +167,9 @@ public:
Halide::Func top = (name.empty() ? Halide::Func() : Halide::Func(name));
Halide::Var x("x"), y("y"), c("c"), n("n");
const int weightsBlobIndex = 2;
const int biasBlobIndex = weightsBlobIndex + hasWeights;
const int numChannels = blobs[0].total();
float* meanData = (float*)blobs[0].data;
float* stdData = (float*)blobs[1].data;
float* weightsData = (hasWeights ? (float*)blobs[weightsBlobIndex].data : NULL);
float* biasData = (hasBias ? (float*)blobs[biasBlobIndex].data : NULL);
float varMeanScale = 1.f;
if (!hasWeights && !hasBias) {
varMeanScale = *blobs[2].ptr<float>();
if (varMeanScale != 0)
varMeanScale = 1/varMeanScale;
}
Halide::Buffer<float> weights(numChannels);
Halide::Buffer<float> bias(numChannels);
for (int i = 0; i < numChannels; ++i)
{
weights(i) = (hasWeights ? weightsData[i] : 1.0f) /
sqrt(stdData[i] * varMeanScale + epsilon);
bias(i) = (hasBias ? biasData[i] : 0.0f) -
weights(i) * meanData[i] * varMeanScale;
}
weights.set_host_dirty();
bias.set_host_dirty();
const int numChannels = weights_.total();
auto weights = wrapToHalideBuffer(weights_, {numChannels});
auto bias = wrapToHalideBuffer(bias_, {numChannels});
top(x, y, c, n) = input * weights(c) + bias(c);
return top;
}

2
modules/dnn/src/layers/convolution_layer.cpp
Unescape View File

@ -625,7 +625,7 @@ public:
{
// prepare weightsMat where each row is aligned and has enough zero padding on the right to
// use vectorized (i.e. with intrinsics) loops without tail processing
Mat wm = blobs[0].reshape(1, outCn);
Mat wm = blobs[0].reshape(1, outCn).clone();
if( wm.step1() % VEC_ALIGN != 0 )
{
int newcols = (int)alignSize(wm.step1(), VEC_ALIGN);

20
modules/dnn/test/test_halide_nets.cpp
Unescape View File

@ -34,7 +34,7 @@ static void loadNet(const std::string& weights, const std::string& proto,
static void test(const std::string& weights, const std::string& proto,
const std::string& scheduler, int inWidth, int inHeight,
const std::string& outputLayer, const std::string& framework,
int targetId)
int targetId, double l1 = 1e-5, double lInf = 1e-4)
{
Mat input(inHeight, inWidth, CV_32FC3), outputDefault, outputHalide;
randu(input, 0.0f, 1.0f);
@ -43,23 +43,23 @@ static void test(const std::string& weights, const std::string& proto,
loadNet(weights, proto, framework, &netDefault);
loadNet(weights, proto, framework, &netHalide);
netDefault.setInput(blobFromImage(input.clone(), 1.0f, false));
netDefault.setInput(blobFromImage(input.clone(), 1.0f, Size(), Scalar(), false));
outputDefault = netDefault.forward(outputLayer).clone();
netHalide.setInput(blobFromImage(input.clone(), 1.0f, false));
netHalide.setInput(blobFromImage(input.clone(), 1.0f, Size(), Scalar(), false));
netHalide.setPreferableBackend(DNN_BACKEND_HALIDE);
netHalide.setPreferableTarget(targetId);
netHalide.setHalideScheduler(scheduler);
outputHalide = netHalide.forward(outputLayer).clone();
normAssert(outputDefault, outputHalide);
normAssert(outputDefault, outputHalide, "First run", l1, lInf);
// An extra test: change input.
input *= 0.1f;
netDefault.setInput(blobFromImage(input.clone(), 1.0, false));
netHalide.setInput(blobFromImage(input.clone(), 1.0, false));
netDefault.setInput(blobFromImage(input.clone(), 1.0, Size(), Scalar(), false));
netHalide.setInput(blobFromImage(input.clone(), 1.0, Size(), Scalar(), false));
normAssert(outputDefault, outputHalide);
normAssert(outputDefault, outputHalide, "Second run", l1, lInf);
// Swap backends.
netHalide.setPreferableBackend(DNN_BACKEND_DEFAULT);
@ -71,7 +71,7 @@ static void test(const std::string& weights, const std::string& proto,
netDefault.setHalideScheduler(scheduler);
outputHalide = netDefault.forward(outputLayer).clone();
normAssert(outputDefault, outputHalide);
normAssert(outputDefault, outputHalide, "Swap backends", l1, lInf);
}
////////////////////////////////////////////////////////////////////////////////
@ -119,7 +119,7 @@ TEST(Reproducibility_ENet_Halide, Accuracy)
{
test(findDataFile("dnn/Enet-model-best.net", false), "",
findDataFile("dnn/halide_scheduler_enet.yml", false),
512, 512, "l367_Deconvolution", "torch", DNN_TARGET_CPU);
512, 512, "l367_Deconvolution", "torch", DNN_TARGET_CPU, 2e-5, 0.15);
};
////////////////////////////////////////////////////////////////////////////////
// OpenCL target
@ -166,7 +166,7 @@ TEST(Reproducibility_ENet_Halide_opencl, Accuracy)
{
test(findDataFile("dnn/Enet-model-best.net", false), "",
findDataFile("dnn/halide_scheduler_opencl_enet.yml", false),
512, 512, "l367_Deconvolution", "torch", DNN_TARGET_OPENCL);
512, 512, "l367_Deconvolution", "torch", DNN_TARGET_OPENCL, 2e-5, 0.14);
};
#endif // HAVE_HALIDE

Write Preview
Loading…
Cancel
Save