mirror of
https://github.com/opencv/opencv.git
synced 2026-07-30 07:43:03 +04:00
Parametric OpenCL deep learning tests
This commit is contained in:
Dmitry Kurtaev
@@ -62,6 +62,21 @@ static std::string _tf(TStr filename, bool inTorchDir = true)
|
||||
return findDataFile(path, false);
|
||||
}
|
||||
|
||||
CV_ENUM(DNNTarget, DNN_TARGET_CPU, DNN_TARGET_OPENCL)
|
||||
static testing::internal::ParamGenerator<DNNTarget> availableBackends()
|
||||
{
|
||||
static std::vector<DNNTarget> targets;
|
||||
if (targets.empty())
|
||||
{
|
||||
targets.push_back(DNN_TARGET_CPU);
|
||||
#ifdef HAVE_OPENCL
|
||||
if (cv::ocl::useOpenCL())
|
||||
targets.push_back(DNN_TARGET_OPENCL);
|
||||
#endif
|
||||
}
|
||||
return testing::ValuesIn(targets);
|
||||
}
|
||||
|
||||
TEST(Torch_Importer, simple_read)
|
||||
{
|
||||
Net net;
|
||||
@@ -100,197 +115,123 @@ static void runTorchNet(String prefix, int targetId = DNN_TARGET_CPU, String out
|
||||
}
|
||||
}
|
||||
|
||||
TEST(Torch_Importer, run_convolution)
|
||||
typedef testing::TestWithParam<DNNTarget> Test_Torch_layers;
|
||||
|
||||
TEST_P(Test_Torch_layers, run_convolution)
|
||||
{
|
||||
runTorchNet("net_conv");
|
||||
runTorchNet("net_conv", GetParam());
|
||||
}
|
||||
|
||||
OCL_TEST(Torch_Importer, run_convolution)
|
||||
TEST_P(Test_Torch_layers, run_pool_max)
|
||||
{
|
||||
runTorchNet("net_conv", DNN_TARGET_OPENCL);
|
||||
runTorchNet("net_pool_max", GetParam(), "", true);
|
||||
}
|
||||
|
||||
TEST(Torch_Importer, run_pool_max)
|
||||
TEST_P(Test_Torch_layers, run_pool_ave)
|
||||
{
|
||||
runTorchNet("net_pool_max", DNN_TARGET_CPU, "", true);
|
||||
runTorchNet("net_pool_ave", GetParam());
|
||||
}
|
||||
|
||||
OCL_TEST(Torch_Importer, run_pool_max)
|
||||
TEST_P(Test_Torch_layers, run_reshape)
|
||||
{
|
||||
runTorchNet("net_pool_max", DNN_TARGET_OPENCL, "", true);
|
||||
int targetId = GetParam();
|
||||
runTorchNet("net_reshape", targetId);
|
||||
runTorchNet("net_reshape_batch", targetId);
|
||||
runTorchNet("net_reshape_single_sample", targetId);
|
||||
runTorchNet("net_reshape_channels", targetId, "", false, true);
|
||||
}
|
||||
|
||||
TEST(Torch_Importer, run_pool_ave)
|
||||
TEST_P(Test_Torch_layers, run_linear)
|
||||
{
|
||||
runTorchNet("net_pool_ave");
|
||||
runTorchNet("net_linear_2d", GetParam());
|
||||
}
|
||||
|
||||
OCL_TEST(Torch_Importer, run_pool_ave)
|
||||
TEST_P(Test_Torch_layers, run_concat)
|
||||
{
|
||||
runTorchNet("net_pool_ave", DNN_TARGET_OPENCL);
|
||||
int targetId = GetParam();
|
||||
runTorchNet("net_concat", targetId, "l5_torchMerge");
|
||||
runTorchNet("net_depth_concat", targetId, "", false, true);
|
||||
}
|
||||
|
||||
TEST(Torch_Importer, run_reshape)
|
||||
TEST_P(Test_Torch_layers, run_deconv)
|
||||
{
|
||||
runTorchNet("net_reshape");
|
||||
runTorchNet("net_reshape_batch");
|
||||
runTorchNet("net_reshape_single_sample");
|
||||
runTorchNet("net_reshape_channels", DNN_TARGET_CPU, "", false, true);
|
||||
runTorchNet("net_deconv", GetParam());
|
||||
}
|
||||
|
||||
TEST(Torch_Importer, run_linear)
|
||||
TEST_P(Test_Torch_layers, run_batch_norm)
|
||||
{
|
||||
runTorchNet("net_linear_2d");
|
||||
runTorchNet("net_batch_norm", GetParam(), "", false, true);
|
||||
}
|
||||
|
||||
TEST(Torch_Importer, run_paralel)
|
||||
TEST_P(Test_Torch_layers, net_prelu)
|
||||
{
|
||||
runTorchNet("net_parallel", DNN_TARGET_CPU, "l5_torchMerge");
|
||||
runTorchNet("net_prelu", GetParam());
|
||||
}
|
||||
|
||||
TEST(Torch_Importer, run_concat)
|
||||
TEST_P(Test_Torch_layers, net_cadd_table)
|
||||
{
|
||||
runTorchNet("net_concat", DNN_TARGET_CPU, "l5_torchMerge");
|
||||
runTorchNet("net_depth_concat", DNN_TARGET_CPU, "", false, true);
|
||||
runTorchNet("net_cadd_table", GetParam());
|
||||
}
|
||||
|
||||
OCL_TEST(Torch_Importer, run_concat)
|
||||
TEST_P(Test_Torch_layers, net_softmax)
|
||||
{
|
||||
runTorchNet("net_concat", DNN_TARGET_OPENCL, "l5_torchMerge");
|
||||
runTorchNet("net_depth_concat", DNN_TARGET_OPENCL, "", false, true);
|
||||
int targetId = GetParam();
|
||||
runTorchNet("net_softmax", targetId);
|
||||
runTorchNet("net_softmax_spatial", targetId);
|
||||
}
|
||||
|
||||
TEST(Torch_Importer, run_deconv)
|
||||
{
|
||||
runTorchNet("net_deconv");
|
||||
}
|
||||
|
||||
OCL_TEST(Torch_Importer, run_deconv)
|
||||
{
|
||||
runTorchNet("net_deconv", DNN_TARGET_OPENCL);
|
||||
}
|
||||
|
||||
TEST(Torch_Importer, run_batch_norm)
|
||||
{
|
||||
runTorchNet("net_batch_norm", DNN_TARGET_CPU, "", false, true);
|
||||
}
|
||||
|
||||
OCL_TEST(Torch_Importer, run_batch_norm)
|
||||
{
|
||||
runTorchNet("net_batch_norm", DNN_TARGET_OPENCL, "", false, true);
|
||||
}
|
||||
|
||||
TEST(Torch_Importer, net_prelu)
|
||||
{
|
||||
runTorchNet("net_prelu");
|
||||
}
|
||||
|
||||
TEST(Torch_Importer, net_cadd_table)
|
||||
{
|
||||
runTorchNet("net_cadd_table");
|
||||
}
|
||||
|
||||
TEST(Torch_Importer, net_softmax)
|
||||
{
|
||||
runTorchNet("net_softmax");
|
||||
runTorchNet("net_softmax_spatial");
|
||||
}
|
||||
|
||||
OCL_TEST(Torch_Importer, net_softmax)
|
||||
{
|
||||
runTorchNet("net_softmax", DNN_TARGET_OPENCL);
|
||||
runTorchNet("net_softmax_spatial", DNN_TARGET_OPENCL);
|
||||
}
|
||||
|
||||
TEST(Torch_Importer, net_logsoftmax)
|
||||
TEST_P(Test_Torch_layers, net_logsoftmax)
|
||||
{
|
||||
runTorchNet("net_logsoftmax");
|
||||
runTorchNet("net_logsoftmax_spatial");
|
||||
}
|
||||
|
||||
OCL_TEST(Torch_Importer, net_logsoftmax)
|
||||
TEST_P(Test_Torch_layers, net_lp_pooling)
|
||||
{
|
||||
runTorchNet("net_logsoftmax", DNN_TARGET_OPENCL);
|
||||
runTorchNet("net_logsoftmax_spatial", DNN_TARGET_OPENCL);
|
||||
int targetId = GetParam();
|
||||
runTorchNet("net_lp_pooling_square", targetId, "", false, true);
|
||||
runTorchNet("net_lp_pooling_power", targetId, "", false, true);
|
||||
}
|
||||
|
||||
TEST(Torch_Importer, net_lp_pooling)
|
||||
TEST_P(Test_Torch_layers, net_conv_gemm_lrn)
|
||||
{
|
||||
runTorchNet("net_lp_pooling_square", DNN_TARGET_CPU, "", false, true);
|
||||
runTorchNet("net_lp_pooling_power", DNN_TARGET_CPU, "", false, true);
|
||||
runTorchNet("net_conv_gemm_lrn", GetParam(), "", false, true);
|
||||
}
|
||||
|
||||
TEST(Torch_Importer, net_conv_gemm_lrn)
|
||||
TEST_P(Test_Torch_layers, net_inception_block)
|
||||
{
|
||||
runTorchNet("net_conv_gemm_lrn", DNN_TARGET_CPU, "", false, true);
|
||||
runTorchNet("net_inception_block", GetParam(), "", false, true);
|
||||
}
|
||||
|
||||
TEST(Torch_Importer, net_inception_block)
|
||||
TEST_P(Test_Torch_layers, net_normalize)
|
||||
{
|
||||
runTorchNet("net_inception_block", DNN_TARGET_CPU, "", false, true);
|
||||
runTorchNet("net_normalize", GetParam(), "", false, true);
|
||||
}
|
||||
|
||||
TEST(Torch_Importer, net_normalize)
|
||||
TEST_P(Test_Torch_layers, net_padding)
|
||||
{
|
||||
runTorchNet("net_normalize", DNN_TARGET_CPU, "", false, true);
|
||||
int targetId = GetParam();
|
||||
runTorchNet("net_padding", targetId, "", false, true);
|
||||
runTorchNet("net_spatial_zero_padding", targetId, "", false, true);
|
||||
runTorchNet("net_spatial_reflection_padding", targetId, "", false, true);
|
||||
}
|
||||
|
||||
OCL_TEST(Torch_Importer, net_normalize)
|
||||
TEST_P(Test_Torch_layers, net_non_spatial)
|
||||
{
|
||||
runTorchNet("net_normalize", DNN_TARGET_OPENCL, "", false, true);
|
||||
runTorchNet("net_non_spatial", GetParam(), "", false, true);
|
||||
}
|
||||
|
||||
TEST(Torch_Importer, net_padding)
|
||||
{
|
||||
runTorchNet("net_padding", DNN_TARGET_CPU, "", false, true);
|
||||
runTorchNet("net_spatial_zero_padding", DNN_TARGET_CPU, "", false, true);
|
||||
runTorchNet("net_spatial_reflection_padding", DNN_TARGET_CPU, "", false, true);
|
||||
}
|
||||
INSTANTIATE_TEST_CASE_P(/**/, Test_Torch_layers, availableBackends());
|
||||
|
||||
TEST(Torch_Importer, net_non_spatial)
|
||||
{
|
||||
runTorchNet("net_non_spatial", DNN_TARGET_CPU, "", false, true);
|
||||
}
|
||||
typedef testing::TestWithParam<DNNTarget> Test_Torch_nets;
|
||||
|
||||
OCL_TEST(Torch_Importer, net_non_spatial)
|
||||
{
|
||||
runTorchNet("net_non_spatial", DNN_TARGET_OPENCL, "", false, true);
|
||||
}
|
||||
|
||||
TEST(Torch_Importer, ENet_accuracy)
|
||||
{
|
||||
Net net;
|
||||
{
|
||||
const string model = findDataFile("dnn/Enet-model-best.net", false);
|
||||
net = readNetFromTorch(model, true);
|
||||
ASSERT_FALSE(net.empty());
|
||||
}
|
||||
|
||||
Mat sample = imread(_tf("street.png", false));
|
||||
Mat inputBlob = blobFromImage(sample, 1./255);
|
||||
|
||||
net.setInput(inputBlob, "");
|
||||
Mat out = net.forward();
|
||||
Mat ref = blobFromNPY(_tf("torch_enet_prob.npy", false));
|
||||
// Due to numerical instability in Pooling-Unpooling layers (indexes jittering)
|
||||
// thresholds for ENet must be changed. Accuracy of resuults was checked on
|
||||
// Cityscapes dataset and difference in mIOU with Torch is 10E-4%
|
||||
normAssert(ref, out, "", 0.00044, 0.44);
|
||||
|
||||
const int N = 3;
|
||||
for (int i = 0; i < N; i++)
|
||||
{
|
||||
net.setInput(inputBlob, "");
|
||||
Mat out = net.forward();
|
||||
normAssert(ref, out, "", 0.00044, 0.44);
|
||||
}
|
||||
}
|
||||
|
||||
TEST(Torch_Importer, OpenFace_accuracy)
|
||||
TEST_P(Test_Torch_nets, OpenFace_accuracy)
|
||||
{
|
||||
const string model = findDataFile("dnn/openface_nn4.small2.v1.t7", false);
|
||||
Net net = readNetFromTorch(model);
|
||||
|
||||
net.setPreferableTarget(GetParam());
|
||||
|
||||
Mat sample = imread(findDataFile("cv/shared/lena.png", false));
|
||||
Mat sampleF32(sample.size(), CV_32FC3);
|
||||
sample.convertTo(sampleF32, sampleF32.type());
|
||||
@@ -306,30 +247,7 @@ TEST(Torch_Importer, OpenFace_accuracy)
|
||||
normAssert(out, outRef);
|
||||
}
|
||||
|
||||
OCL_TEST(Torch_Importer, OpenFace_accuracy)
|
||||
{
|
||||
const string model = findDataFile("dnn/openface_nn4.small2.v1.t7", false);
|
||||
Net net = readNetFromTorch(model);
|
||||
|
||||
net.setPreferableBackend(DNN_BACKEND_DEFAULT);
|
||||
net.setPreferableTarget(DNN_TARGET_OPENCL);
|
||||
|
||||
Mat sample = imread(findDataFile("cv/shared/lena.png", false));
|
||||
Mat sampleF32(sample.size(), CV_32FC3);
|
||||
sample.convertTo(sampleF32, sampleF32.type());
|
||||
sampleF32 /= 255;
|
||||
resize(sampleF32, sampleF32, Size(96, 96), 0, 0, INTER_NEAREST);
|
||||
|
||||
Mat inputBlob = blobFromImage(sampleF32);
|
||||
|
||||
net.setInput(inputBlob);
|
||||
Mat out = net.forward();
|
||||
|
||||
Mat outRef = readTorchBlob(_tf("net_openface_output.dat"), true);
|
||||
normAssert(out, outRef);
|
||||
}
|
||||
|
||||
OCL_TEST(Torch_Importer, ENet_accuracy)
|
||||
TEST_P(Test_Torch_nets, ENet_accuracy)
|
||||
{
|
||||
Net net;
|
||||
{
|
||||
@@ -338,8 +256,7 @@ OCL_TEST(Torch_Importer, ENet_accuracy)
|
||||
ASSERT_TRUE(!net.empty());
|
||||
}
|
||||
|
||||
net.setPreferableBackend(DNN_BACKEND_DEFAULT);
|
||||
net.setPreferableTarget(DNN_TARGET_OPENCL);
|
||||
net.setPreferableTarget(GetParam());
|
||||
|
||||
Mat sample = imread(_tf("street.png", false));
|
||||
Mat inputBlob = blobFromImage(sample, 1./255);
|
||||
@@ -374,7 +291,7 @@ OCL_TEST(Torch_Importer, ENet_accuracy)
|
||||
// -median_filter 0 \
|
||||
// -image_size 0 \
|
||||
// -model models/instance_norm/feathers.t7
|
||||
TEST(Torch_Importer, FastNeuralStyle_accuracy)
|
||||
TEST_P(Test_Torch_nets, FastNeuralStyle_accuracy)
|
||||
{
|
||||
std::string models[] = {"dnn/fast_neural_style_eccv16_starry_night.t7",
|
||||
"dnn/fast_neural_style_instance_norm_feathers.t7"};
|
||||
@@ -385,6 +302,8 @@ TEST(Torch_Importer, FastNeuralStyle_accuracy)
|
||||
const string model = findDataFile(models[i], false);
|
||||
Net net = readNetFromTorch(model);
|
||||
|
||||
net.setPreferableTarget(GetParam());
|
||||
|
||||
Mat img = imread(findDataFile("dnn/googlenet_1.png", false));
|
||||
Mat inputBlob = blobFromImage(img, 1.0, Size(), Scalar(103.939, 116.779, 123.68), false);
|
||||
|
||||
@@ -404,37 +323,17 @@ TEST(Torch_Importer, FastNeuralStyle_accuracy)
|
||||
}
|
||||
}
|
||||
|
||||
OCL_TEST(Torch_Importer, FastNeuralStyle_accuracy)
|
||||
INSTANTIATE_TEST_CASE_P(/**/, Test_Torch_nets, availableBackends());
|
||||
|
||||
// TODO: fix OpenCL and add to the rest of tests
|
||||
TEST(Torch_Importer, run_paralel)
|
||||
{
|
||||
std::string models[] = {"dnn/fast_neural_style_eccv16_starry_night.t7",
|
||||
"dnn/fast_neural_style_instance_norm_feathers.t7"};
|
||||
std::string targets[] = {"dnn/lena_starry_night.png", "dnn/lena_feathers.png"};
|
||||
runTorchNet("net_parallel", DNN_TARGET_CPU, "l5_torchMerge");
|
||||
}
|
||||
|
||||
for (int i = 0; i < 2; ++i)
|
||||
{
|
||||
const string model = findDataFile(models[i], false);
|
||||
Net net = readNetFromTorch(model);
|
||||
|
||||
net.setPreferableBackend(DNN_BACKEND_DEFAULT);
|
||||
net.setPreferableTarget(DNN_TARGET_OPENCL);
|
||||
|
||||
Mat img = imread(findDataFile("dnn/googlenet_1.png", false));
|
||||
Mat inputBlob = blobFromImage(img, 1.0, Size(), Scalar(103.939, 116.779, 123.68), false);
|
||||
|
||||
net.setInput(inputBlob);
|
||||
Mat out = net.forward();
|
||||
|
||||
// Deprocessing.
|
||||
getPlane(out, 0, 0) += 103.939;
|
||||
getPlane(out, 0, 1) += 116.779;
|
||||
getPlane(out, 0, 2) += 123.68;
|
||||
out = cv::min(cv::max(0, out), 255);
|
||||
|
||||
Mat ref = imread(findDataFile(targets[i]));
|
||||
Mat refBlob = blobFromImage(ref, 1.0, Size(), Scalar(), false);
|
||||
|
||||
normAssert(out, refBlob, "", 0.5, 1.1);
|
||||
}
|
||||
TEST(Torch_Importer, DISABLED_run_paralel)
|
||||
{
|
||||
runTorchNet("net_parallel", DNN_TARGET_OPENCL, "l5_torchMerge");
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user