opencv/modules/dnn/test/test_caffe_importer.cpp at master · pythonmjs/opencv · GitHub

History

485 lines (400 loc) · 18.9 KB

Raw

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

265

266

267

268

269

270

271

272

273

274

275

276

277

278

279

280

281

282

283

284

285

286

287

288

289

290

291

292

293

294

295

296

297

298

299

300

301

302

303

304

305

306

307

308

309

310

311

312

313

314

315

316

317

318

319

320

321

322

323

324

325

326

327

328

329

330

331

332

333

334

335

336

337

338

339

340

341

342

343

344

345

346

347

348

349

350

351

352

353

354

355

356

357

358

359

360

361

362

363

364

365

366

367

368

369

370

371

372

373

374

375

376

377

378

379

380

381

382

383

384

385

386

387

388

389

390

391

392

393

394

395

396

397

398

399

400

401

402

403

404

405

406

407

408

409

410

411

412

413

414

415

416

417

418

419

420

421

422

423

424

425

426

427

428

429

430

431

432

433

434

435

436

437

438

439

440

441

442

443

444

445

446

447

448

449

450

451

452

453

454

455

456

457

458

459

460

461

462

463

464

465

466

467

468

469

470

471

472

473

474

475

476

477

478

479

480

481

482

483

484

485

/*M///////////////////////////////////////////////////////////////////////////////////////

// IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.

// By downloading, copying, installing or using the software you agree to this license.

// If you do not agree to this license, do not download, install,

// copy or use the software.

// License Agreement

// For Open Source Computer Vision Library

// Third party copyrights are property of their respective owners.

// Redistribution and use in source and binary forms, with or without modification,

// are permitted provided that the following conditions are met:

// * Redistribution's of source code must retain the above copyright notice,

// this list of conditions and the following disclaimer.

// * Redistribution's in binary form must reproduce the above copyright notice,

// this list of conditions and the following disclaimer in the documentation

// and/or other materials provided with the distribution.

// * The name of the copyright holders may not be used to endorse or promote products

// derived from this software without specific prior written permission.

// This software is provided by the copyright holders and contributors "as is" and

// any express or implied warranties, including, but not limited to, the implied

// warranties of merchantability and fitness for a particular purpose are disclaimed.

// In no event shall the Intel Corporation or contributors be liable for any direct,

// indirect, incidental, special, exemplary, or consequential damages

// (including, but not limited to, procurement of substitute goods or services;

// loss of use, data, or profits; or business interruption) however caused

// and on any theory of liability, whether in contract, strict liability,

// or tort (including negligence or otherwise) arising in any way out of

// the use of this software, even if advised of the possibility of such damage.

//M*/

#include "test_precomp.hpp"

#include "npy_blob.hpp"

#include <opencv2/dnn/shape_utils.hpp>

namespace opencv_test { namespace {

template<typename TString>

static std::string _tf(TString filename)

{

return (getOpenCVExtraDir() + "/dnn/") + filename;

}

TEST(Test_Caffe, memory_read)

{

const string proto = findDataFile("dnn/bvlc_googlenet.prototxt", false);

const string model = findDataFile("dnn/bvlc_googlenet.caffemodel", false);

string dataProto;

ASSERT_TRUE(readFileInMemory(proto, dataProto));

string dataModel;

ASSERT_TRUE(readFileInMemory(model, dataModel));

Net net = readNetFromCaffe(dataProto.c_str(), dataProto.size());

net.setPreferableBackend(DNN_BACKEND_OPENCV);

ASSERT_FALSE(net.empty());

Net net2 = readNetFromCaffe(dataProto.c_str(), dataProto.size(),

dataModel.c_str(), dataModel.size());

ASSERT_FALSE(net2.empty());

}

TEST(Test_Caffe, read_gtsrb)

{

Net net = readNetFromCaffe(_tf("gtsrb.prototxt"));

ASSERT_FALSE(net.empty());

}

TEST(Test_Caffe, read_googlenet)

{

Net net = readNetFromCaffe(_tf("bvlc_googlenet.prototxt"));

ASSERT_FALSE(net.empty());

}

typedef testing::TestWithParam<tuple<bool, Target> > Reproducibility_AlexNet;

TEST_P(Reproducibility_AlexNet, Accuracy)

{

bool readFromMemory = get<0>(GetParam());

Net net;

{

const string proto = findDataFile("dnn/bvlc_alexnet.prototxt", false);

const string model = findDataFile("dnn/bvlc_alexnet.caffemodel", false);

if (readFromMemory)

{

string dataProto;

ASSERT_TRUE(readFileInMemory(proto, dataProto));

string dataModel;

ASSERT_TRUE(readFileInMemory(model, dataModel));

net = readNetFromCaffe(dataProto.c_str(), dataProto.size(),

dataModel.c_str(), dataModel.size());

}

else

net = readNetFromCaffe(proto, model);

ASSERT_FALSE(net.empty());

}

int targetId = get<1>(GetParam());

const float l1 = 1e-5;

const float lInf = (targetId == DNN_TARGET_OPENCL_FP16) ? 3e-3 : 1e-4;

net.setPreferableBackend(DNN_BACKEND_OPENCV);

net.setPreferableTarget(targetId);

Mat sample = imread(_tf("grace_hopper_227.png"));

ASSERT_TRUE(!sample.empty());

net.setInput(blobFromImage(sample, 1.0f, Size(227, 227), Scalar(), false), "data");

Mat out = net.forward("prob");

Mat ref = blobFromNPY(_tf("caffe_alexnet_prob.npy"));

normAssert(ref, out, "", l1, lInf);

}

INSTANTIATE_TEST_CASE_P(/**/, Reproducibility_AlexNet, Combine(testing::Bool(),

Values(DNN_TARGET_CPU, DNN_TARGET_OPENCL, DNN_TARGET_OPENCL_FP16)));

#if !defined(_WIN32) || defined(_WIN64)

TEST(Reproducibility_FCN, Accuracy)

{

Net net;

{

const string proto = findDataFile("dnn/fcn8s-heavy-pascal.prototxt", false);

const string model = findDataFile("dnn/fcn8s-heavy-pascal.caffemodel", false);

net = readNetFromCaffe(proto, model);

ASSERT_FALSE(net.empty());

}

net.setPreferableBackend(DNN_BACKEND_OPENCV);

Mat sample = imread(_tf("street.png"));

ASSERT_TRUE(!sample.empty());

std::vector<int> layerIds;

std::vector<size_t> weights, blobs;

net.getMemoryConsumption(shape(1,3,227,227), layerIds, weights, blobs);

net.setInput(blobFromImage(sample, 1.0f, Size(500, 500), Scalar(), false), "data");

Mat out = net.forward("score");

Mat refData = imread(_tf("caffe_fcn8s_prob.png"), IMREAD_ANYDEPTH);

int shape[] = {1, 21, 500, 500};

Mat ref(4, shape, CV_32FC1, refData.data);

normAssert(ref, out);

}

#endif

TEST(Reproducibility_SSD, Accuracy)

{

Net net;

{

const string proto = findDataFile("dnn/ssd_vgg16.prototxt", false);

const string model = findDataFile("dnn/VGG_ILSVRC2016_SSD_300x300_iter_440000.caffemodel", false);

net = readNetFromCaffe(proto, model);

ASSERT_FALSE(net.empty());

}

net.setPreferableBackend(DNN_BACKEND_OPENCV);

Mat sample = imread(_tf("street.png"));

ASSERT_TRUE(!sample.empty());

if (sample.channels() == 4)

cvtColor(sample, sample, COLOR_BGRA2BGR);

Mat in_blob = blobFromImage(sample, 1.0f, Size(300, 300), Scalar(), false);

net.setInput(in_blob, "data");

Mat out = net.forward("detection_out");

Mat ref = blobFromNPY(_tf("ssd_out.npy"));

normAssertDetections(ref, out);

}

typedef testing::TestWithParam<Target> Reproducibility_MobileNet_SSD;

TEST_P(Reproducibility_MobileNet_SSD, Accuracy)

{

const string proto = findDataFile("dnn/MobileNetSSD_deploy.prototxt", false);

const string model = findDataFile("dnn/MobileNetSSD_deploy.caffemodel", false);

Net net = readNetFromCaffe(proto, model);

int targetId = GetParam();

const float l1 = (targetId == DNN_TARGET_OPENCL_FP16) ? 1.5e-4 : 1e-5;

const float lInf = (targetId == DNN_TARGET_OPENCL_FP16) ? 4e-4 : 1e-4;

net.setPreferableBackend(DNN_BACKEND_OPENCV);

net.setPreferableTarget(targetId);

Mat sample = imread(_tf("street.png"));

Mat inp = blobFromImage(sample, 1.0f / 127.5, Size(300, 300), Scalar(127.5, 127.5, 127.5), false);

net.setInput(inp);

Mat out = net.forward();

const float scores_diff = (targetId == DNN_TARGET_OPENCL_FP16) ? 4e-4 : 1e-5;

const float boxes_iou_diff = (targetId == DNN_TARGET_OPENCL_FP16) ? 5e-3 : 1e-4;

Mat ref = blobFromNPY(_tf("mobilenet_ssd_caffe_out.npy"));

normAssertDetections(ref, out, "", 0.0, scores_diff, boxes_iou_diff);

// Check that detections aren't preserved.

inp.setTo(0.0f);

net.setInput(inp);

out = net.forward();

out = out.reshape(1, out.total() / 7);

const int numDetections = out.rows;

ASSERT_NE(numDetections, 0);

for (int i = 0; i < numDetections; ++i)

{

float confidence = out.ptr<float>(i)[2];

ASSERT_EQ(confidence, 0);

}

// Check batching mode.

ref = ref.reshape(1, numDetections);

inp = blobFromImages(std::vector<Mat>(2, sample), 1.0f / 127.5, Size(300, 300), Scalar(127.5, 127.5, 127.5), false);

net.setInput(inp);

Mat outBatch = net.forward();

// Output blob has a shape 1x1x2Nx7 where N is a number of detection for

// a single sample in batch. The first numbers of detection vectors are batch id.

outBatch = outBatch.reshape(1, outBatch.total() / 7);

EXPECT_EQ(outBatch.rows, 2 * numDetections);

normAssert(outBatch.rowRange(0, numDetections), ref, "", l1, lInf);

normAssert(outBatch.rowRange(numDetections, 2 * numDetections).colRange(1, 7), ref.colRange(1, 7),

"", l1, lInf);

}

INSTANTIATE_TEST_CASE_P(/**/, Reproducibility_MobileNet_SSD,

Values(DNN_TARGET_CPU, DNN_TARGET_OPENCL, DNN_TARGET_OPENCL_FP16));

typedef testing::TestWithParam<Target> Reproducibility_ResNet50;

TEST_P(Reproducibility_ResNet50, Accuracy)

{

Net net = readNetFromCaffe(findDataFile("dnn/ResNet-50-deploy.prototxt", false),

findDataFile("dnn/ResNet-50-model.caffemodel", false));

int targetId = GetParam();

net.setPreferableBackend(DNN_BACKEND_OPENCV);

net.setPreferableTarget(targetId);

float l1 = (targetId == DNN_TARGET_OPENCL_FP16) ? 3e-5 : 1e-5;

float lInf = (targetId == DNN_TARGET_OPENCL_FP16) ? 6e-3 : 1e-4;

Mat input = blobFromImage(imread(_tf("googlenet_0.png")), 1.0f, Size(224,224), Scalar(), false);

ASSERT_TRUE(!input.empty());

net.setInput(input);

Mat out = net.forward();

Mat ref = blobFromNPY(_tf("resnet50_prob.npy"));

normAssert(ref, out, "", l1, lInf);

if (targetId == DNN_TARGET_OPENCL || targetId == DNN_TARGET_OPENCL_FP16)

{

UMat out_umat;

net.forward(out_umat);

normAssert(ref, out_umat, "out_umat", l1, lInf);

std::vector<UMat> out_umats;

net.forward(out_umats);

normAssert(ref, out_umats[0], "out_umat_vector", l1, lInf);

}

INSTANTIATE_TEST_CASE_P(/**/, Reproducibility_ResNet50,

Values(DNN_TARGET_CPU, DNN_TARGET_OPENCL, DNN_TARGET_OPENCL_FP16));

typedef testing::TestWithParam<Target> Reproducibility_SqueezeNet_v1_1;

TEST_P(Reproducibility_SqueezeNet_v1_1, Accuracy)

{

Net net = readNetFromCaffe(findDataFile("dnn/squeezenet_v1.1.prototxt", false),

findDataFile("dnn/squeezenet_v1.1.caffemodel", false));

int targetId = GetParam();

net.setPreferableBackend(DNN_BACKEND_OPENCV);

net.setPreferableTarget(targetId);

Mat input = blobFromImage(imread(_tf("googlenet_0.png")), 1.0f, Size(227,227), Scalar(), false);

ASSERT_TRUE(!input.empty());

Mat out;

if (targetId == DNN_TARGET_OPENCL)

{

// Firstly set a wrong input blob and run the model to receive a wrong output.

// Then set a correct input blob to check CPU->GPU synchronization is working well.

net.setInput(input * 2.0f);

out = net.forward();

}

net.setInput(input);

out = net.forward();

Mat ref = blobFromNPY(_tf("squeezenet_v1.1_prob.npy"));

normAssert(ref, out);

}

INSTANTIATE_TEST_CASE_P(/**/, Reproducibility_SqueezeNet_v1_1, availableDnnTargets());

TEST(Reproducibility_AlexNet_fp16, Accuracy)

{

const float l1 = 1e-5;

const float lInf = 3e-3;

const string proto = findDataFile("dnn/bvlc_alexnet.prototxt", false);

const string model = findDataFile("dnn/bvlc_alexnet.caffemodel", false);

shrinkCaffeModel(model, "bvlc_alexnet.caffemodel_fp16");

Net net = readNetFromCaffe(proto, "bvlc_alexnet.caffemodel_fp16");

net.setPreferableBackend(DNN_BACKEND_OPENCV);

Mat sample = imread(findDataFile("dnn/grace_hopper_227.png", false));

net.setInput(blobFromImage(sample, 1.0f, Size(227, 227), Scalar(), false));

Mat out = net.forward();

Mat ref = blobFromNPY(findDataFile("dnn/caffe_alexnet_prob.npy", false));

normAssert(ref, out, "", l1, lInf);

}

TEST(Reproducibility_GoogLeNet_fp16, Accuracy)

{

const float l1 = 1e-5;

const float lInf = 3e-3;

const string proto = findDataFile("dnn/bvlc_googlenet.prototxt", false);

const string model = findDataFile("dnn/bvlc_googlenet.caffemodel", false);

shrinkCaffeModel(model, "bvlc_googlenet.caffemodel_fp16");

Net net = readNetFromCaffe(proto, "bvlc_googlenet.caffemodel_fp16");

net.setPreferableBackend(DNN_BACKEND_OPENCV);

std::vector<Mat> inpMats;

inpMats.push_back( imread(_tf("googlenet_0.png")) );

inpMats.push_back( imread(_tf("googlenet_1.png")) );

ASSERT_TRUE(!inpMats[0].empty() && !inpMats[1].empty());

net.setInput(blobFromImages(inpMats, 1.0f, Size(), Scalar(), false), "data");

Mat out = net.forward("prob");

Mat ref = blobFromNPY(_tf("googlenet_prob.npy"));

normAssert(out, ref, "", l1, lInf);

}

// https://github.com/richzhang/colorization

TEST(Reproducibility_Colorization, Accuracy)

{

const float l1 = 3e-5;

const float lInf = 3e-3;

Mat inp = blobFromNPY(_tf("colorization_inp.npy"));

Mat ref = blobFromNPY(_tf("colorization_out.npy"));

Mat kernel = blobFromNPY(_tf("colorization_pts_in_hull.npy"));

const string proto = findDataFile("dnn/colorization_deploy_v2.prototxt", false);

const string model = findDataFile("dnn/colorization_release_v2.caffemodel", false);

Net net = readNetFromCaffe(proto, model);

net.setPreferableBackend(DNN_BACKEND_OPENCV);

net.getLayer(net.getLayerId("class8_ab"))->blobs.push_back(kernel);

net.getLayer(net.getLayerId("conv8_313_rh"))->blobs.push_back(Mat(1, 313, CV_32F, 2.606));

net.setInput(inp);

Mat out = net.forward();

normAssert(out, ref, "", l1, lInf);

}

TEST(Reproducibility_DenseNet_121, Accuracy)

{

const string proto = findDataFile("dnn/DenseNet_121.prototxt", false);

const string model = findDataFile("dnn/DenseNet_121.caffemodel", false);

Mat inp = imread(_tf("dog416.png"));

inp = blobFromImage(inp, 1.0 / 255, Size(224, 224));

Mat ref = blobFromNPY(_tf("densenet_121_output.npy"));

Net net = readNetFromCaffe(proto, model);

net.setPreferableBackend(DNN_BACKEND_OPENCV);

net.setInput(inp);

Mat out = net.forward();

normAssert(out, ref);

}

TEST(Test_Caffe, multiple_inputs)

{

const string proto = findDataFile("dnn/layers/net_input.prototxt", false);

Net net = readNetFromCaffe(proto);

net.setPreferableBackend(DNN_BACKEND_OPENCV);

Mat first_image(10, 11, CV_32FC3);

Mat second_image(10, 11, CV_32FC3);

randu(first_image, -1, 1);

randu(second_image, -1, 1);

first_image = blobFromImage(first_image);

second_image = blobFromImage(second_image);

Mat first_image_blue_green = slice(first_image, Range::all(), Range(0, 2), Range::all(), Range::all());

Mat first_image_red = slice(first_image, Range::all(), Range(2, 3), Range::all(), Range::all());

Mat second_image_blue_green = slice(second_image, Range::all(), Range(0, 2), Range::all(), Range::all());

Mat second_image_red = slice(second_image, Range::all(), Range(2, 3), Range::all(), Range::all());

net.setInput(first_image_blue_green, "old_style_input_blue_green");

net.setInput(first_image_red, "different_name_for_red");

net.setInput(second_image_blue_green, "input_layer_blue_green");

net.setInput(second_image_red, "old_style_input_red");

Mat out = net.forward();

normAssert(out, first_image + second_image);

}

typedef testing::TestWithParam<tuple<std::string, Target> > opencv_face_detector;

TEST_P(opencv_face_detector, Accuracy)

{

std::string proto = findDataFile("dnn/opencv_face_detector.prototxt", false);

std::string model = findDataFile(get<0>(GetParam()), false);

dnn::Target targetId = (dnn::Target)(int)get<1>(GetParam());

Net net = readNetFromCaffe(proto, model);

Mat img = imread(findDataFile("gpu/lbpcascade/er.png", false));

Mat blob = blobFromImage(img, 1.0, Size(), Scalar(104.0, 177.0, 123.0), false, false);

net.setPreferableBackend(DNN_BACKEND_OPENCV);

net.setPreferableTarget(targetId);

net.setInput(blob);

// Output has shape 1x1xNx7 where N - number of detections.

// An every detection is a vector of values [id, classId, confidence, left, top, right, bottom]

Mat out = net.forward();

Mat ref = (Mat_<float>(6, 7) << 0, 1, 0.99520785, 0.80997437, 0.16379407, 0.87996572, 0.26685631,

0, 1, 0.9934696, 0.2831718, 0.50738752, 0.345781, 0.5985168,

0, 1, 0.99096733, 0.13629119, 0.24892329, 0.19756334, 0.3310290,

0, 1, 0.98977017, 0.23901358, 0.09084064, 0.29902688, 0.1769477,

0, 1, 0.97203469, 0.67965847, 0.06876482, 0.73999709, 0.1513494,

0, 1, 0.95097077, 0.51901293, 0.45863652, 0.5777427, 0.5347801);

normAssertDetections(ref, out, "", 0.5, 1e-5, 2e-4);

}

INSTANTIATE_TEST_CASE_P(Test_Caffe, opencv_face_detector,

Combine(

Values("dnn/opencv_face_detector.caffemodel",

"dnn/opencv_face_detector_fp16.caffemodel"),

Values(DNN_TARGET_CPU, DNN_TARGET_OPENCL)

)

);

TEST(Test_Caffe, FasterRCNN_and_RFCN)

{

std::string models[] = {"VGG16_faster_rcnn_final.caffemodel", "ZF_faster_rcnn_final.caffemodel",

"resnet50_rfcn_final.caffemodel"};

std::string protos[] = {"faster_rcnn_vgg16.prototxt", "faster_rcnn_zf.prototxt",

"rfcn_pascal_voc_resnet50.prototxt"};

Mat refs[] = {(Mat_<float>(3, 7) << 0, 2, 0.949398, 99.2454, 210.141, 601.205, 462.849,

0, 7, 0.997022, 481.841, 92.3218, 722.685, 175.953,

0, 12, 0.993028, 133.221, 189.377, 350.994, 563.166),

(Mat_<float>(3, 7) << 0, 2, 0.90121, 120.407, 115.83, 570.586, 528.395,

0, 7, 0.988779, 469.849, 75.1756, 718.64, 186.762,

0, 12, 0.967198, 138.588, 206.843, 329.766, 553.176),

(Mat_<float>(2, 7) << 0, 7, 0.991359, 491.822, 81.1668, 702.573, 178.234,

0, 12, 0.94786, 132.093, 223.903, 338.077, 566.16)};

for (int i = 0; i < 3; ++i)

{

std::string proto = findDataFile("dnn/" + protos[i], false);

std::string model = findDataFile("dnn/" + models[i], false);

Net net = readNetFromCaffe(proto, model);

net.setPreferableBackend(DNN_BACKEND_OPENCV);

Mat img = imread(findDataFile("dnn/dog416.png", false));

resize(img, img, Size(800, 600));

Mat blob = blobFromImage(img, 1.0, Size(), Scalar(102.9801, 115.9465, 122.7717), false, false);

Mat imInfo = (Mat_<float>(1, 3) << img.rows, img.cols, 1.6f);

net.setInput(blob, "data");

net.setInput(imInfo, "im_info");

// Output has shape 1x1xNx7 where N - number of detections.

// An every detection is a vector of values [id, classId, confidence, left, top, right, bottom]

Mat out = net.forward();

normAssertDetections(refs[i], out, ("model name: " + models[i]).c_str(), 0.8);

}

}} // namespace

opencv/modules/dnn/test/test_caffe_importer.cpp at master · pythonmjs/opencv · GitHub

Expand file tree

Breadcrumbs

test_caffe_importer.cpp

Latest commit

History

Breadcrumbs

test_caffe_importer.cpp

File metadata and controls