potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-31 08:13:04 +04:00
Code Packages Releases Wiki Activity

Merge pull request #21910 from zihaomu:fast_conv_ARM

Browse Source 
DNN: Accelerating convolution

* Fast Conv of ARM, X86 and universal intrinsics.

* improve code style.

* error fixed.

* improve the License

* optimize memory allocated and Adjust the threshold.

* change FasterRCNN_vgg16 to 2GB memory.
This commit is contained in:
Zihao Mu
2022-07-01 18:03:15 +08:00
committed by GitHub
parent b91f173680
commit 59b870a87a
11 changed files with 3286 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/dnn/test/test_caffe_importer.cpp
+2 -2
View File
@@ -653,7 +653,7 @@ TEST_P(opencv_face_detector, Accuracy)
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);
normAssertDetections(ref, out, "", 0.5, 1e-4, 2e-4);
}
// False positives bug for large faces: https://github.com/opencv/opencv/issues/15106
@@ -695,7 +695,7 @@ TEST_P(Test_Caffe_nets, FasterRCNN_vgg16)
#if defined(OPENCV_32BIT_CONFIGURATION) && defined(HAVE_OPENCL)
CV_TEST_TAG_MEMORY_2GB, // utilizes ~1Gb, but huge blobs may not be allocated on 32-bit systems due memory fragmentation
#else
(target == DNN_TARGET_CPU ? CV_TEST_TAG_MEMORY_1GB : CV_TEST_TAG_MEMORY_2GB),
CV_TEST_TAG_MEMORY_2GB,
#endif
CV_TEST_TAG_LONG,
CV_TEST_TAG_DEBUG_VERYLONG