621 Commits (2bb44454a548b931153b7bb304bc42fa9329a4ef)

Author SHA1 Message Date
AlexeyAB 2bb44454a5 Minor fix 7 years ago
AlexeyAB 7762372e5b Compilation fix for OpenCV 3.4.x and Jetson Xavier. 7 years ago
AlexeyAB 7ee4135910 Fix OpenCV compilation. maxpool_layer on GPU uses cuDNN. 7 years ago
erick 38801979b2 Classifier now is working. The file softmax_layer.c was outdated 7 years ago
AlexeyAB 24b60456c7 Version 0.2.5 - fixed ) 7 years ago
AlexeyAB 0cf56d1ccf Version 0.2.5 ) 7 years ago
AlexeyAB c02216120b Compile fix 7 years ago
AlexeyAB 5cc2a7e20d Added mistakes checking 7 years ago
AlexeyAB 67f33ff5dc Another compile fix 7 years ago
AlexeyAB e92c635f35 Compile fix 7 years ago
AlexeyAB c0e2512af2 Activation improvement, more robust timer. 7 years ago
AlexeyAB e203ab9046 Minor fixes 7 years ago
AlexeyAB 7dd97537fb XNOR-net tiny-yolo_xnor.cfg ~2x faster than cuDNN on CUDA (nVidia GPU Maxwell) 7 years ago
AlexeyAB 0224ba3d0d Compile fix 7 years ago
AlexeyAB 03e95320a1 XNOR coalesced memory access, and avoid bank conflicts 7 years ago
AlexeyAB ca43bbdaae Fixed openmp bugs for XNOR 7 years ago
AlexeyAB c0e01fd63c Test for XNOR-conv on CUDA 7 years ago
AlexeyAB 57e878b4f9 another compile fix 7 years ago
AlexeyAB b141f85cab Compile fix 7 years ago
AlexeyAB 007878393f Temporary Slow implementation of XNOR on CUDA (shared_memory) 7 years ago
AlexeyAB c4a9e3422e Temporary implementation of XNOR on CUDA 7 years ago
AlexeyAB 9753b72aeb temp fix, don't use it 7 years ago
AlexeyAB 18d5e4f39c Fixed yolov3-tiny_xnor.cfg 7 years ago
AlexeyAB 31b6b0bad3 XNOR-net 4x acceleration on CPU for yolov2-tiny - 22 FPS (CPU Core i7 6700K) 7 years ago
AlexeyAB f606b5456e XNOR-net 21 FPS on CPU yolov2-tiny.cfg 7 years ago
AlexeyAB 8436251a05 maxpool_layer on CPU uses AVX2 and OpenMP 7 years ago
AlexeyAB e1801f5aec Added trim() function for label paths 7 years ago
AlexeyAB 552207d6f0 Minor fix 7 years ago
AlexeyAB c2a8cc2ad3 Fix GCC compile 7 years ago
AlexeyAB bd8a5c3eb1 Different checks for AVX and FMA 7 years ago
AlexeyAB f007f7b90e Fixes for MSVS2017 7 years ago
AlexeyAB 7f9145729c Another one fix for MSVS2017 7 years ago
AlexeyAB e548489182 Fix for MSVS2017 for _mm256_extract_epi64 and _mm256_extract_epi32 7 years ago
AlexeyAB f92b20580a Some fixes for AVX support on CPU 7 years ago
AlexeyAB b1dddf02cc Fixed AVX compiled bug 7 years ago
AlexeyAB 1f2155b886 Experiments 7 years ago
AlexeyAB a9fef1bd66 Bug fixes. Tested im2col_cpu_custom_transpose - bad way. 7 years ago
AlexeyAB 3e856ec04e Optimized: transpose 7 years ago
AlexeyAB d59a172a1d Fixed wrong labels 7 years ago
AlexeyAB 5c876bb918 Another one fix 7 years ago
AlexeyAB 3baf534a2d Compile error fix 7 years ago
AlexeyAB d6162af210 Optimized on CPU: gemm_bin, im2col, activation, transpose 7 years ago
AlexeyAB a284a7da8d Try to use avx_hs() - slow and requires alignment 4096 bits < (l.size*l.size*l.c) 7 years ago
AlexeyAB 0a326e7afe XNOR-net on CPU AVX2 7 years ago
AlexeyAB e6c97a53a7 Maxpool fixes 7 years ago
AlexeyAB 043289426b max pool layer is fixed 7 years ago
AlexeyAB b8e6e80c6d Added spatial Yolo v3 yolov3-spp.cfg 7 years ago
AlexeyAB dfbec7ea2b PascalVOC label scripts are updated 7 years ago
vinjn 08957081d4 Expose YOLODLL_API void top_k() 7 years ago
Tino Hager 2c711de013 optimize performance detect 7 years ago