ArsenLuca

Results 14 issues of ArsenLuca

It seem Mean Shift is not used in the algorithm

@AnjieZheng Would you please release the pretrained model on ImageNet?

When I use the following image as input, the algorithm meets with a memory error in function int EDLineDetector::EDline(image_int8u_p image, LineChains &lines, bool smoothed) It seems to be a memory...

When I run :python experiments/deeplab/deeplab_train_test.py --cfg experiments/deeplab/cfgs/deeplab_resnet_v1_101_voc12_segmentation_base.yaml It failed with information: Called with argument: Namespace(cfg='experiments/deeplab/cfgs/deeplab_resnet_v1_101_voc12_segmentation_base.yaml', frequent=10) {'CLASS_AGNOSTIC': True, 'MXNET_VERSION': 'mxnet', 'SCALES': [(360, 600)], 'TEST': {'BATCH_IMAGES': 1, 'test_epoch': 12}, 'TRAIN': {'BATCH_IMAGES':...

@itijyou Could you please give the scripts for training the model "voc_rna-a1_cls21_s8_ep-0001.params"(80.84% mIoU)? Thanks

I tried to re-implement the semantic segmentation experiment but found that coco images with .png annotations are included in train++.lst. So how can I get the .png annotations?

Would you please share the shufflenet v2 x1.0 pretrained model? @Randl

1. 使用libopencv_imgproc.a编译时,resize报错: ``` opencv-mobile-4.5.1-android/sdk/native/staticlibs/arm64-v8a/libopencv_imgproc.a(resize.cpp.o): In function `(anonymous namespace)::interpolationLinear::getCoeffs(int, int*, (anonymous namespace)::fixedpoint32*)': resize.cpp:(.text._ZN12_GLOBAL__N_119interpolationLinearIsE9getCoeffsEiPiPNS_12fixedpoint32E+0x38): undefined reference to `cv::softdouble::softdouble(int)' resize.cpp:(.text._ZN12_GLOBAL__N_119interpolationLinearIsE9getCoeffsEiPiPNS_12fixedpoint32E+0x50): undefined reference to `cv::softdouble::operator+(cv::softdouble const&) const' resize.cpp:(.text._ZN12_GLOBAL__N_119interpolationLinearIsE9getCoeffsEiPiPNS_12fixedpoint32E+0x60): undefined reference to `cv::softdouble::operator*(cv::softdouble const&) const'...