adhara123007

training prototxt file reading only limited entries in lmdb file

4

Dear Sir, I installed your software. I have 50000 entries in my lmdb file but when I run the training prototxt file, it reads only 13000 files. Can you please...

Need for compressing the label by 20

2

Dear Sir, "We scale the ground truth flow by 20 and downsample it to obtain the supervision signals at different levels" is written in your paper . What was the...

Hi, While training the network on my own dataset, the losses ires_disp_loss0, ires_disp_loss1 and ires_disp_loss2 looks same. Is this seem reasonable ? 

Get following error when compiling

5

Cannot compile. Get the following error... nvcc -g -std=c++11 -I`python -c "import tensorflow; print(tensorflow.sysconfig.get_include())"` -I"/usr/local/cuda-9.0/include" -DGOOGLE_CUDA=1 -D_MWAITXINTRIN_H_INCLUDED -D_FORCE_INLINES -D__STRICT_ANSI__ -D_GLIBCXX_USE_CXX11_ABI=0 -c -gencode=arch=compute_30,code=sm_30 FlowNet2_src/ops/preprocessing/kernels/data_augmentation.cu.cc -x cu -Xcompiler -fPIC -o FlowNet2_src/ops/build/data_augmentation.o /home/adhara/anaconda3/envs/tf2/lib/python3.6/site-packages/tensorflow/include/unsupported/Eigen/CXX11/../../../Eigen/src/Core/MathFunctions.h(1255):...