Issues
- 14
Can not download weights?
#62 opened by heiheiya - 4
Can't download pretrained weights
#105 opened by srzhao - 3
- 16
No file named 'correlation.so'
#65 opened by KarelZhang - 11
- 2
Can't download pretrained weights from aws
#104 opened by jhhan45 - 0
- 10
Different error when running test: Undefined symbol: _ZN10tensorflow3PadERKN5Eigen9GpuDeviceEPKfiiiiiiPf
#93 opened by fperezgamonal - 1
No OpKernel was registered...
#107 opened by YoungJ-Baek - 3
make error
#108 opened by jujuhe - 1
- 1
- 10
There was a problem in successive calling to the function that generated the optical flow
#75 opened by TaowzzZ - 3
Is flownet2-tf cuda 10 compatible?
#74 opened by jiapei100 - 0
Update of FN2 to TF2.x?
#109 opened by romanseidel - 0
- 3
InvalidArgumentError (see above for traceback): Restoring from checkpoint failed. This is most likely due to a mismatch between the current graph and the graph from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error: No OpKernel was registered to support Op 'Correlation' with these attrs. Registered devices: [CPU], Registered kernels: device='GPU' [[Node: FlowNet2/FlowNetCSS/FlowNetCS/FlowNetC/Correlation = Correlation[kernel_size=1, max_displacement=20, pad=20, stride_1=1, stride_2=2](FlowNet2/FlowNetCSS/FlowNetCS/FlowNetC/conv3/lrelu/add, FlowNet2/FlowNetCSS/FlowNetCS/FlowNetC/conv3_1/lrelu/add)]]
#68 opened by mengyaaa - 0
Which tensorflow version to use?
#103 opened by pushkalkatara - 2
- 11
Unable to download the pre-trained models
#86 opened by t-naveenkumar - 0
- 1
NotFoundError:\.\ops\build\downsample.so not found
#99 opened by hfutfl - 0
ImportError: No module named 'matplotlib._path'
#98 opened by hfutfl - 0
make error
#97 opened by jijiangyan - 0
- 0
About augmentation
#95 opened by xianshunw - 2
Compile the makefile on windows
#64 opened by ADHARACSM - 0
I got a very large number of the flow?
#94 opened by bestzxp - 16
nvcc not found
#73 opened by lovekittynine - 1
error: no module named png
#92 opened by IRIS00123 - 1
If I want to test the optical flow map between three consecutive frames in the video, how can I modify the code?
#91 opened by weilanShi - 0
- 6
- 1
Variable FlowNet2/FlowNetCSS/FlowNetCS/FlowNetC/conv1/weights already exists, disallowed
#89 opened by vkumar1997 - 3
CUDA and CUDNN installed by Anaconda
#88 opened by AliKafaei - 2
undefined symbol: _ZN10tensorflow12OpDefBuilder4AttrENSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEE
#87 opened by 3bhady - 10
InvalidArgumentError (see above for traceback): Restoring from checkpoint failed. This is most likely due to a mismatch between the current graph and the graph from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint.
#81 opened by fighttiger25 - 4
very poor performance
#84 opened by fighttiger25 - 3
error: expression must have a constant value
#85 opened by crazyblacker - 1
Correlation may not calculate correctly
#83 opened by Guoxs - 0
- 2
Train my own datasets
#71 opened by MengyunQ - 0
Solution to"Trained Own Data"
#77 opened by PoojaGhaywate - 7
Cannot compile on ubuntu 18.04
#76 opened by MostafaSalem - 1
how to test with videos?
#72 opened by LakyTT - 0
- 0
- 4
undefined symbol: __cudaPushCallConfiguration
#67 opened by mengyaaa - 4
constexpr & __shfl errors
#66 opened by Hjorth2 - 2
Getting png error
#63 opened by ADHARACSM