flownet2-tf
flownet2-tf copied to clipboard
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Hi Sampepose, Many thanks for your flownet2 model implementation. Currently, I can use the pre-traiend model to generate the optical-flow image. Is there any demo that we can use the...
Hi.At first,thank you four your wonderful work.I want to use this project to deal with a video,I have split the video into frames,then I want to call the function of...
Dear all, I have an issue trying to compile the code with tensorflow 1.4. I already solve the problem of cuda_config.h missing, looking at a solved issue. Here is the...
Two typical **ERROR**s while running **make -j8**. 1. ~/.local/lib/python3.6/site-packages/tensorflow/include/absl/strings/string_view.h(496): error: constexpr function return is non-constant 2. ~/.local/lib/python3.6/site-packages/tensorflow/include/tensorflow/core/util/cuda_device_functions.h(532): error: calling a constexpr __host__ function("imag") from a __device__ function("CudaAtomicAdd") is not allowed....
Hi, does anyone (plan to) port the current version of flownet to Tensorflow 2.x? We would ne very lucky, if you share your contribution here. Cheers, Roman
The error I'm facing - ``` src/ops/preprocessing/kernels/data_augmentation.cu.cc:7:53: fatal error: tensorflow/core/util/cuda_kernel_helper.h: No such file or directory compilation terminated. Makefile:62: recipe for target 'preprocessing' failed make: *** [preprocessing] Error 1 ```
Firstly, after I finished the compile with adding the "-NDEBUG " to CFLAGS , i meet the problem " xxxxxxx/correlation.so: **undefined symbol: **_ZTIN10tensorflow8OpKernelE****" when i want to run the Inference....
I am unable to download trained models using download.sh. I am getting following error `Resolving s3.us-east-2.amazonaws.com (s3.us-east-2.amazonaws.com)... 52.219.104.210 Connecting to s3.us-east-2.amazonaws.com (s3.us-east-2.amazonaws.com)|52.219.104.210|:443... connected. WARNING: cannot verify s3.us-east-2.amazonaws.com's certificate, issued by...
@sampepose Thank you for creating this amazing repository! **Main question**: I would like to know why do we need `flow = predict_flow2 * 20.0` (line 107) in `flownet_s.py`? In the...