flownet2-tf
flownet2-tf copied to clipboard
sampepose
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Env: cuda: 9.0 cudnn: 9.0 tensorflow: 1.8.0 Ubuntu 16.04 I followed the instructions in Wxjwjj's post. Still get errors. File "/home/charles/Libraries/anaconda2/envs/tensorflow1.2/lib/python2.7/site-packages/tensorflow/python/framework/load_library.py", line 64, in load_op_library None, None, error_msg, error_code) tensorflow.python.framework.errors_impl.NotFoundError:...
hello，centos7+cuda10，make error，and I don't know how to solve it. Can you help me? Thanks! /usr/local/cuda-10.0/../cuda/include/cuda_fp16.h(96): error: invalid redeclaration of type name "__half" /usr/local/cuda-10.0/bin/..//include/cuda_fp16.hpp(147): here /usr/local/cuda-10.0/../cuda/include/cuda_fp16.h(100): error: invalid redeclaration of type...
I can do inference with Tensorflow 1.13 + python 3.5.2 and get reasonable output with pre-trained model. However, when I trained a model with flying chair dataset, the result didn't...
Hello, I'm appreciate your work!! But when I replicate your code, I have met a error: fatal error: cuda/cuda_config.h: No such file or directory, while I run 'make all'. How...
From my observation, you modified the data augmentation code from the caffe version. But it still cannot run on GPU. How can I do it by GPU or multi-CPU? Thanks.
Hi, Has anyone tried to compile on Windows? I just want to test on a couple of images. Thanks
Enev: cuda: 9.0 cudnn: 9.0 tensorflow: 1.8.0 Ubuntu16.04 Makefile modified ```bash CUDA_HOME := /home/ /wuxj/cuda-9.0 CGPUFLAGS: add your tensorflow library eg: -L /home//.local/lib/python2.7/site-packages/tensorflow -ltensorflow_framework ``` Headers modified (from error) `vi...
https://github.com/sampepose/flownet2-tf/blob/18f87081db44939414fc4a48834f9e0da3e69f4c/src/dataset_configs.py#L95 does this mean that excepting geometric augmentation, only Gaussian noise is applied to the first image? And are the Gaussian noise of the two images exactly the same?
Hi all, Can I compile in anaconda on Windows ? I am getting the following errors: (tensorflow3) D:\CSM\Spring2019\tensorflow\flownet2-tf>make all 1 [main] make 20384 find_fast_cwd: WARNING: Couldn't compute FAST_CWD pointer. Please...
> physical GPU (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:49:00.0, compute capability: 6.1) max flow: 44159.5898 flow range: u = -12376.481 .. 9278.501 v = -767.675...
