IamMegatron

Results 73 comments of IamMegatron

pretrain model

Can you provide the pre-trained model? @HzDmS Do you have any progress with the pre-trained model? @gao-shi @BlueWinters

undefined reference to `cv::FAST` when build using cmake and make

@FedorovPavel thanks for your reply. What version is the `OpenCV-android-sdk` you use ?

undefined reference to `cv::FAST` when build using cmake and make

@FedorovPavel Thanks. Now I also AS to build this project with `gradle`, and it works. But I would like to know how do compile the app code using `cmake and...

undefined reference to `cv::FAST` when build using cmake and make

@FedorovPavel Thank you too.

Can you tall me which version of ndk ?

@ReallyHardToName Do you build it successfully? Can you help me with the [problem](https://github.com/muziyongshixin/ORB-SLAM2-based-AR-on-Android/issues/6)? Thanks.

make -j16 and get error: ‘DeformableConvolutionParameter’ was not declared in this scope

meet the same error.

the size larger than 64x64 does work for nemo model

@AliaksandrSiarohin Thanks for your reply. 1. I use `resize`. For example, for driving image `test/213_deliberate_smile_1.png`, I modify some codes in `frames_dataset.py` to : ``` video_array = np.moveaxis(image, 1, 0) video_array...

stuck in `Loading ./pretrained_models/FlowNet2_checkpoint.pth.tar`

@nbei V100. Now it works when I install correct version of torch0.4.0 by `pip install https://download.pytorch.org/whl/cu90/torch-0.4.0-cp36-cp36m-linux_x86_64.whl` as I use cuda9.0. Still thanks.

Cuda version and Operating System?

torch 0.4.0 cuda 9.0 python3.6 work.

kitti test do not have test labels

I am also curious about this