王加华 comments

Results 21 comments of


                                            王加华

compilation errors in tf_ops folders

@ccu1tn Actually, you need to change the tensorflow path and CUDA path in ` tf_xxx_compile.sh`.

compilation errors in tf_ops folders

Usually ~/anaconda/envs/env_name/lib/python2.7/site-packages/tensorflow if using Anaconda. > Hi, > could you tell me what the commands are to retrieve both the TensorFlow and CUDA paths in my computer? I'm using Ubuntu...

Which Version of Tensorflow is this running on?

Hi @zsyzzsoft @tiwarikaran , I have difficulty setting the environment. My virtual environment variants are listed here: `` python 3.6.13 tensorflow-gpu 1.14.0 CUDA: 10.2 `` There is an error when...

Which Version of Tensorflow is this running on?

Thanks, It now works when I change `--compiler-options \'-fPIC -D_GLIBCXX_USE_CXX11_ABI=0` to `--compiler-options \'-fPIC -D_GLIBCXX_USE_CXX11_ABI=1` [here](https://github.com/zsyzzsoft/co-mod-gan/blob/master/dnnlib/tflib/custom_ops.py#L130), since I use gcc 5.4. No need to switch CUDA version.

Error in SO-NET code

Downgrading torch version to 1.1 works for me. My env, python=3.7, torch=1.1, cuda=10.0.

Error in SO-NET code

Hi, @amiltonwong, did you compile the index_max operation successfully?

Error in SO-NET code

Then I don't know the reason, sorry couldnot help.

RuntimeError: The shape of the mask [32, 8732] at index 0 does not match the shape of the indexed tensor [279424, 1] at index 0

> What file should be updated? You may try to update your file `/home/.../ssd.pytorch/layers/modules/multibox_loss.py`, and add one line as @LZP4GitHub said above.

How can we use more classes?

You may change filter numbers before the YOLO layer.

How can we use more classes?

Hey dude, @UsmannK , are you in Lyft Autonomous Driving Competition? I tried to apply this repo on Lyft dataset( converted to Kitti format), but the score is really low,...