Johannes Meyer

Fix the problem of "Incompatible shapes" described in #260

3

Fixes the problem defined in the issue #260

With boundingboxes a = [0, 0, 10, 10] b = [1, 1, 11, 11] The intersection area of both boxes is from point [1, 1] to [10, 10]. The size...

As described in #185 I get a similar problem. I fixed it by applying the boolean_mask cls_flatten not only to the bbox_flatten tensor but also the bbox_offset_targets_labeled. Thus, the elements...

It appears to me as if one can safely remove "ARG github_token" from the Dockerfile(s). If one specifies the github_token via a ``--build-arg`` the Dockerfile fails to build with the...

Fixes the problem in #1 by adding a new error message if no files are present in the dataset directory.

Custom panel is slow on first render

3

Hi,I created a custom panel in order to visualize some data from ROS in a more convenient way. However, I am struggling with the problem that at first render the...

Code to reproduce NYU RGBD results / input pipeline

4

Hi, thanks for your repo. It would be nice if you could provide the code / the input pipeline which you used to run the NYU RGB-D experiments as well...

Error 404 when cloning repository

1

Hi, I am getting the following error when performing git clone on the repository ``` git clone https://github.com/tsunghan-wu/ReDAL Cloning into 'ReDAL'... remote: Enumerating objects: 193, done. remote: Counting objects: 100%...

Training aborts when saving checkpoint after epoch 1

3

Hi, I am currently trying to train the network on the S3DIS dataset using the ``td3d_is_s3dis-3d-5class`` config. The training works fine for all training steps in epoch 1. At the...

Training of OA-CNN with custom data fails on flat surfaces

3

Hi, first of all thanks for the nice repository. I am trying to train various models on custom data. However, with OA-CNN I encounter the problem below. ``` Traceback (most...