Chia-Lun Hsu
Hi @mileyan, Thanks for sharing the amazing work. I am curious about the `_build_volume_2d3` function in line 118 of anynet.py. https://github.com/mileyan/AnyNet/blob/83badc75af596e76edce67e4917ba4fbacbb7c1d/models/anynet.py#L118 Why `batch_disp = batch_disp - batch_shift.float()` and not `batch_disp...
Modify `gwc_volumed` to `gwc_volume`.
Based on pytorch docs, the parameter "labels" of add_pr_curve() should be ground truth data. But in Line 141, class_labels append our own predictions. Therefore, I substitute "labels" for "predicted".
As stated in [issue 229](https://github.com/mapillary/inplace_abn/issues/229), I contribute the implementation to check Pillow version. If the version of Pillow >= 8.3.0, the `_PALETTE` list must consist of all channels for one...
I try to test picture as below shown but get a strange result not like the result of [issue 49](https://github.com/mapillary/inplace_abn/issues/49#issuecomment-418132607). Therefore, I try to find the bug of `test_vistas_single_gpu.py`. In...
Hi authors, Thanks for your amazing work. I have a question about scale of camera pose. I use ZED camera to collect data and compare camra pose of ZED and...