dcy0577

Hi @oliverholworthy , I observed that since transformers 4.35.0, they removed the use_cuda_amp, and the amp was entirely migrated to Accelerate: https://github.com/huggingface/transformers/issues/27760 Do you think we can remove it from...

I've reviewed the clm masking code, and I'm little confused about this line here: https://github.com/NVIDIA-Merlin/Transformers4Rec/blob/625897c3f55135342dbe53c32b7650a8ecb86c75/transformers4rec/torch/masking.py#L319 I would like to know, what is the purpose of removing the last padding item...

anyway, I changed some code in `apply_mask_to_inputs` of clm masking: ``` def apply_mask_to_inputs_CLM( self, inputs: torch.Tensor, mask_schema: torch.Tensor, training: bool = False, testing: bool = False, ) -> torch.Tensor: if...

I got the same error as well. @suyee97 Could you please share where to load model class and how? And if I use the code from [notebook 02](https://github.com/NVIDIA-Merlin/Transformers4Rec/blob/main/examples/getting-started-session-based/02-session-based-XLNet-with-PyT.ipynb) to save...

I think this line of code need to be removed: https://github.com/NVIDIA-Merlin/Transformers4Rec/blob/d0cce61b988a1e923545f94ac22499fb57928d18/transformers4rec/torch/masking.py#L298 As solution just use the mask_label from `predict_all()` above. And I think the reason why current code somehow works...

Hello, are there any updates regarding this issue? @rnyak @SPP3000

> I think you should use the 2D CNN to predict all the features from the images, lift to 3D and save the feature augmented point clouds to disk. Then,...

Hi Max, thanks again for your advice. I got some questions regarding labels when go deep into your code. 1. In scannet2d3d dataset, you use `seg_label = self.nyu40_to_scannet[seg_label].astype(np.int64)` to map...

> This seems weird indeed. Have you made sure that the input data is always the same? Maybe you can write a unit test with some dummy data which is...