Chenxi Huang

I don't know in `test.py lines 25: labels = make_variable(labels).squeeze_()`, why the lables need squeeze_(), and in 'pretrain.py' the labels don't need squeeze(). Maybe because the USPS dataset?

TypeError: zip argument #1 must support iteration

3

Did anyone get the same problem? Or did anyone has ideas? ```Traceback (most recent call last): File "scripts/train_rpn_3d.py", line 196, in main(sys.argv[1:]) File "scripts/train_rpn_3d.py", line 122, in main cls, prob,...

Something missing and how to convert kps into positions

3

Thanks for your excellent work. Can you give me some suggestions on how to convert **kps to positions**? Either relationship diagram or tutorial website is both Ok. I would appreciate...

There are two issues in latest pytorch. Does someone modify the project in latest pytorch?

3

When I do `./make.sh`, I got two issues: 1. **`ImportError: torch.utils.ffi is deprecated. Please use cpp extensions instead.`** It only change the `from torch.utils.ffi import create_extension` to `from torch.utils.cpp_extension import...

About small_gt_generator.py

1

First of all thanks for the great tool. But I got an error while using small_gt_generator.py. ``` File "tools/small_gt_generator.py", line 47, in main frame = file_data['frame_idx'] TypeError: 'TFRecordDatasetV2' object is...

Some confusion and a request

2

First of all, thank you for your excellent work. But I have some confusion and a request. 1.[kitti_dataset](https://github.com/amazon-research/progressive-coordinate-transforms/blob/main/lib/datasets/kitti_dataset.py) 27 lines of the code, you load label in 'ddmp', not the...

### What is the feature? Add scannetpp dataset, and update the processing for 3D object detection. ### Any other context? _No response_

How to implement some functions in Minkow in spconv? - MinkowskiEngine's convolution and deconvolution can pass in the coordinate parameter in forward - The SparseTensor of MinkowskiEngine has an attribute:...

The log does not contain the evaluated value. Can the epoch be made smaller? Which indicator represents Overall performance?

5

1. The log file only contains loss information, and the evaluation information is only printed in the terminal, which is very unfriendly for epoch 400 training. I have to test...

[P1] For left_padding in compute_metrics.py

2

When I training using llama-7b and math, I found that the sizes of left_pdding and intervention_locations did not match. This is because the tokenizer. bos_token_id=0 of llama-7b has multiple positions...