AttributeError: module 'numpy' has no attribute 'float' in DeepIM-PyTorch

[spoonytripod]

Hi!
I encountered an error while running demo.sh in DeepIM-PyTorch. The error seems to be related to the deprecation of np.float in NumPy 1.20 and later.

Error message:

./experiments/scripts/demo.sh

• set -e
• export PYTHONUNBUFFERED=True
• PYTHONUNBUFFERED=True
• export CUDA_VISIBLE_DEVICES=0
• CUDA_VISIBLE_DEVICES=0
• ./tools/test_images.py --gpu 0 --imgdir data/demo/ --meta data/demo/meta.yml --color '*color.png' --network flownets --pretrained data/checkpoints/ycb_object/flownets_ycb_object_20objects_color_self_supervision_epoch_10.checkpoint.pth --dataset ycb_object_test --cfg experiments/cfgs/ycb_object_flow.yml
  Traceback (most recent call last):
  File "./tools/test_images.py", line 26, in
  from datasets.factory import get_dataset
  File "/home/cilab/DeepIM-PyTorch/tools/../lib/datasets/init.py", line 10, in
  from .dex_ycb import DexYCBDataset
  File "/home/cilab/DeepIM-PyTorch/tools/../lib/datasets/dex_ycb.py", line 25, in
  from utils.cython_bbox import bbox_overlaps
  File "bbox.pyx", line 9, in init cython_bbox
  File "/home/cilab/miniconda3/envs/py38-nvlabs/lib/python3.8/site-packages/numpy/init.py", line 305, in getattr
  raise AttributeError(former_attrs[attr])
  AttributeError: module 'numpy' has no attribute 'float'.
  np.float was a deprecated alias for the builtin float. To avoid this error in existing code, use float by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use np.float64 here.
  The aliases was originally deprecated in NumPy 1.20; for more details and guidance see the original release note at:
  https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations

real 0m2.687s
user 0m1.758s
sys 0m2.571s

Steps to reproduce:
Run the demo script: ./experiments/scripts/demo.sh

Environment Details:
OS: Ubuntu 22.04
Python Version: 3.8
NumPy Version: 1.24.4
CUDA Version: 11.7.r11.7
PyTorch Version: 2.0.1

Additional Information:
I attempted to fix the issue by modifying bbox.pyx at line 9:
DTYPE = np.float # Original
DTYPE = np.float64 # Modified

However, the same error persists. I would appreciate any guidance on resolving this issue.
Thank you!

[BigBuffa1o]

Can you help me upload the pretrained model and other files like post result that are destroyed by author or send to my email(1005617814@qq.com) ? that's very important to me , thank you so much!

[spoonytripod]

Can you help me upload the pretrained model and other files like post result that are destroyed by author or send to my email(1005617814@qq.com) ? that's very important to me , thank you so much!

Unfortunately, I am also trying to look for those files. As an alternative, I am attempting to use the files provided in the original implementation of the repository from https://github.com/liyi14/mx-DeepIM