NotImplementedError #1
Comments
Hi, sorry for the late reply. Could you have a look at this issue? Hope it helps: |
|
I had the exact same problem with him and didn't find a solution |
1 similar comment
|
I had the exact same problem with him and didn't find a solution |
Hi, have you already tried this? |
|
|
看起来没问题，等进度条完成就好了。 |
|
运行训练命令时我是可以正常训练的，但是python eval.py就会一直卡在百分之零 |
啊？没见过这个问题诶……你有更多的线索吗？不然我想不到有什么解决方法 |
|
我现在也不是很清楚，正在进行训练，等结束了我再看一看 |
|
想知道python eval.py大概会运行多久？ |
|
总结一下我遇到的问题和解决方法：（1）NotImplementedError：这个问题应该是因为数据集和预训练模型的路径没有放在PointCloudSegmentation目录下，我模仿作者的文件路径存放后解决了这个问题（2）训练在第31个epoch停止，python eval.py会卡住，我想这两个是一个原因导致，参考作者之前提供的环境文件，把pip下没有安装或者版本不同的更改以后解决了问题 |
您好，请问（1）的NotImplementedError是应该具体改什么路径呢 |
when I tried to run eval.py based on the PointGroup-PAPER.pt you provided, a mistake happened:
(treeins) (base) root@d8fc5cfcc777:/home/ForAINet-main/PointCloudSegmentation# python eval.py
/opt/conda/envs/treeins/lib/python3.8/site-packages/MinkowskiEngine/init.py:36: UserWarning: The environment variable
OMP_NUM_THREADSnot set. MinkowskiEngine will automatically setOMP_NUM_THREADS=16. If you want to setOMP_NUM_THREADSmanually, please export it on the command line before running a python script. e.g.export OMP_NUM_THREADS=12; python your_program.py. It is recommended to set it below 24.warnings.warn(
[2024-04-22 10:32:56,977][torch_points3d.trainer][INFO] - DEVICE : cuda
[2024-04-22 10:33:09,479][torch_points3d.metrics.model_checkpoint][INFO] - Loading checkpoint from /home/ForAINet-main/PointCloudSegmentation/checkpoint/PointGroup-PAPER.pt
Traceback (most recent call last):
File "eval.py", line 13, in main
trainer = Trainer(cfg)
File "/home/ForAINet-main/PointCloudSegmentation/torch_points3d/trainer.py", line 48, in init
self._initialize_trainer()
File "/home/ForAINet-main/PointCloudSegmentation/torch_points3d/trainer.py", line 90, in _initialize_trainer
self._dataset: BaseDataset = instantiate_dataset(self._checkpoint.data_config)
File "/home/ForAINet-main/PointCloudSegmentation/torch_points3d/datasets/dataset_factory.py", line 46, in instantiate_dataset
dataset = dataset_cls(dataset_config)
File "/home/ForAINet-main/PointCloudSegmentation/torch_points3d/datasets/panoptic/treeins.py", line 629, in init
self.test_dataset = dataset_cls(
File "/home/ForAINet-main/PointCloudSegmentation/torch_points3d/datasets/segmentation/treeins.py", line 491, in init
super().init(root, grid_size, *args, **kwargs)
File "/home/ForAINet-main/PointCloudSegmentation/torch_points3d/datasets/segmentation/treeins.py", line 187, in init
super(TreeinsOriginalFused, self).init(root, transform, pre_transform, pre_filter)
File "/opt/conda/envs/treeins/lib/python3.8/site-packages/torch_geometric/data/in_memory_dataset.py", line 60, in init
super().init(root, transform, pre_transform, pre_filter)
File "/opt/conda/envs/treeins/lib/python3.8/site-packages/torch_geometric/data/dataset.py", line 83, in init
self._download()
File "/opt/conda/envs/treeins/lib/python3.8/site-packages/torch_geometric/data/dataset.py", line 140, in _download
self.download()
File "/home/ForAINet-main/PointCloudSegmentation/torch_points3d/datasets/panoptic/treeins.py", line 562, in download
super().download()
File "/home/ForAINet-main/PointCloudSegmentation/torch_points3d/datasets/segmentation/treeins.py", line 517, in download
super().download()
File "/opt/conda/envs/treeins/lib/python3.8/site-packages/torch_geometric/data/in_memory_dataset.py", line 50, in download
raise NotImplementedError
NotImplementedError
I downloaded the FOR-instance dataset and placed it in the correct location ,but I still get this issue, how did you fix it?
The text was updated successfully, but these errors were encountered: