Comments (5)
using spconv 1.0 not spconv 1.1
from openpcdet.
Every time I try to install the spconv 1.0 library , the 1.1 version gets installed. I do what the documentation says and then I find in the ./dist this file (spconv-1.1-cp36-cp36m-linux_x86_64.whl) which is for installing the 1.1 version. I don't know why this happens for me. I need the spconv 1.0 version but I can't get it.
from openpcdet.
In the spcnv git repo you cloned, use this command which will let the git repo go to version 1:
git checkout 8da6f96
Then continue with the same installation instructions you did.
from openpcdet.
new version has this question using spconv1.1.
2020-06-25 09:14:28,205 INFO **********************Start training cfgs/kitti_models/pv_rcnn(ttt)********************** epochs: 0%| | 0/16 [00:00<?, ?it/s] train: 0%| | 0/3712 [00:00<?, ?it/s] epochs: 0%| | 0/16 [00:00<?, ?it/s] Traceback (most recent call last): File "/home/jty/pcdet/pvrcnn/OpenLidarPerceptron/tools/train.py", line 166, in <module> main() File "/home/jty/pcdet/pvrcnn/OpenLidarPerceptron/tools/train.py", line 158, in main merge_all_iters_to_one_epoch=args.merge_all_iters_to_one_epoch File "/home/jty/pcdet/pvrcnn/OpenLidarPerceptron/tools/train_utils/train_utils.py", line 92, in train_model dataloader_iter=dataloader_iter File "/home/jty/pcdet/pvrcnn/OpenLidarPerceptron/tools/train_utils/train_utils.py", line 18, in train_one_epoch batch = next(dataloader_iter) File "/home/jty/anaconda3/envs/pointpillars/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 819, in __next__ return self._process_data(data) File "/home/jty/anaconda3/envs/pointpillars/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 846, in _process_data data.reraise() File "/home/jty/anaconda3/envs/pointpillars/lib/python3.7/site-packages/torch/_utils.py", line 369, in reraise raise self.exc_type(msg) AssertionError: Caught AssertionError in DataLoader worker process 0. Original Traceback (most recent call last): File "/home/jty/anaconda3/envs/pointpillars/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop data = fetcher.fetch(index) File "/home/jty/anaconda3/envs/pointpillars/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/jty/anaconda3/envs/pointpillars/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in <listcomp> data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/jty/pcdet/pvrcnn/OpenLidarPerceptron/pcdet/datasets/kitti/kitti_dataset.py", line 388, in __getitem__ data_dict = self.prepare_data(data_dict=input_dict) File "/home/jty/pcdet/pvrcnn/OpenLidarPerceptron/pcdet/datasets/dataset.py", line 94, in prepare_data data_dict=data_dict File "/home/jty/pcdet/pvrcnn/OpenLidarPerceptron/pcdet/datasets/processor/data_processor.py", line 87, in forward data_dict = cur_processor(data_dict=data_dict) File "/home/jty/pcdet/pvrcnn/OpenLidarPerceptron/pcdet/datasets/processor/data_processor.py", line 65, in transform_points_to_voxels voxels, coordinates, num_points = voxel_generator.generate(points) File "/home/jty/anaconda3/envs/pointpillars/lib/python3.7/site-packages/spconv/utils/__init__.py", line 164, in generate or self._max_voxels, self._full_mean) File "/home/jty/anaconda3/envs/pointpillars/lib/python3.7/site-packages/spconv/utils/__init__.py", line 65, in points_to_voxel assert block_filtering is False
from openpcdet.
new version has this question using spconv1.1.
2020-06-25 09:14:28,205 INFO **********************Start training cfgs/kitti_models/pv_rcnn(ttt)********************** epochs: 0%| | 0/16 [00:00<?, ?it/s] train: 0%| | 0/3712 [00:00<?, ?it/s] epochs: 0%| | 0/16 [00:00<?, ?it/s] Traceback (most recent call last): File "/home/jty/pcdet/pvrcnn/OpenLidarPerceptron/tools/train.py", line 166, in <module> main() File "/home/jty/pcdet/pvrcnn/OpenLidarPerceptron/tools/train.py", line 158, in main merge_all_iters_to_one_epoch=args.merge_all_iters_to_one_epoch File "/home/jty/pcdet/pvrcnn/OpenLidarPerceptron/tools/train_utils/train_utils.py", line 92, in train_model dataloader_iter=dataloader_iter File "/home/jty/pcdet/pvrcnn/OpenLidarPerceptron/tools/train_utils/train_utils.py", line 18, in train_one_epoch batch = next(dataloader_iter) File "/home/jty/anaconda3/envs/pointpillars/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 819, in __next__ return self._process_data(data) File "/home/jty/anaconda3/envs/pointpillars/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 846, in _process_data data.reraise() File "/home/jty/anaconda3/envs/pointpillars/lib/python3.7/site-packages/torch/_utils.py", line 369, in reraise raise self.exc_type(msg) AssertionError: Caught AssertionError in DataLoader worker process 0. Original Traceback (most recent call last): File "/home/jty/anaconda3/envs/pointpillars/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop data = fetcher.fetch(index) File "/home/jty/anaconda3/envs/pointpillars/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/jty/anaconda3/envs/pointpillars/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in <listcomp> data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/jty/pcdet/pvrcnn/OpenLidarPerceptron/pcdet/datasets/kitti/kitti_dataset.py", line 388, in __getitem__ data_dict = self.prepare_data(data_dict=input_dict) File "/home/jty/pcdet/pvrcnn/OpenLidarPerceptron/pcdet/datasets/dataset.py", line 94, in prepare_data data_dict=data_dict File "/home/jty/pcdet/pvrcnn/OpenLidarPerceptron/pcdet/datasets/processor/data_processor.py", line 87, in forward data_dict = cur_processor(data_dict=data_dict) File "/home/jty/pcdet/pvrcnn/OpenLidarPerceptron/pcdet/datasets/processor/data_processor.py", line 65, in transform_points_to_voxels voxels, coordinates, num_points = voxel_generator.generate(points) File "/home/jty/anaconda3/envs/pointpillars/lib/python3.7/site-packages/spconv/utils/__init__.py", line 164, in generate or self._max_voxels, self._full_mean) File "/home/jty/anaconda3/envs/pointpillars/lib/python3.7/site-packages/spconv/utils/__init__.py", line 65, in points_to_voxel assert block_filtering is False
while spconv1.0 is ok
from openpcdet.
Related Issues (20)
- The training phase of train.py shows epochs: 0it [00:00, ?it/s]. HOT 1
- Low Acc on 3D task, in Custom datasets. HOT 2
- training with pvrcnn losses not decreasing as seen in the tensor-board !!!! HOT 2
- pointpillar_newaugs.yaml can not use. HOT 2
- Adding MPPNet support for NuScenes HOT 2
- Visualizing the results
- Error when running demo.py HOT 2
- About BaseBEVBackbone HOT 1
- How to get validation loss and display it in Tensorboard HOT 2
- Abnormal demo.py result using nuscenses dataset pre-trained models HOT 2
- Ensemble or test-time augmentation? HOT 1
- free(): double free detected in tcache 2 HOT 1
- questions about GETTING_STARTED.md
- 'EasyDict' object has no attribute 'BACKUP_DB_INFO' HOT 1
- What should we set the overlap values for custom datasets? HOT 4
- TypeError: expected str, bytes or os.PathLike object, not NoneType
- `pillar_features` IndexError: too many indices for tensor of dimension 1
- Question about adam_onecycle optimizer HOT 1
- PV RCNN++ pretained model
- [Docs] A100算力加持!书生大模型实战营第3期全面升级,趣味闯关模式等你开启
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from openpcdet.