Comments (3)
Hi @justinday123 , thanks for your feedback.
We fix the bug. It should work fine now. Please refer to #8 for more details.
from hop.
i got an another issue
Traceback (most recent call last):
File "tools/train.py", line 288, in
main()
File "tools/train.py", line 277, in main
train_model(
File "/workspace/hyundai/HoP/mmdet3d/apis/train.py", line 344, in train_model
train_detector(
File "/workspace/hyundai/HoP/mmdet3d/apis/train.py", line 319, in train_detector
runner.run(data_loaders, cfg.workflow)
File "/opt/conda/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 136, in run
epoch_runner(data_loaders[i], **kwargs)
File "/opt/conda/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 53, in train
self.run_iter(data_batch, train_mode=True, **kwargs)
File "/opt/conda/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 31, in run_iter
outputs = self.model.train_step(data_batch, self.optimizer,
File "/opt/conda/lib/python3.8/site-packages/mmcv/parallel/data_parallel.py", line 77, in train_step
return self.module.train_step(*inputs[0], **kwargs[0])
File "/opt/conda/lib/python3.8/site-packages/mmdet/models/detectors/base.py", line 248, in train_step
losses = self(**data)
File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/opt/conda/lib/python3.8/site-packages/mmcv/runner/fp16_utils.py", line 116, in new_func
return old_func(*args, **kwargs)
File "/workspace/hyundai/HoP/mmdet3d/models/detectors/base.py", line 60, in forward
return self.forward_train(**kwargs)
File "/workspace/hyundai/HoP/mmdet3d_plugin/hop/detectors/hop_bevdet.py", line 399, in forward_train
img_feats, pts_feats, depth, prev_feats = self.extract_feat(
File "/workspace/hyundai/HoP/mmdet3d_plugin/hop/detectors/hop_bevdet.py", line 184, in extract_feat
img_feats, depth, prev_feats = self.extract_img_feat(img, img_metas, **kwargs)
File "/workspace/hyundai/HoP/mmdet3d_plugin/hop/detectors/hop_bevdet.py", line 231, in extract_img_feat
bev_feat, depth = self.prepare_bev_feat(*inputs_curr)
File "/workspace/hyundai/HoP/mmdet3d_plugin/hop/detectors/hop_bevdet.py", line 142, in prepare_bev_feat
bev_feat, depth = self.img_view_transformer(
File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/workspace/hyundai/HoP/mmdet3d/models/necks/view_transformer.py", line 697, in forward
return self.view_transform(input, depth, tran_feat)
File "/workspace/hyundai/HoP/mmdet3d/models/necks/view_transformer.py", line 285, in view_transform
return self.view_transform_core(input, depth, tran_feat)
File "/workspace/hyundai/HoP/mmdet3d/models/necks/view_transformer.py", line 276, in view_transform_core
coor = self.get_lidar_coor(*input[1:7])
File "/workspace/hyundai/HoP/mmdet3d/models/necks/view_transformer.py", line 132, in get_lidar_coor
points = torch.inverse(post_rots).view(B, N, 1, 1, 1, 3, 3)
RuntimeError: CUDA error: operation not supported when calling cusparseCreate(handle)
how could i solve it?
i'm using CUDA 11.1
from hop.
Hi, the problem seems to be related to your environment. Maybe this link can be of help.
from hop.
Related Issues (17)
- Temporal BEV feature align HOT 2
- When will release code for HoP on BEVFormer? HOT 1
- 训练中得到0map HOT 5
- KeyError: 'ann_info'
- Segmentation Fault while inference over R50 Models HOT 1
- When will the SOTA model for nuScenes detection task be posted in model_zoo?
- Why is HoP useful even thought it is not used in inferring?
- Bevformer+HoP config,please HOT 2
- Pretrained weights for NuScenes detection HOT 1
- How to get the ground truth of history frames? HOT 2
- Ablation study of the bev feature at timestamp t-k HOT 3
- Does it work for 2 camera views?
- Why does the channel reduction can prune the height info ?
- Can Hop used in PETR model? HOT 1
- Some Issues with Replication HOT 3
- Will open sota config on nuscenes benchmark ?
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 hop.