Comments (3)
Hi, can you reproduce the reported number using the provided checkpoint?
If you can reproduce results by checkpoint, the performance gap can be caused by the training randomness.
The performances reported in config files are obtained without TTA.
from crn.
@SunLuyue26 Hello,
I encoutered some errors while trying to compile the CRN Checkpoint. I see that you came to measure its performance could you help me please solve this issue.
from crn.
Hello, I replicated the experiment following the experimental setup in your paper's appendix and your code, but did not achieve the results mentioned in your code comments. Is there any additional configuration, such as Test Time Augmentation (TTA)? Or what could be the reason for this discrepancy? Looking forward to your reply, thank you very much!
have you solved the problem?i also can't reproduce the results
from crn.
Related Issues (20)
- CUDA error during training HOT 1
- invalid box type during evaluation HOT 1
- Resnet 101 with depth estimation >= 100m of distance does not converge HOT 2
- Visualization HOT 2
- Training duration and GPU memory HOT 1
- CUDA error: operation not supported when calling `cusparseCreate(handle)` on 4090 GPU HOT 3
- Radar percpective view HOT 1
- Latest cuda version adaptation HOT 1
- Looking forward to the BEV segmentation code HOT 1
- Bounding boxes offset HOT 12
- Inference on a video HOT 2
- can not see the details of MFA module, there is only binary file HOT 2
- can't reproduce the r50 HOT 9
- FileNotFoundError: [Errno 2] No such file or directory: 'data/nuScenes/samples/RADAR_FRONT/n015-2018-07-18-11-07-57+0800__RADAR_FRONT__1531883530440378.pcd'
- how can i strat to train your model?
- Why does resnet101.py not exist in the project file?
- python [EXP_PATH] --amp_backend native -b 4 --gpus 4 in this ,what the EXP_PATH represent? And i can use the nuscenes-mini to train? HOT 1
- Change to single input
- Error When Training Model on nuScenes Dataset: MisconfigurationException Related to bfloat16 and PyTorch Version
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 crn.