Comments (17)
@yinchimaoliang Do you have any plan to release the config file and model shown on the detection leaderboard?
from bevdepth.
Hi! The input resolution is 640 x 1600, the backbone we use is ConvNext, the bev resolution is 256 x 256, we also use train and val split for training.
from bevdepth.
Hi, thanks for the info! I'll make sure to give it a try!
from bevdepth.
Hello, can you tell me which ConvNeXt architecture you guys use? Tiny, small base or large? Thanks!
from bevdepth.
Hi, @yinchimaoliang, I wonder if the data augmentation in your submission is the same one used in the r50 config? So the only differences are (I) image resolution (2) bev resolution (3) image backbone (4) trainval for test, right?
from bevdepth.
Hi! When the resolution of the input image is changed, the resize_lim
and final_dim
of ida should be changed accordingly.
from bevdepth.
Hi, @bluffish. BEVDepth-pure extends the BEVDepth by using ConvNeXt-base as backbone.
from bevdepth.
Hi, @yinchimaoliang thanks for your information. I am trying to use ConvNeXt but encountered OOM problem. I wonder if you adopt torch.utils.checkpoint to save your memory in the ConvNeXt backbone? If so, do you use it in the stage conv or also in the downsample layers ?Thanks!
from bevdepth.
Hi, @zehuichen123 , we didn't adopt torch.utils.checkpoint, we used V100 with a memory of 32GB, you can try it if you are using machines with smaller memory size.
from bevdepth.
Thanks! I am using V100 machine too. BTW, how did you set your batch size for each GPU as well as the learning rate? (since a batch size of 8 is impossible in this case)
from bevdepth.
Thanks! I am using V100 machine too. BTW, how did you set your batch size for each GPU as well as the learning rate? (since a batch size of 8 is impossible in this case)
The batch size for each card is set to 2, and we use 4 machines. Learning rate is 2e-4.
from bevdepth.
Got it! Thanks! 😊
from bevdepth.
Hi, @zehuichen123, we also encountered OOM problem. Did you solve this problem?
from bevdepth.
Thanks! I am using V100 machine too. BTW, how did you set your batch size for each GPU as well as the learning rate? (since a batch size of 8 is impossible in this case)
The batch size for each card is set to 2, and we use 4 machines. Learning rate is 2e-4.
@yinchimaoliang Did you use base lr = 2e-4 or final lr = 2e-4? I see in the code the basic learning rate for 64 samples per batch is set to 2e-4. I wonder if it is the same for 2 (batch size) * 4 (machine) * 8(gpu per machine)?
from bevdepth.
Also, I see from here that you uses dcn head in the submitted version to the test set leaderboard, which is not mentioned in this issue. I wonder if there is anything else we should pay attention to to reproduce the leaderboard results (other than (I) image resolution (2) bev resolution (3) image backbone (4) use both train/val set for training)?
Hi! When the resolution of the input image is changed, the
resize_lim
andfinal_dim
of ida should be changed accordingly.
For instance, what is the right value of resize_lim
and final_dim
of ida here?
from bevdepth.
Also, I have noticed ConvNeXT uses different drop_path_rate
for different architectures. What value did you use for drop_path_rate
?
from bevdepth.
Why does the author not answer these questions (by zeyuwang615)?? They are quite important T T
from bevdepth.
Related Issues (20)
- How to test after training??
- error: no instance of overloaded function "atomicAdd" matches the argument list HOT 5
- Unfreeze backbone network HOT 1
- Questions for BEV features and voxel pooling
- Welcome update to OpenMMLab 2.0
- Depth aggregation autocast HOT 2
- BEVDepth perform very bad when training with batch size 1! HOT 2
- Input type different & Memory usage during training
- Performance of MatrixVT HOT 3
- inference with depth gt HOT 1
- can't reproduce [bev_depth_lss_r50_256x704_128x128_24e_2key_ema]
- Deployment of BEVDepth on Nvidia board with onnx conversion
- error detected in the compilation of "/tmp/tmpxft_00005518_00000000-6_voxel_pooling_train_forward_cuda.cpp1.ii HOT 2
- mmcv mmdet mmseg 版本问题 HOT 3
- 推理速度
- what the accuracy of your depth map fusion model?
- Memory Peak
- How to deal with camera pixels without lidar point? HOT 1
- gen_info error
- Why Depthnet need take bda into account?
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 bevdepth.