Comments (7)
You should change scale_factor
in ida
accordingly.
from bevdepth.
You should change
scale_factor
inida
accordingly.
ida_aug_conf = { 'resize_lim': (0.386, 0.55), 'final_dim': final_dim, 'rot_lim': (-5.4, 5.4), 'H': H, 'W': W, 'rand_flip': True, 'bot_pct_lim': (0.0, 0.0), 'cams': [ 'CAM_FRONT_LEFT', 'CAM_FRONT', 'CAM_FRONT_RIGHT', 'CAM_BACK_LEFT', 'CAM_BACK', 'CAM_BACK_RIGHT' ], 'Ncams': 6, }
The final_dim map is assigned final_dim variable , Is scale_factor you mean resize_lim ?
from bevdepth.
Yes, I mean resize_lim
.
from bevdepth.
Yes, I mean
resize_lim
.
If input size is changed to 896x1600, How to set the resize_lim value corresponding?
from bevdepth.
You may change to [0.95, 1.25].
from bevdepth.
You may change to [0.95, 1.25].
Ok, I will try it. What is the reasons that to set [0.95, 1.25] ? It is an experimental parameter?
from bevdepth.
You may change to [0.95, 1.25]
If final_dim=(900,1600), how much should resize_lim be set to? I have tried resize_lim=(1.0,1.0) and (1.0, 1.25), but none of them work. May I ask how the range of resize_lim can be found?
from bevdepth.
Related Issues (20)
- MatrixVT config issue HOT 1
- training speed very slow HOT 7
- Confused about Support efficient voxel pooling v2 HOT 4
- what's the meaning of the "use_cbgs" ,thx HOT 1
- can I just use keyframes? Can only keyframes be detected and constraints on depth?Thx HOT 5
- whatis the meaning of the 'sweep_idxes', thanks HOT 1
- Config issue about MatrixVT HOT 2
- train error about MatrixVT config HOT 2
- Why use the "binary_cross_entropy" to compute the depth loss? Thx HOT 1
- depth supervision good for ate and map but not for the others HOT 2
- about the 'code_weight' in exp file
- MatrixVT exps HOT 5
- Training time is super long for MatrixVT HOT 3
- about geom_xyz HOT 1
- question about get_proj_mat()? HOT 1
- Why sweep_lidar_info use calibrated_sensor_token of cam_data in gen_info ? HOT 1
- When can we have Matrix VT model? HOT 4
- BEV grid resolution HOT 4
- training speed HOT 1
- I use a single A100 to train this model, which spends 10 hours for single epoch. My batch size is 32.
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.