Comments (7)
You can add +runner.validation_index=all
to generate the full validation set.
from magicdrive.
Hello, I have improved the test config according to your method, but I found that although I can infer the entire test set, the generated images still do not meet the standards of Nuscenes. In Nuscenes' samples, the images exist as a single view, but the generated images are concatenated with 6 views. At the same time, the file names used for indexing the generated images are different from those in the Nuscenes dataset samples. How can I replace the images in the old dataset with images from the new dataset?
from magicdrive.
For FID, please track progress at #32
from magicdrive.
Dear author, thank you very much for your reply. However, if we only calculate FID, I think we can use the test generated ori_img and gen_img to calculate it. But compared to this, I am more concerned about how to apply it to object detection networks such as BEVFusion in the future. The current generation method seems to only be able to concatenate 6 views together. May I ask if I need to use the generated images to create a new dataset, do I need to split all the images in the test generated validation set myself and convert them into the format of nuscenes validation set?
from magicdrive.
if we only calculate FID, I think we can use the test generated ori_img and gen_img to calculate it.
You can calculate like this if you want, but this is not the standard process and we never adopt this in any case.
The current generation method seems to only be able to concatenate 6 views together.
If you look into the code, you will find out that each image is generated separately and then stitch together. You can change the code for your purpose.
from magicdrive.
Okay, thank you for your reply. I will try it out.
from magicdrive.
Close for now. If you have other follow-ups, feel free to re-open.
from magicdrive.
Related Issues (20)
- Bug in nuscenes_t_dataset HOT 1
- Your Loss is NaN HOT 9
- What's the meaning of several parametes in default.yaml? HOT 1
- How to use the pretrained weight "SDv1.5mv-rawbox_2023-09-07_18-39_224x400" to launch another train? HOT 3
- Adding objects HOT 1
- version of some packpages HOT 2
- Code for Quantitative Evaluation (Image Branch) HOT 1
- The training time for the entire nuscenes dataset is too long HOT 2
- Machine and time query request HOT 1
- Problems about training on one mechine 8 A100 HOT 7
- How long train 61 frames? HOT 5
- Can 61 frames pretrained weight be released? HOT 3
- Running on local URL: http://0.0.0.0:7860 To create a public link, set `share=True` in `launch()`. HOT 2
- docker images for magicdrive HOT 1
- ERROR: Could not build wheels for xformers, which is required to install pyproject.toml-based projects HOT 2
- Question about initialize class_tokens HOT 1
- AttributeError: 'NoneType' object has no attribute 'update' HOT 5
- cannot import name 'visualize_camera' from 'mmdet3d.core.utils'
- No velocity on *** in sample: ***
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 magicdrive.