Comments (4)
- This is an auxiliary loss (focal loss on vehicle centers) used by FIERY that I tried and left in. works fine without this
- After major cleanup of the code for release and trying to train mixed-precision this lr seems to be more stable
- These objects are not visible to the ego-vehicle and need to be filtered out for correctness
- If you take a look the dataset generation code can the missing index is pedestrian - we included this in the label set since it could be useful for future tasks
The config is accurate - i will check to make sure nothing diverged in the release
Thanks for the questions!
from cross_view_transformers.
Hello bradyz ! Many thanks for your response !
. 3. I understand that, I will clarify. My question is about how you evaluate. In your paper, to obtain the score in table 1, do you evaluate on all vehicles or only on visible vehicles ?
. 1. Ok this is as further experiments, the results in your paper were obtain using the Focal loss
. 2. I see, indeed it is a nice feature to be able to train with mixed-precision
. 4. Ok
from cross_view_transformers.
Table 1 is visible vehicles only - unfortunately almost all methods for this task evaluate slightly differently but I would argue this is the right way to do it
from cross_view_transformers.
Ok I better understand now, many thanks.
from cross_view_transformers.
Related Issues (20)
- How to segmentate road_segment and dynamic objects together ? HOT 1
- error training HOT 1
- How long does it take to train the model?
- Geometric reasoning in cross-view attention
- How to train this for segmenting more than 2 classes? HOT 1
- Question about camera extrinsics
- Question about the implementation of 'camera-aware positional encoding' part
- The labels of dataset Argoverse.
- loss function mutation when training
- When run [train.py] RuntimeError: unmatched '}' in format string HOT 2
- Discrepancy in the validation IOU values for Driveable Area segmentation HOT 14
- About setting1 HOT 1
- The label link is broken
- generating labels error : [OSError]: [Error 24] Too many open files HOT 1
- train error : urllib.error.URLError : <urlopen error Error instantiating 'cross_view_transformer.model.backbones.efficientnet.EfficientNetExtractor' : <urlopen error [Errno 111] Connection refused> ]
- Error executing job with overrides HOT 1
- no test.py
- about the model test
- Error running training (LR Scheduler) HOT 1
- 运行时出现以下错误
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 cross_view_transformers.