Comments (2)
CSautier
commented on August 19, 2024
At the end of the pretraining, for the provided weights with minkunet, the training loss was ~2.7 and the validation loss around 1 points higher.
The PPKT training only reached ~3.5 training loss as the objective is harder.
from slidr.
Stephanie-Shen324
commented on August 19, 2024
Thank you! I can confirm that the pretraining results are reproducible!
from slidr.
Related Issues (20)
- SLIC instead of 2D segmentation HOT 1
- Object detection experiments HOT 2
- PPKT pretrain model
- The calculation method of mAP in object detection experiment HOT 4
- detection on kitti using Minkowski SR-Unet HOT 3
- problems of Semantic segmentation HOT 5
- problem of the randomness of dectection experiment
- Nuscenes dataset selection for downstream task of semantic segmentation HOT 1
- About the the number of superpixels HOT 4
- How to use this project to complete the distillation of target detection method HOT 1
- Maybe a Bug: Missing Feature Normalize in VoxelNet HOT 3
- Could you please share the visualised code? HOT 2
- Random initialization in linear probing HOT 1
- One confusing conv layer in Res16UnetBase
- Can not reproduce the results in PV-RCNN for object detection. Voxel size different? HOT 1
- Downstream Object Detection Experiments HOT 2
- Setting of the fraction of the training labels HOT 2
- Can't pickle local object 'PretrainDataModule.train_dataloader.<locals>.<lambda>' HOT 1
- Object detection experiments HOT 1
- None
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 slidr.