Comments (3)
If you will train (fine-tune) the resnet backbone during training your scene parsing network instead of fixing it, you can directly using the existing model pretrained with zero padding. Just change your nn.Conv2d to PartialConv2d. Their parameter numbers are the exactly same.
As long as you fine-tune it enough, it should not matter too much. This is also reflected in Kaiming's recent paper: Rethink ImageNet Pre-training. https://arxiv.org/abs/1811.08883
The segmentation experiments in the paper are also both using the pretrained weights with zero padding; but during the fine-tuning, one is using nn.Conv2d while the other is using PartialConv2d.
I will upload the pretrained weights of partial conv powered models soon.
from partialconv.
@liuguilin1225 Thanks. I will try it latter.
from partialconv.
@PkuRainBow The pretrained weights for VGG and ResNet networks with partial convolution based padding can be found here: https://www.dropbox.com/sh/t6flbuoipyzqid8/AACJ8rtrF6V5b9348aG5PIhia?dl=0
from partialconv.
Related Issues (20)
- Pretrained Checkpoints
- Demo not working HOT 12
- About train details
- papaer arch partial conv num question HOT 1
- Problem with Pretrained checkpoints
- Some comments about code of PartialConv2d HOT 4
- How to test the code with the different ratios mask? HOT 1
- About mask training dataset HOT 5
- Doesn't take 2 channel mask as input HOT 2
- Online Demo down? HOT 7
- Pytorch export trace/script
- Blurry results and non-recoverable facial features in CelebA-HQ dataset HOT 3
- image inpainting error
- I can't import models in main.py
- About args: multi-channel for image inpainting
- partial con
- Inpainting demo not working HOT 2
- The updating of mask HOT 1
- 2d and 3d implementation differences
- Map at edges is peaking (PartialConv2d implementation + fix) HOT 6
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 partialconv.