Comments (3)
Firstly you need to use RRM (one-step) to generate pseudo labels of all training data, then you can use them to train any fully segmentation model (FCN), such as deeplab, PSPnet and so on. when I train the FCN, i.e., deeplab-v1 and v2, I use the official code and all the settings are the same with their papers. If you do not want the pre-trained model on COCO, I suggest you to train another FCN such as deeplab v3 or v3+. If you find the init model without COCO pre-trained using official code, please let me know, because I also think it is not a good choice.
from rrm.
@zbf1991 Thank you for your explanation. I have gotten a good result from official deeplabv2 with VGG16 and deeplabv3 is helpful. But, I cannot get a good result from official deeplabv2 with resnet101 without loading pretrain weight on MS COCO. Here is where I stuck. Do you train deeplabv2-resnet101 without any pretrained weights such as ImageNet?
Without COCO pretrain weight, I do not think people can get a good result on deeplabv2-resnet101 with the same setting in deeplabv2 paper. For example, in deeplabv2-resnet101, they freeze the batch normalization in each layer so people must load pretrain weight if they use the same setting of deeplabv2. In addition, they set different learning rates to different layers, so people may get a poor result if they train deeplabv2-resnet101 without any pretrain weight. Or, maybe I am wrong.
Another question, which official code of deeplabv2-resnet101 do you use? I think there are two official codes. One is Caffe model and another is Tensorflow(deeplabv3). Do you use its init.caffemodel? I try to delete it before training. However, the performance of deeplabv2-resnet101 became very worse.
from rrm.
I used caffe-version and use its init.caffemodel
from rrm.
Related Issues (20)
- About the dataloader
- About the dense energy loss
- How can I get the mIOU results? HOT 1
- computer crash HOT 2
- outputs are all black images HOT 1
- Unable to reproduce results HOT 5
- Did you use COCO pretrain weight when training DeepLabv2-resnet101 ? HOT 2
- Can people get the result in the paper if they train it from 'init'? HOT 3
- How do you calculate mIoU? HOT 1
- Loss NAN HOT 2
- The Energy loss HOT 2
- Could you share pretrained weights using google drive?
- Would you tell me where is the function of evaluation in the RRM_infer.py? HOT 4
- why I could not use the RRM_10000.pth in PSA project?
- What's the difference between the AAAI'20 work and the extended work? HOT 1
- zero-size array to reduction operation maximum which has no identity HOT 2
- How can I use my dataset to train the model? HOT 1
- permutohedral.hpp:75: Warning 325: Nested struct not currently supported (Neighbors ignored) HOT 1
- 跑通了infer_RRM.py后只有结果图并没有显示关于mIOU指标的结果,请问需要如何操作?
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 rrm.