Comments (4)
Hi,
You should train the segmentation backbone before training the refinement. The guideline for training backbone is already here https://github.com/VinAIResearch/MagNet#training-backbone-networks
from magnet.
I made some attempts to retrain the backbone and refinement. As the model performance after training, the best_mIou of the backbone and the epoch_IoU of the refinement model are around 0.6 and 0.25, respectively. But the epoch_IoU can go up to 0.9 when the refinement model is retrained with the pretrained backbone. I think the difference is caused by the backbone not being trained well. So I try different random seed, batch_size, learning rate, and distributed training to get backbone to work well, but all failed. I guess that some tricks are used in the training process. Could the checkpoint.pth.tar or training log be made publiced?
from magnet.
Recently, I separated the validate part from backbone/train.py to evaluate the performance of pretrained backbone. Through comparing the performance of backbone with pretrained and retrained parameters, it would be cleared where the abnormalities occured in the process of retraining on deepglobe dataset. The fpn and hrnet_ocr backbone with pretrained parameters have been evaluated. The best_Iou of retrained fpn and hrnet_ocr are 0.61, 0.63 learned from the training log, while the best_Iou of pretrained fpn and hrnet_ocr are unknown. As the evaluate result, the mIou of pretrained fpn and hrnet_ocr are 0.07 and 0.61. The 0.61 mIou of pretrained hrnet_ocr could prove the upper best_Iou limit of retrained fpn is around 0.6. The retraining of fpn backbone seems work well. However, in the retraining of refinement model on deepglobe dataset, the epoch_IoU only rises to 0.3 with 0.61 best_iou retrained fpn, while the epoch_Iou with 0.07 mIou pretrained fpn could go up to 0.9; in the retraining of refinement model on cityscapes dataset, the epoch_IoU could rise to 0.87 with 0.63 best_iou retrained hrnet_ocr, and the epoch_Iou with pretrained hrnet_ocr could go up to 0.93. The performance between pretrained and retrained fpn is opposite to the evaluate result, but the performance between pretrained and retrained hrnet_ocr is matching with the evaluate result. Have you ever encountered this difference?
from magnet.
Hi,
It would help if you break down your issues into multiple questions. I'm still not understanding your problem here.
Thank you.
from magnet.
Related Issues (20)
- prepare_cityscapes.sh
- Some problems about Gleason dataset HOT 3
- How to train without using pretrained weight weights? HOT 4
- some details about the results of experiment
- Training details on methods in Table 4 HOT 2
- How to apply train.py trained parameters to test.py? HOT 1
- Patches and refined locations HOT 9
- the epoch_IoU of retrained refinement network can only up to 0.35 on deepglobe dataset HOT 4
- # of required GPUs to reproduce Best outputs HOT 10
- RuntimeError: shape '[1, 1, -1, 508, 508]' is invalid for input of size 16451136 HOT 1
- input to the model HOT 1
- RuntimeError: shape '[1, 1, -1, 508, 508]' is invalid for input of size 16451136 HOT 2
- a small question about Deepglobe dataset HOT 1
- Why the input_size of backbone is set to the number of 508×508 on the DeepGlobe dataset experiment? HOT 1
- About the result of deepglobe dataset HOT 5
- demo.py: error: --sub_batch_size HOT 2
- About the Gleason dataset
- Questions about Binary Semantic Segmentation HOT 2
- the inputs of the "refinement model" are different between train.py and test.py 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 magnet.