RRM - GitLite

KO | EN

gitlite — search

#react #ai #typescript #llm #nodejs #java #windows #awesome #cli #vue #awesome-list #pytorch #openai #open-source

RRM

(★ 97)

Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach

File Explorer

Download Latest Version (.zip)

- misc.xml
- modules.xml
- psa_zbf.iml
- vcs.xml
- workspace.xml
- DenseEnergyLoss.cpython-36.pyc
- - resnet38d.cpython-36.pyc
- resnet38d.py
- RRM(attention).py
- RRM(noMultiScale).py
- RRM.py
- - imutils.cpython-36.pyc
  - myTool.cpython-36.pyc
  - pyutils.cpython-36.pyc
  - torchutils.cpython-36.pyc
- imutils.py
- myTool.py
- pyutils.py
- torchutils.py
- - data.cpython-36.pyc
- cls_labels.npy
- data.py
- test.txt
- train.txt
- train_aug(id).txt
- train_aug.txt
- val(id).txt
- val.txt
- - bilateralfilter.cpp
  - bilateralfilter.hpp
  - bilateralfilter.i
  - bilateralfilter.py
  - bilateralfilter_wrap.cxx
  - numpy.i
  - permutohedral.cpp
  - permutohedral.hpp
  - setup.py
DenseEnergyLoss.py
infer_RRM(attention).py
infer_RRM.py
README.md
train_from_cls_weight(attention).py
train_from_cls_weight(ori).py
train_from_cls_weight.py
train_from_init(attention).py
train_from_init.py

# Installation Guide

1. Get the code

git clone https://github.com/zbf1991/RRM

Downloads the entire project code from GitHub to your computer.

cd RRM

Moves into the project folder you just downloaded.

2. Python

Easy Recommended

Prerequisites

Git Needed to download the project code from GitHub.
Python 3 On Windows, be sure to check 'Add Python to PATH' during installation.

⚠️ This is a large repository, so this method may point to an internal sub-package rather than the actual core product. Check the full README as well.

pip install .

Installs the package published on PyPI directly — no need to clone the source.

python <실행할 파일명>.py # README에서 정확한 실행 파일명을 확인하세요

Runs the Python script (or module).

✅ If it runs without errors and prints output in the terminal, it worked.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach
AAAI 2020 (Spotlight).

The code of the new extended work now is available. In the further, I will try to merge these two works so that making the whole project is more elegant.

Paper of the extended work will come soon.

This project is based on [Regularized loss](https://github.com/meng-tang/rloss) and [PSA](https://github.com/jiwoon-ahn/psa).

## Before Running, build python extension module:
```
cd wrapper/bilateralfilter
swig -python -c++ bilateralfilter.i
python setup.py install
```
More details please see [here](https://github.com/meng-tang/rloss/tree/master/pytorch)

## Download pretrained models to ./netWeights:
Google: due to the coronavirus outbreak in China, I will upload models after I can enter my lab. But you can
download “[ilsvrc-cls_rna-a1_cls1000_ep-0001.params]” and “[res38_cls.pth]” from [here](https://github.com/jiwoon-ahn/psa).

[BaiduYun](https://pan.baidu.com/s/15AwO6Jn9vQQtThE02QOefw)

[ilsvrc-cls_rna-a1_cls1000_ep-0001.params] is an init pretained model.
 
 [res38_cls.pth] is a classification model pretrained on VOC 2012 dataset.
 
 [RRM_final.pth] is the final model (AAAI).
 
 [RRM(attention)_final.pth] is the final model of the new extended work (64.7 mIoU on Pascal Voc 2012 val set).

## Training of the New Extended Work:

### Training from init model:
you need 4 GPUs and the pretrained model [ilsvrc-cls_rna-a1_cls1000_ep-0001.params]:
```
python train_from_init(attention).py --voc12_root /your/path/VOCdevkit/VOC2012
```
 
### Training from a pretrained classification model:
you only need 2 GPU and the pretrained model [res38_cls.pth]
```
python train_from_cls_weight(attention).py --IMpath /your/path/VOCdevkit/VOC2012/JPEGImages
```

## Training of the AAAI Work:
I suggest that it is better to use the 2nd method due to lower computing costs.
### Training from init model:
you need 4 GPUs and the pretrained model [ilsvrc-cls_rna-a1_cls1000_ep-0001.params]:
```
python train_from_init.py --voc12_root /your/path/VOCdevkit/VOC2012
```
 
### Training from a pretrained classification model:
you only need 1 GPU and the pretrained model [res38_cls.pth]
```
python train_from_cls_weight.py --IMpath /your/path/VOCdevkit/VOC2012/JPEGImages
```
## Inferencing of the extended work:
you need 1 GPU and the final model [RRM(attention)_final.pth]:
```
python infer_RRM.py --IMpath /your/path/VOCdevkit/VOC2012/JPEGImages
```
## Inferencing of the AAAI work:
you need 1 GPU and the final model [RRM_final.pth]:
```
python infer_RRM.py --IMpath /your/path/VOCdevkit/VOC2012/JPEGImages