文件最后提交记录最后更新时间
init 4 年前
!1224 [众智][PyTorch]pytorch模型torch版本判断由1.8.1改为1.8 * 众智pytorch模型torch版本判断由1.8.1改为1.8 3 年前
!1224 [众智][PyTorch]pytorch模型torch版本判断由1.8.1改为1.8 * 众智pytorch模型torch版本判断由1.8.1改为1.8 3 年前
!4671 【fix】批量修改模型python版本,兼容环境上的python3.8版本 * fix python version 3 年前
init 4 年前
init 4 年前
fix link validity Co-authored-by: frozenleaves<914814442@qq.com> # message auto-generated for no-merge-commit merge: !7517 merge master into master fix link validity Created-by: frozenn Commit-by: frozenleaves Merged-by: ascend-robot Description: ## Motivation Please describe the motivation of this PR and the goal you want to achieve through this PR. ## Modification Please briefly describe what modification is made in this PR. ## Self-test (Optional) If modifications to this PR may cause/fix function/accuracy/performance DTSs/issues, a self-inspection record needs to be attached. ## BC-breaking (Optional) If there are compatibility issues, such as dependencies on cann/torch_npu versions, they need to be explained in the PR. ## Checklist **Before PR**: - [ ] The new code needs to comply with the Clean Code specification. - [ ] The PR content is self-checked, and the expression can be clear and the writing standardized **After PR**: - [ ] CLA has been signed and all committers have signed the CLA in this PR. - [ ] The ci-pipeline is passed, Code Check is passed. See merge request: Ascend/ModelZoo-PyTorch!75171 个月前
init 4 年前
init 4 年前
!7376 optimize public_address_statement.md Merge pull request !7376 from 王凯宇/master 8 个月前
[众智][PyTorch]整改模型中的requirements.txt文件,删除torch,apex Signed-off-by: bailang <bailang12@h-partners.com> 3 年前
README.md

RefineNet

This repository is an NPU implementation of the "RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation", referring to https://github.com/DrSleep/refinenet-pytorch

Requirements

See requirements.txt

  • PyTorch
  • torchvision
  • Numpy 1.15.1
  • Pillow 9.1.0
  • h5py 2.8.0
  • tqdm 4.28.1
  • h5py 3.4.0
  • opencv-python 3.4.4.19
  • albumentations 0.4.5 Note: pillow recommends installing a newer version. If the corresponding torchvision version cannot be installed directly, you can use the source code to install the corresponding version. The source code reference link: Suggestion the pillow is 9.1.0 and the torchvision is 0.6.0
  • install densetorch as follow:
 git clone https://github.com/DrSleep/DenseTorch
 cd ./DenseTorch
 python setup.py install

Training

The processed VOC dataset can be downloaded from Download with extraction code: vnhb (about 9 G), put it in ./VOC. Or, you can download it by:

bash load_data.sh

The training common:

# 1p train perf
bash test/train_performance_1p.sh 

# 8p train perf
bash test/train_performance_8p.sh

# 8p train full
bash test/train_full_8p.sh

# finetuning
bash test/train_finetune_1p.sh

In the first running, it requires time to downloaded the model pre-trained on ImageNet. Or you can manually download it by:

cd ~
mkdir .torch
mkdir .torch/models
cd .torch/models
wget https://download.pytorch.org/models/resnet101-5d3b4d8f.pth 
mv resnet101-5d3b4d8f.pth 101_imagenet.pth.tar

Log path: ./log/

Saved model path: ./model/

Training result

IOU FPS NPU_nums BS/NPU AMP_type
78.56 25.56 1 16 O2
77.34 159.46 8 8 O2

Citation

RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation
Guosheng Lin, Anton Milan, Chunhua Shen, Ian Reid
In CVPR 2017

Statement

For details about the public address of the code in this repository, you can get from the file public_address_statement.md