dd6fe347创建于 4月9日历史提交

文件	最后提交记录	最后更新时间
additional_need	!3710 【PyTorch】r2plus1d 修复fps计算 Merge pull request !3710 from wuxiankun/r21d	3 年前
configs	init	4 年前
docker	init	4 年前
docs	init	4 年前
docs_zh_CN	init	4 年前
mmaction	fix r2plus1d fps compute bug	3 年前
requirements	[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
test	!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
tools	!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
.gitignore	init	4 年前
.keep	init	4 年前
.pre-commit-config.yaml	init	4 年前
.pylintrc	init	4 年前
.readthedocs.yml	init	4 年前
LICENSE	init	4 年前
MANIFEST.in	init	4 年前
README.md	!5250 [众智][PyTorch]R(2+1)D模型部分公网地址整改 * 添加公网声明	2 年前
benchmark.py	init	4 年前
model-index.yml	init	4 年前
modelzoo_level.txt	init	4 年前
public_address_statement.md	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!7517	1 个月前
requirements.txt	init	4 年前
setup.cfg	init	4 年前
setup.py	init	4 年前
train.py	init	4 年前

R(2+1)d模型使用说明

Dataset Prepare

将处理好的数据集放到模型目录的 /data 文件夹下

Requirements

安装依赖

pip3.7 install ./requirements/requirements.txt
注：pillow建议安装较新版本， 与之对应的torchvision版本如果无法直接安装，可使用源码安装对应的版本，源码参考链接：https://github.com/pytorch/vision ,建议Pillow版本是9.1.0 torchvision版本是0.6.0

安装mmcv

git clone -b 1.3.9 https://github.com/open-mmlab/mmcv.git
cd mmcv
MMCV_WITH_OPS=1 pip install -e .  # 安装full版本

Before Train

更改底层文件,分别修改mmcv和apex的底层源码

# mmcv_need
/bin/cp -f additional_need/mmcv/distributed.py ../mmcv/mmcv/parallel/
/bin/cp -f additional_need/mmcv/dist_utils.py ../mmcv/mmcv/runner/
/bin/cp -f additional_need/mmcv/optimizer.py ../mmcv/mmcv/runner/hooks/
/bin/cp -f additional_need/mmcv/text.py ../mmcv/mmcv/runner/hooks/logger/

# apex_need
/bin/cp -f additional_need/amp/scaler.py ../apex/amp/

Train MODEL

单卡

# 精度
sh ./test/run_1p.sh

# 性能
sh ./test/run_1p_perf.sh

8卡

chmod a+x ./tools/dist_train.sh

# 精度
sh ./test/run_8p.sh

# 性能
sh ./test/run_8p_perf.sh

log文件位置

运行产生的log文件和模型的参数文件在项目目录的 work_dirs 文件夹下

公网地址说明

代码涉及公网地址参考 public_address_statement.md