Skip to content

GitLab

Commit a68071f2 authored by dcuai's avatar dcuai
Browse files

Update README.md -dtk24.04.2

parent 2108983f
Show whitespace changes
Inline Side-by-side
Showing with 38 additions and 29 deletions
README.md
View file @ a68071f2
...@@ -24,11 +24,10 @@ X-Decoder 通过一个统一的解码器结构，将像素级、图像级和语 ...@@ -24,11 +24,10 @@ X-Decoder 通过一个统一的解码器结构，将像素级、图像级和语
此处提供[光源](https://www.sourcefind.cn/#/service-details)拉取docker镜像的地址与使用步骤，以及[光合](https://developer.hpccube.com/tool/)开发者社区深度学习库下载地址 此处提供[光源](https://www.sourcefind.cn/#/service-details)拉取docker镜像的地址与使用步骤，以及[光合](https://developer.hpccube.com/tool/)开发者社区深度学习库下载地址
``` ```
docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-centos7.6-dtk23.10-py38 docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-ubuntu20.04-dtk24.04.2-py3.10
docker run -it --shm-size=128G -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal:/opt/hyhal:ro --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name xdecoder_mmcv <your IMAGE ID> bash # <your IMAGE ID>为以上拉取的docker的镜像ID替换，本镜像为：ffa1f63239fc docker run -it --shm-size=128G -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal:/opt/hyhal:ro --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name xdecoder_mmcv <your IMAGE ID> bash # <your IMAGE ID>为以上拉取的docker的镜像ID替换
cd /path/your_code_data/xdecoder_mmcv cd /path/your_code_data/xdecoder_mmcv
pip install -r requirements/multimodal.txt -i https://mirrors.aliyun.com/pypi/simple/ pip install -r requirements/multimodal.txt -i https://mirrors.aliyun.com/pypi/simple/
pip install mmcv-2.0.1_gitfb7d8f3.abi0.dtk2310.torch2.1.-cp38-cp38-manylinux2014_x86_64.whl
pip install mmdet -i https://mirrors.aliyun.com/pypi/simple/ pip install mmdet -i https://mirrors.aliyun.com/pypi/simple/
git clone https://github.com/cocodataset/panopticapi.git git clone https://github.com/cocodataset/panopticapi.git
cd panopticapi cd panopticapi
...@@ -43,7 +42,6 @@ docker build --no-cache -t xdecoder:latest . ...@@ -43,7 +42,6 @@ docker build --no-cache -t xdecoder:latest .
docker run -it --shm-size=128G -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal:/opt/hyhal:ro --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name xdecoder_mmcv xdecoder bash docker run -it --shm-size=128G -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal:/opt/hyhal:ro --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name xdecoder_mmcv xdecoder bash
cd /path/your_code_data/xdecoder_mmcv cd /path/your_code_data/xdecoder_mmcv
pip install -r requirements/multimodal.txt -i https://mirrors.aliyun.com/pypi/simple/ pip install -r requirements/multimodal.txt -i https://mirrors.aliyun.com/pypi/simple/
pip install mmcv-2.0.1_gitfb7d8f3.abi0.dtk2310.torch2.1.-cp38-cp38-manylinux2014_x86_64.whl
pip install mmdet -i https://mirrors.aliyun.com/pypi/simple/ pip install mmdet -i https://mirrors.aliyun.com/pypi/simple/
git clone https://github.com/cocodataset/panopticapi.git git clone https://github.com/cocodataset/panopticapi.git
cd panopticapi cd panopticapi
...@@ -55,16 +53,17 @@ pip install e . ...@@ -55,16 +53,17 @@ pip install e .
关于本项目DCU显卡所需的特殊深度学习库可从[光合](https://developer.hpccube.com/tool/)开发者社区下载安装。 关于本项目DCU显卡所需的特殊深度学习库可从[光合](https://developer.hpccube.com/tool/)开发者社区下载安装。
``` ```
#DTK驱动：dtk23.10 DTK驱动：dtk24.04.2
# python：python3.8 python：python3.10
# torch: 2.1.0 torch: 2.1.0
# torchvision: 0.16.0 torchvision: 0.16.0
# mmcv: 2.0.1 mmcv: 2.0.1
conda create -n xdecoder python=3.8
conda create -n xdecoder python=3.10
conda activate xdecoder conda activate xdecoder
pip install torch-2.1.0a0+git793d2b5.abi0.dtk2310-cp38-cp38-manylinux2014_x86_64.whl pip install torch-2.1.0+das.opt1.dtk24042-cp310-cp310-manylinux_2_28_x86_64.whl
pip install torchvision-0.16.0+git267eff6.abi0.dtk2310.torch2.1.0-cp38-cp38-manylinux2014_x86_64.whl pip install torchvision-0.16.0+das.opt1.dtk24042-cp310-cp310-manylinux_2_28_x86_64.whl
pip install mmcv-2.0.1_gitfb7d8f3.abi0.dtk2310.torch2.1.-cp38-cp38-manylinux2014_x86_64.whl pip install mmcv-2.0.1+das.opt1.dtk24042-cp310-cp310-manylinux_2_28_x86_64.whl
``` ```
`Tips：以上dtk驱动、python、torch等DCU相关工具版本需要严格一一对应` `Tips：以上dtk驱动、python、torch等DCU相关工具版本需要严格一一对应`
...@@ -141,11 +140,25 @@ data ...@@ -141,11 +140,25 @@ data
│ │ ├── panoptic_train2017 │ │ ├── panoptic_train2017
│ │ ├── panoptic_val2017.json │ │ ├── panoptic_val2017.json
│ │ ├── panoptic_val2017 │ │ ├── panoptic_val2017
│ │ ├── panoptic_semseg_train2017 (生成)
│ │ ├── panoptic_semseg_val2017 (生成)
│ │ ... │ │ ...
│ ├── train2017 │ ├── train2017
│ ├── val2017 │ ├── val2017
│ ├── test2017 │ ├── test2017
│ ├── ... │ ├── ...
│ ├── refcoco
│ │ ├── instances.json
│ │ ├── refs(google).p
│ │ └── refs(unc).p
│ ├── refcoco+
│ │ ├── instances.json
│ │ └── refs(unc).p
│ ├── refcocog
│ │ ├── instances.json
│ │ ├── refs(google).p
│ │ └── refs(umd).p
│ │── train2014
... ...
``` ```
...@@ -219,49 +232,45 @@ python demo.py ../../images/coco configs/xdecoder-tiny_zeroshot_text-image-retri ...@@ -219,49 +232,45 @@ python demo.py ../../images/coco configs/xdecoder-tiny_zeroshot_text-image-retri
(1) Semantic segmentation on ADE20K (1) Semantic segmentation on ADE20K
``` ```
./tools/dist_test.sh projects/XDecoder/configs/xdecoder-tiny_zeroshot_open-vocab-semseg_ade20k.py xdecoder_focalt_best_openseg.pt 4 --cfg-options model.test_cfg.use_thr_for_mc=False HIP_VISIBLE_DEVICES=0,1,2,3 PYTHONPATH=/public/home/luopl/xdecoder_mmcv/projects/XDecoder ./tools/dist_test.sh projects/XDecoder/configs/xdecoder-tiny_zeroshot_open-vocab-semseg_ade20k.py xdecoder_focalt_best_openseg.pt 4 --cfg-options model.test_cfg.use_thr_for_mc=False
``` ```
(2) Instance segmentation on ADE20K (2) Instance segmentation on ADE20K
``` ```
./tools/dist_test.sh projects/XDecoder/configs/xdecoder-tiny_zeroshot_open-vocab-instance_ade20k.py xdecoder_focalt_best_openseg.pt 4 HIP_VISIBLE_DEVICES=0,1,2,3 PYTHONPATH=/public/home/luopl/xdecoder_mmcv/projects/XDecoder ./tools/dist_test.sh projects/XDecoder/configs/xdecoder-tiny_zeroshot_open-vocab-instance_ade20k.py xdecoder_focalt_best_openseg.pt 4
``` ```
(3) Panoptic segmentation on ADE20K (3) Panoptic segmentation on ADE20K
``` ```
./tools/dist_test.sh projects/XDecoder/configs/xdecoder-tiny_zeroshot_open-vocab-panoptic_ade20k.py xdecoder_focalt_best_openseg.pt 4 HIP_VISIBLE_DEVICES=0,1,2,3 PYTHONPATH=/public/home/luopl/xdecoder_mmcv/projects/XDecoder ./tools/dist_test.sh projects/XDecoder/configs/xdecoder-tiny_zeroshot_open-vocab-panoptic_ade20k.py xdecoder_focalt_best_openseg.pt 4
``` ```
(4) Semantic segmentation on COCO2017 (4) Semantic segmentation on COCO2017
``` ```
./tools/dist_test.sh projects/XDecoder/configs/xdecoder-tiny_zeroshot_open-vocab-semseg_coco.py xdecoder_focalt_last_novg.pt 4 --cfg-options model.test_cfg.use_thr_for_mc=False HIP_VISIBLE_DEVICES=0,1,2,3 PYTHONPATH=/public/home/luopl/xdecoder_mmcv/projects/XDecoder ./tools/dist_test.sh projects/XDecoder/configs/xdecoder-tiny_zeroshot_open-vocab-semseg_coco.py xdecoder_focalt_last_novg.pt 4 --cfg-options model.test_cfg.use_thr_for_mc=False
``` ```
(5) Instance segmentation on COCO2017 (5) Instance segmentation on COCO2017
``` ```
./tools/dist_test.sh projects/XDecoder/configs/xdecoder-tiny_zeroshot_open-vocab-instance_coco.py xdecoder_focalt_last_novg.pt 4 HIP_VISIBLE_DEVICES=0,1,2,3 PYTHONPATH=/public/home/luopl/xdecoder_mmcv/projects/XDecoder ./tools/dist_test.sh projects/XDecoder/configs/xdecoder-tiny_zeroshot_open-vocab-instance_coco.py xdecoder_focalt_last_novg.pt 4
``` ```
(6) Panoptic segmentation on COCO2017 (6) Panoptic segmentation on COCO2017
``` ```
./tools/dist_test.sh projects/XDecoder/configs/xdecoder-tiny_zeroshot_open-vocab-panoptic_coco.py xdecoder_focalt_last_novg.pt 4 HIP_VISIBLE_DEVICES=0,1,2,3 PYTHONPATH=/public/home/luopl/xdecoder_mmcv/projects/XDecoder ./tools/dist_test.sh projects/XDecoder/configs/xdecoder-tiny_zeroshot_open-vocab-panoptic_coco.py xdecoder_focalt_last_novg.pt 4
``` ```
(7) Referring segmentation on RefCOCO (7) Referring segmentation on RefCOCO
``` ```
./tools/dist_test.sh projects/XDecoder/configs/xdecoder-tiny_zeroshot_open-vocab-ref-seg_refcocog.py xdecoder_focalt_last_novg.pt 4 --cfg-options test_dataloader.dataset.split='val' HIP_VISIBLE_DEVICES=0,1,2,3 PYTHONPATH=/public/home/luopl/xdecoder_mmcv/projects/XDecoder ./tools/dist_test.sh projects/XDecoder/configs/xdecoder-tiny_zeroshot_open-vocab-ref-seg_refcocog.py xdecoder_focalt_last_novg.pt 4 --cfg-options test_dataloader.dataset.split='val'
``` ```
(8) Image Caption on COCO2014 (8) Image Caption on COCO2014
在测试前需要安装jdk1.8，否则在测试过程中会提示 java does not exist 在测试前需要安装jdk1.8，否则在测试过程中会提示 java does not exist
直接yum install java-1.8.0-openjdk-devel安装jdk失败，可参考以下安装步骤更换repos： 可参考以下安装步骤更换repos：
``` ```
cd /etc/yum.repos.d/ apt update
mkdir bak apt install -y openjdk-8-jdk
mv * bak
wget http://mirrors.aliyun.com/repo/Centos-7.repo
yum clean all
yum makecache
yum install java-1.8.0-openjdk-devel
``` ```
``` ```
./tools/dist_test.sh projects/XDecoder/configs/xdecoder-tiny_zeroshot_caption_coco2014.py xdecoder_focalt_last_novg.pt 4 HIP_VISIBLE_DEVICES=0,1,2,3 PYTHONPATH=/public/home/luopl/xdecoder_mmcv/projects/XDecoder ./tools/dist_test.sh projects/XDecoder/configs/xdecoder-tiny_zeroshot_caption_coco2014.py xdecoder_focalt_last_novg.pt 4
``` ```
## result ## result
(1) Open Vocabulary Semantic Segmentation (1) Open Vocabulary Semantic Segmentation
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment