Commit 79325982 authored by dcuai's avatar dcuai
Browse files

Update README.md ——24.04.2

parent d4ea11f9
......@@ -27,11 +27,12 @@ RepVL-PAN结构如下图,通过自顶向下和自底向上的方式,建立
### Docker(方法一)
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:1.13.1-ubuntu20.04-dtk23.10-py38
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 yolo_world_pytorch <your IMAGE ID> bash # <your IMAGE ID>为以上拉取的docker的镜像ID替换,本镜像为:0a56ef1842a7
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 yolo_world_pytorch <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/yolo_world_pytorch
pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com
pip uninstall deepspeed
pip install --upgrade setuptools wheel
cd third_party
git clone https://github.com/onuralpszr/mmyolo.git
cd mmyolo
......@@ -45,6 +46,7 @@ docker run -it --shm-size=128G -v /path/your_code_data/:/path/your_code_data/ -v
cd /path/your_code_data/yolo_world_pytorch
pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com
pip uninstall deepspeed
pip install --upgrade setuptools wheel
cd third_party
git clone https://github.com/onuralpszr/mmyolo.git
cd mmyolo
......@@ -55,16 +57,17 @@ pip install -v -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。
```
#DTK驱动:dtk23.10
# python:python3.8
# torch: 1.3.1
# torchvision: 0.14.1
# mmcv-2.0.1
DTK驱动:dtk23.10
python:python3.8
torch: 1.3.1
torchvision: 0.14.1
mmcv-2.0.1
conda create -n yoloworld python=3.8
conda activate yoloworld
pip install torch-1.13.1+git7d2dd01.abi0.dtk2310-cp38-cp38-manylinux2014_x86_64.whl
pip install torchvision-0.14.1+gitf78f29f.abi1.dtk2310.torch1.13-cp38-cp38-manylinux2014_x86_64.whl
pip install mmcv-2.0.1+gite2f0eed.abi0.dtk2310.torch1.13-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+das.opt1.dtk24042-cp310-cp310-manylinux_2_28_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`
......@@ -72,6 +75,7 @@ pip install mmcv-2.0.1+gite2f0eed.abi0.dtk2310.torch1.13-cp38-cp38-manylinux2014
```
cd /path/your_code_data/yolo_world_pytorch
pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com
pip install --upgrade setuptools wheel
cd third_party
git clone https://github.com/onuralpszr/mmyolo.git
cd mmyolo
......@@ -90,7 +94,7 @@ pip install -v -e .
将所有数据下载并放置于data文件夹下,数据目录如下:
注意:lvis_v1_minival_inserted_image_name.json放于coco/lvis/文件夹下,其余数据标注文件放于各数据文件的annotations文件夹下
注意:lvis_v1_minival_inserted_image_name.json放于coco/lvis/文件夹下,其余数据标注文件放于各数据文件的annotations文件夹下,仓库中已提供annotation文件[./data/texts](https://developer.sourcefind.cn/codes/modelzoo/yolo_world_pytorch/-/tree/master/data/texts)
mixed_grounding对应GQA数据
......@@ -115,9 +119,12 @@ mixed_grounding对应GQA数据
```
## 训练
首先下载clip-vit模型文件,放于openai目录下:
SCnet快速下载链接:
[clip-vit-large-patch14-336](http://113.200.138.88:18080/aimodels/clip-vit-large-patch14-336)
[clip-vit-base-patch32](http://113.200.138.88:18080/aimodels/clip-vit-base-patch32)
官方下载链接:
[clip-vit-large-patch14-336下载](https://huggingface.co/openai/clip-vit-large-patch14-336)
[clip-vit-base-patch32下载](https://huggingface.co/openai/clip-vit-base-patch32)
### 单机单卡
```
......
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