Commit 0c9479eb authored by chenzk's avatar chenzk
Browse files

Update url.md

parent 0ebd1a19
...@@ -93,11 +93,9 @@ https://developer.hpccube.com/tool/ ...@@ -93,11 +93,9 @@ https://developer.hpccube.com/tool/
## 数据集 ## 数据集
下载地址: HDTF_warprefine下载地址:
https://drive.google.com/file/d/166eNbabM6TeJVy7hxol2gL1kUGKHi3Do/view?usp=share_link https://drive.google.com/file/d/166eNbabM6TeJVy7hxol2gL1kUGKHi3Do/view?usp=share_link
- [data](http://113.200.138.88:18080/aidatasets/metaportrait_base_model_data)
``` ```
base_model base_model
data data
...@@ -124,17 +122,6 @@ data ...@@ -124,17 +122,6 @@ data
(模型)https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth (模型)https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth
数据集快速下载中心:[SCNet AIDatasets](http://113.200.138.88:18080/aidatasets)
项目中的预训练权重可从快速下载通道下载:
- [GFPGANv1.3](http://113.200.138.88:18080/aimodels/findsource-dependency/gfpganv1.3)
- [temporal_gfpgan](http://113.200.138.88:18080/aimodels/findsource-dependency/temporal_gfpgan)
数据集快速下载中心:[SCNet AIDatasets](http://113.200.138.88:18080/aidatasets)
- [HDTF_warprefine](http://113.200.138.88:18080/aidatasets/hdtf_warprefine)
``` ```
sr_model sr_model
...@@ -174,14 +161,6 @@ sr_model ...@@ -174,14 +161,6 @@ sr_model
下载模型:https://drive.google.com/file/d/1Kmdv3w6N_we7W7lIt6LBzqRHwwy1dBxD/view (放入checkpoint文件夹中) 下载模型:https://drive.google.com/file/d/1Kmdv3w6N_we7W7lIt6LBzqRHwwy1dBxD/view (放入checkpoint文件夹中)
预训练权重快速下载中心:[SCNet AIModels](http://113.200.138.88:18080/aimodels)
项目中的预训练权重可从快速下载通道下载:
- [MetaPortrait](http://113.200.138.88:18080/aimodels/metaportrait)
cd base_model cd base_model
CUDA_VISIBLE_DEVICES=0 python inference.py --save_dir result --config config/meta_portrait_256_eval.yaml --ckpt checkpoint/ckpt_base.pth.tar CUDA_VISIBLE_DEVICES=0 python inference.py --save_dir result --config config/meta_portrait_256_eval.yaml --ckpt checkpoint/ckpt_base.pth.tar
......
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