This project contains the ClonedPerson dataset and code described in our paper "Cloning Outfits from Real-World Images to 3D Characters for Generalizable Person Re-Identification".
You mentioned "Download accessories (e.g., hair, beard, shoes, and skin) according to the "5characters/accessories/download.txt"."
How those download file organize ?
I know how clothes organize , you point it out in .txt file, but I didn't konw the othors
Hi! I have the same problem with: open-mmlab/mmdetection#413;
But I still don't know how to solve this problem.
In your project , there exist a folder named mmdet(ClonedPerson\pipeline\1Pedestron\mmdet),
Do I need to recompile?And which version of mmdection to download and install? Or how to solve this problem?
您好，我遇到了这个问题，在mmdection的issues中也有人遇到，但是我还是不太清楚怎么去解决它？
好像是需要重新编译？（听说旧版本需要使用./compile.sh,或者新版本直接执行python setup.py develop）
但我看这里好像调用的是项目中自带的这个mmdet文件夹中的代码，也并没有找到compile.sh或者setup.py这两个文件，我去下载了mmdetection最新的版本，试着运行，但发现和其他环境不匹配，不清楚您用的是哪个版本的mmdection？
或者我应该怎么解决这个问题呢？
Here are the traceback details:
(clonedperson_1pede) D:\2_Work\experiment\ClonedPerson\pipeline\1Pedestron>sh demo.sh && cd ..
Traceback (most recent call last):
File "tools/demo.py", line 16, in <module>
from mmdet.apis import inference_detector, init_detector, show_result
File "D:\2_Work\experiment\ClonedPerson\pipeline\1Pedestron\tools\..\mmdet\apis\__init__.py", line 2, in <module>
from .train import train_detector
File "D:\2_Work\experiment\ClonedPerson\pipeline\1Pedestron\tools\..\mmdet\apis\train.py", line 7, in <module>
from mmdet.core.my_mmcv.runner.mean_teacher_runner import Mean_teacher_Runner as Runner
File "D:\2_Work\experiment\ClonedPerson\pipeline\1Pedestron\tools\..\mmdet\core\__init__.py", line 6, in <module>
from .post_processing import * # noqa: F401, F403
File "D:\2_Work\experiment\ClonedPerson\pipeline\1Pedestron\tools\..\mmdet\core\post_processing\__init__.py", line 1, in <module>
from .bbox_nms import multiclass_nms
File "D:\2_Work\experiment\ClonedPerson\pipeline\1Pedestron\tools\..\mmdet\core\post_processing\bbox_nms.py", line 3, in <module>
from mmdet.ops.nms import nms_wrapper
File "D:\2_Work\experiment\ClonedPerson\pipeline\1Pedestron\tools\..\mmdet\ops\__init__.py", line 1, in <module>
from .dcn import (DeformConv, DeformConvPack, ModulatedDeformConv,
File "D:\2_Work\experiment\ClonedPerson\pipeline\1Pedestron\tools\..\mmdet\ops\dcn\__init__.py", line 1, in <module>
from .functions.deform_conv import deform_conv, modulated_deform_conv
File "D:\2_Work\experiment\ClonedPerson\pipeline\1Pedestron\tools\..\mmdet\ops\dcn\functions\deform_conv.py", line 5, in <module>
from .. import deform_conv_cuda
ImportError: cannot import name 'deform_conv_cuda' from 'mmdet.ops.dcn' (D:\2_Work\experiment\ClonedPerson\pipeline\1Pedestron\tools\..\mmdet\ops\dcn\__init__.py)
May I ask if the eight clothing styles mentioned in the article and the key points on the provided UV images are manually labeled?
Can you share the training parameters of the experimental QAConv
Hello, first of all thanks for your anwesome work !
Could you please provide the environment with the libs you used for the demo, because I'm struggling to install them all.
Thank you guys !
I can't use operator like dcn cause my cuda version is 10.2，but you compile it with cuda10.1
Hello, thank you for your excellent work~
I have some other problems when I try the step5 in the pipeline:
I am not clear about how to run step5 successfully.
①It warns that I don't have cuda11.0, because I used cuda10.0 that time. Is the cuda11.0 necessary? Or there exist another problem in fact？
②How to fix this checkpoint problem？
If I want to add new cloth model, what should I do? Just adding a new floder (conclude .mhclo, .mhmat, .obj, .thumb flie ) (floder name index++) in */ClonedPerson/pipeline/5characters/models would be OK?
Here are the error details:
(clonedperson_4cluster) hex@TP:~/work/ClonedPerson/pipeline/5characters$ sh demo.sh
2023-04-14 16:48:17.545442: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/cuda-10.0/lib64
2023-04-14 16:48:17.545463: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
save_step_open: False
Create IBN-Net model resnet50_ibn_b.
Using cache found in /home/hex/.cache/torch/hub/XingangPan_IBN-Net_master
/home/hex/miniconda3/envs/clonedperson_4cluster/lib/python3.7/site-packages/torchvision/transforms/transforms.py:281: UserWarning: Argument interpolation should be of type InterpolationMode instead of int. Please, use InterpolationMode enum.
"Argument interpolation should be of type InterpolationMode instead of int. "
Loading checkpoint...
=> Loaded checkpoint 'checkpoint.pth.tar'
0 img/pair_0.989210_56_0_137_249_1_21_1.jpeg 8
Error: getLabels wrong, 0 [1, 2, 3, 4] ['4.50873600874602E+053']
Error: getLabels wrong, 1 [1, 2, 3, 4] ['4.50873600874602E+053']
Error: getLabels wrong, 2 [1, 2, 3, 4] ['4.50873600874602E+053']
Error: getLabels wrong, 3 [1, 2, 3, 4] ['4.50873600874602E+053']
Traceback (most recent call last):
File "clonedperson.py", line 640, in <module>
main(parser.parse_args())
File "clonedperson.py", line 549, in main
homography_result, cloth_img, model_landmark, save_name, model_img = PerspectiveHomography([source_folder + cloth_path, cloth_landmark], model_list[model_index%len(model_list)], [source_folder + cloth_path2, cloth_landmark2], cloth_index)
File "clonedperson.py", line 152, in PerspectiveHomography
H, mask = cv2.findHomography(cloth_keypoints_position, model_keypoints_position)
cv2.error: OpenCV(4.5.3) /tmp/pip-req-build-l1r0y34w/opencv/modules/calib3d/src/fundam.cpp:378: error: (-5:Bad argument) The input arrays should be 2D or 3D point sets in function 'findHomography'
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft
Open source projects and samples from Microsoft.
Google
Google ❤️ Open Source for everyone.
Alibaba
Alibaba Open Source for everyone
D3
Data-Driven Documents codes.
Tencent
China tencent open source team.