Comments (3)
Thanks for your report. It appears that the problem arose due to your internet connection. You can manually download the pretrained model by following the instructions here. Please note that the correct directory to store pretrained models can be identified from the printed message during the automatic download process.
from libcom.
Ah, no I checked it again and again on multiple devices. Broken symlinks were a consistent issue throughout. I have also tried the same on paperspace servers in the cloud.
The symlink was broke, I didnt need to download it again, I simply corrected the symlink from terminal and it started to work. Also the shared pretrained model Vit, was not working even when I downloaded it manually, I simply removed the hugging face manual download part of the code. Unzipped and only then it started working. I have tried it on three systems, linux and windows and also on cloud, none seem to solve this issue.
from libcom.
Hi, after rechecking, I've identified the bug, which stems from the failure of shutil.move
to relocate the target file of a symlink. I have addressed this issue in the following commit. Please download the latest code and give it another try.
from libcom.
Related Issues (20)
- How could i do image harmonization like demo_image_composition? HOT 1
- 处理后的图像,细节部分处理不行,如何改善? HOT 1
- Failed to produce desired output HOT 1
- Training for specific use cases HOT 3
- Getting out of memory HOT 1
- pip install problem HOT 3
- 'Segmentation fault (core dumped)' in image_harmonization HOT 5
- training HOT 1
- pip install libcom error HOT 1
- CudaCheckError when applying CDTNet for image harmonization HOT 1
- 您好,controllable_composition生成的图像分辨率是512*512,看起来比较模糊,请问有办法生成分辨率更大或更清晰的图片吗? HOT 1
- Pip Installation Error: opencv_python==4.1.2.30: No Matching Distribution Found HOT 1
- 阴影生成模型SGDiffusion HOT 3
- pip install libcom fails HOT 1
- Resolution is too low HOT 1
- Import error for trilinear package HOT 1
- Unexpected harmonization results HOT 1
- opa_score报错 HOT 1
- high CPU consumption when using PCTNet HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 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.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
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.
from libcom.