Comments (10)
你好,我想知道你跑这个模型,跑了多长时间,我把它放在3060上跑,max_iters=140000,跑了两天了,还没结束
from edge-connect.
方便的话,可以加一下qq:2635505974
from edge-connect.
hello,your ID shows cannot be found
from edge-connect.
Hi, have you solved this problem yet?
from edge-connect.
Hello @knazeri Thanks for your opening source code. I have used your implementation to train from scratch. I stay all your settings unchanged, but only use another remote sensing dataset, which contains only 800 training images with size 256x256.
At the beginning, I trained a edge model with "MODEL=1". It is observed that after 1000 epoches training, the edge model does learn something, but very slow and far from convergency.
The above images are the samples during training after 1 and 67000 iterations respectively. It shows that the edge model was learning throughout the whole training procedure, but could you tell me why does the estimated results so bad?
Beyond that, I have also trained a inpainting model alone with "MODEL=2", but I get a very different results from the results above, as I list below. It is clear that the inpainting model convergenced successfully, which proves the correctness of the training strategy. So Why I get a results above?
Looking for your replys.
Hello @knazeri Thanks for your opening source code. I have used your implementation to train from scratch. I stay all your settings unchanged, but only use another remote sensing dataset, which contains only 800 training images with size 256x256.
At the beginning, I trained a edge model with "MODEL=1". It is observed that after 1000 epoches training, the edge model does learn something, but very slow and far from convergency.
The above images are the samples during training after 1 and 67000 iterations respectively. It shows that the edge model was learning throughout the whole training procedure, but could you tell me why does the estimated results so bad?
Beyond that, I have also trained a inpainting model alone with "MODEL=2", but I get a very different results from the results above, as I list below. It is clear that the inpainting model convergenced successfully, which proves the correctness of the training strategy. So Why I get a results above?
Looking for your replys.
Hello, I also encountered the same problem as you when training the edge model, the repaired edge is very bad. Have you solved the problem? If you solved the problem can you tell me how you did it? It means a lot to me. Thank you!
from edge-connect.
Hi, have you solved this problem yet?
Hello, I have been reproducing this code recently, and the edge repair results were poor when training MODEL=1. Have you solved the problem?
from edge-connect.
Hi, have you solved this problem yet?
Hello, I have been reproducing this code recently, and the edge repair results were poor when training MODEL=1. Have you solved the problem?
Hello, I also encountered this problem, did you solve it?
from edge-connect.
Did you solve the issue?
from edge-connect.
Did you solve the issue?
I think it can not be solved.
from edge-connect.
This work has trained connect work on a custom dataset and they have a model working fine. Its trained in 2022 https://github.com/amiretefaghi/E2F-GAN
from edge-connect.
Related Issues (20)
- Test image is being filled in a lighter shade HOT 1
- Who can help me slove this error? (when I try to train ) HOT 5
- Run the program on CoLab
- Hello, After reading your paper, may I have a question that why you choice 178 for the celebA dataset drop size.
- 如果对图像修复,edge-connect感兴趣,或者需要帮助,可以联系我
- Training on Google Colab immediately stops HOT 1
- Selection of dataset
- Canny sigma HOT 1
- how to implement the visualization for the learned edges? HOT 2
- Sizes of tensors must match except in dimension 1
- New easy to use inpanting method with transformers
- When using edge=2, training has ValueError: operands could not be broadcast together with shapes (256,256,3) (256,256)
- Why is there an error when I train MODEL4: joint model/为什么我训练MODEL4 :joint model会报错
- When I tried to start training, I got an error:RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [1, 512, 4, 4]] is at version 2; expected version 1 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True). HOT 15
- About precision and recall during training HOT 1
- The loss function is abnormal when the edge network is trained
- RuntimeError: CUDA error: device-side assert triggered CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
- a question
- Edge Model Not converging
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 edge-connect.