Comments (2)
@fskurniak Thank you for your interest in our work.
1- Actually we are working on some new ideas that can increase the model capacity and performance! Adversarial Hinge loss, for example, works much better than the non-saturating loss for edge generator! And it's early to say but, multi-discriminator approach also seems to be working for us. We will soon publish our findings, so stay tuned!
2- The second stage of our model (the image completion model) has the capacity to inpaint images up-to 512x512 with a very good quality if it receives good edge information. As you can see the bottleneck of the model is the edge generator. To improve the quality of the edge-generator, we can play with the loss. But it's more important to increase the model receptive field. 512x512 images are very challenging and the model needs a good receptive field to cover the entire missing area! We are also developing some techniques to improve this problem. To answer your question, it always helps to continue training. In fact, when we were training the models, we always started with 128x128 and then use the wights for 256x256. Smaller images help early layers of the network learn faster.
3- As I mentioned earlier, bigger masks are very challenging. One approach to look into is an image pyramid. This paper by Nvidia is a good start.
from edge-connect.
1 - I will try experimenting with hinge loss, thanks. It might be interesting to see your setup especially in context of papers (deepfillv1 -> deepfillv2)
2 - thanks for the remarks about receptive field. Indeed this might be crucial
3 - interesting approach 👍
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
- Convergency of edge model HOT 10
- 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 HOT 1
- 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.