Comments (8)
Thank you for reporting! I'm sorry to update the README.md
. The minimum requirement for PyTorch is 0.4.1
. Could you install it and try again?
from pytorch-inpainting-with-partial-conv.
After installing torch0.4.1, new error is
And I can't find out how to solve it.
from pytorch-inpainting-with-partial-conv.
Could you pull the latest master and try again? I haven't faced such problems currently.
from pytorch-inpainting-with-partial-conv.
Thanks for your answering.
- I found above error was caused by setting --image_size=256 in train.py. Now I am wondering the meaning of the third and forth line of output images in snapshots/default/images.
- Besides I use 2242243 training images and 2242241 masks. Is it OK? I found generate_data.py generates 3 chanel masks in which pixel value is in [0,255]. But pixels in my masks is 0 or 255, without other values in (0,255).
- Is the code suitable for inpainting images covered by big maks like below?
I found another code is only suitable for inpainting very small masks like below
from pytorch-inpainting-with-partial-conv.
- I've added the description here.
- So you mean there are non-black or non-white pixels in the masks and it might harm the performance, right?
- Please refer to the original paper by the original authors. Personally I think its possible
from pytorch-inpainting-with-partial-conv.
After training, I tested the model and got results like below
input image of network:
mask:
inpainting results:
The result is blurry. Do you have any suggestions to generate more plausible results.
loss_tv curve in tensorboard is like below:
from pytorch-inpainting-with-partial-conv.
One general advice is that the hyper-parameters that the author reported are for datasets of natural images like Places2, they might be not suitable for your setting.
I'm sorry if there still remains a bug.
from pytorch-inpainting-with-partial-conv.
In addition, the style/content loss is calculated based on pre-trained VGG. I'm not sure using these losses works for your grayscale images.
from pytorch-inpainting-with-partial-conv.
Related Issues (20)
- A problem in net.py
- Blurry problem in training HOT 1
- can not find the dataset Places2 HOT 2
- Problem while using net.py HOT 1
- Inquiry about LICENSE HOT 2
- test.py uses Places2 Class incorrectly
- Hi, where are the trained models in your project? HOT 1
- About Model Size HOT 1
- bad examples HOT 1
- Slight scaling issue in PartialConv function
- Blurry results HOT 3
- Generate Mask HOT 1
- 索引 HOT 2
- 版本不匹配 HOT 1
- 类型错误
- 类型错误
- Why the mask is convolved in partial conv?
- Loss values vary a lot
- http://places2.csail.mit.edu/ が開けません HOT 1
- Your Partial Conv is new in computer vision. However, if you use a ground truth image in your loss function for your model trining, your paper is worthless for image inpainting. In most cases, we only have a deteriorated image, and the the ground truth is an unknown target. HOT 3
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 pytorch-inpainting-with-partial-conv.