Comments (7)
Hi, thanks for your attention to RN!
I believe the problems you posted are caused by the I/O of the model. Specifically, the file lists you maked are not correct and then the pytorch dataset is maked wrongly. You can vim the flist and check if the image paths are correct.
from rn.
i just chenked and unfortunately i donot know wheres the mistake
this is the path of dataset
and this is the flist
from rn.
I've just ran the main.py and it worked well in my machine. Was your python command of training correct?
I suggest you debug step-by-step. And make sure if the model has loaded data correctly first.
from rn.
oh,thanks for your suggestion,i solved the question above!but there is a new problem as follow:
from rn.
It seems the "self.mask_data" is empty. Are you sure that the masks loading is correct ?
from rn.
yes!you r right!it works after i modify the masks' path.but when i try the eval.py there are some problems as follow
some say it is because
but it did not work. i notice that you just update the code here to support cpu,but my trainning and evaling are all on the centos,could you give some suggestions?
from rn.
It's weird. It works well for my machine. Are you sure the codes you run are the newest?
from rn.
Related Issues (20)
- Why use the given pre-training model to get such results? HOT 2
- Training on custom dataset with custom mask for Inpainting HOT 1
- the loss is None HOT 1
- I have trained this on single gpu with cuda 11.2 and pytorch 1.8 but still confuse about multi-gpu training HOT 1
- wu
- 无结果
- i wana better result plz help HOT 10
- bad results HOT 14
- Details for training Places2 dataset and irregular mask HOT 4
- About loss function HOT 1
- Questions about training
- About your pretrained model HOT 1
- Please provide demo images to run your test. HOT 1
- How to test it for a single photo. HOT 1
- Example Inputs and masks for evaluation HOT 3
- Question about more regions (K>2) HOT 1
- add one more channel HOT 1
- 请问一下训练后的结果在哪里测试呢?没看见有测试程序啊 HOT 1
- 关于修复结果的请教 HOT 5
- About output from the pretrained model
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 rn.