Comments (4)
EyalMichaeli
commented on July 27, 2024
1
I used png images and that's ok
from photorealismenhancement.
lucamarini22
commented on July 27, 2024
I mean, when I specify the path to the robust label maps in the csv file, is it ok for them to be png files? Because that's the output I got from MSeg, but please let me know if it is correct or not
from photorealismenhancement.
srrichter
commented on July 27, 2024
Yes, png is fine. The important thing for the labels is that the number of classes corresponds to the embedding in the discriminator.
from photorealismenhancement.
luda1013
commented on July 27, 2024
Hallo Pros,
sorry but i am still stuck at step robust labeling using MSeg. i used the PfD Datasets and Cityscapes.
i am using pretrained weigt for MSeg like in their Colab. But when i did the segmenting for a image folder of PfD, i only got the gray scale images and for 1 image the process took 10 min! so crazy!!
so can i use just the gray scale image for the robust label map?
Thank you very much
from photorealismenhancement.
Related Issues (20)
- What does "name_load" in test_pfd2cs.yaml mean? HOT 1
- How many images should I input? HOT 1
- Question HOT 2
- Training config for hr_new (ienet2.py) HOT 1
- How many GPUs used during training? HOT 1
- Struggling with a bit of the setup HOT 1
- Sigmoid missing in hr_new? HOT 2
- MSeg difficulties HOT 9
- Can't figure out how to compile it. HOT 2
- How to get the ground truth label map of GTA game? HOT 1
- Loading model for training HOT 2
- ValueError when saving model HOT 3
- RuntimeError while training HOT 3
- usage
- Tensor size mismatch error for batch_size>1 - File:gb_encoder.py HOT 1
- step: Matching patches across datasets. Error num_samples = 0 HOT 3
- Train without using robust labels map from Mseg HOT 6
- Problem on MSeg, took 10 minutes for 1 image and only produced the gray scaled image? HOT 17
- Error Training -> Num_samples = 0
- License? HOT 2
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 photorealismenhancement.