Comments (7)
I don't understand your question. Could you elaborate or provide any visualisation to support your concern?
from mtan.
index=1
a=np.load(data_path + '/image/{:d}.npy'.format(index))
I get result like that
array([[[0.55294118, 0.49019608, 0.49411765],
[0.55294118, 0.49019608, 0.49411765],
[0.55294118, 0.49019608, 0.49411765],
...,
[0.67843137, 0.61176471, 0.64313725],
[0.67843137, 0.61176471, 0.64705882],
[0.68235294, 0.61568627, 0.65490196]],
so I think the data have been pre-processed
I originally thought you were dividing each pixel by 255, but this is not the case。
a=a*255
img = Image.fromarray(a, 'RGB')
img.show()
from mtan.
from mtan.
Just do plt.imshow()
would work.
from mtan.
it's not working.
I think the NYUv2 dataset you provide is not raw data. Each pixel has been mapped to 0 to 1
from mtan.
After you load the image from np, directly plot the image by plt.imshow(a) without sending them to the PIL.
from mtan.
thank you
from mtan.
Related Issues (20)
- depth and segmentation label in cityscape HOT 1
- NYUv2 surface normals grey boundary HOT 1
- Missing items in cityscapes/val/label_19 HOT 2
- Training with my own dataset HOT 16
- Definition of multi-task loss function HOT 5
- Training MTAN-DeepLabv3 HOT 10
- About the instantiation of the model HOT 1
- DWA HOT 1
- The para Temperature of DWA HOT 6
- about the uncertainty loss HOT 4
- about visulization of the result HOT 1
- Avg Cost accumulation HOT 2
- why dwa didn't consider common scale of gradient? HOT 8
- 关于Attention Module的设计 HOT 4
- results inconsistency HOT 19
- Question about the pre-processed cityscapes HOT 5
- DWA的loss梯度爆炸问题 HOT 2
- Question about the structure of the encoder_block_att. HOT 2
- Used Mtan on depth estimation and object detection HOT 5
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 mtan.