Comments (3)
Thank you for using our model, I believe that the main problem is that idisc
is not in the pythonpath.
You should do something like export PYTHONPATH="<IDISC-REPO_PATH>:${PYTHONPATH}"
before running the model (where <IDISC-REPO_PATH> is the to idisc dir like $HOME/Workspace/idisc
).
from idisc.
Thank you. export
command did not work on Goggle Colab. However, I did this.
import os
os.environ['PYTHONPATH'] = f"{os.getcwd()}:{os.environ.get('PYTHONPATH', '')}"
Also, I had to manually change /idisc/idisc/models/ops/make.sh
file on line 5
python setup.py build install --prefix $VIRTUAL_ENV
to
pip install -e .
Then I could finally run !bash ./make.sh
After doing that I was able to run the test.py code. I got the same results as stated without disparity.
E.g.
Thank you very much.
from idisc.
Hi, could you please share the Google Colab notebook you use?
from idisc.
Related Issues (20)
- I want to visualize your results, but you don't seem to use visulization.py in your code, where should I use them HOT 3
- Can you tell me about the steps you do to normalize the input depth image? HOT 1
- I want to verify your nyunormal results, but the results I ran out were different from yours, and I wanted to know what went wrong and how to run your results
- The evaluation index of the prediction result of the table plane normal vector estimation is printed incorrectly HOT 1
- How to test the depth of a picture
- Cannot import 'MultiScaleDeformableAttention' HOT 4
- AttributeError: 'IDisc' object has no attribute 'no_sync' HOT 2
- Question about Diode indoor dataset HOT 2
- Surface Normal Estimation procedure
- Question about outdoor zeroshot datasets HOT 2
- Evaluating on KITTI Improved Ground Truth HOT 1
- Abnormal Training Phenomena and Bad Performance HOT 6
- _IncompatibleKeys failure loading weights. HOT 1
- About the results of my own test picture are inconsistent with the paper HOT 5
- Setting cross_attn_{i+1}_d{1} but not cross_attn_{i+1}_d{j} on purpose or typo in id_module.py?
- Transposed Cross Attention (page 4 in the paper)
- Input to AFP module
- Saved depth seems wrong HOT 2
- Question : How is GT-Based Depth Rescaling for Diode Indoor Dataset performed ? 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 idisc.