Comments (8)
Thank you for your answer.
The name of results in the website misleading me.
So, I need train a cityscapes model.
from monodepth.
Hi,
Could you please me bit more specific?
What results and how are they different?
from monodepth.
The result in matrix just range from 0.14x to 0.15x. You can find that it is wrong.
In your results: http://visual.cs.ucl.ac.uk/pubs/monoDepth/results/.
The range is from near 0 to about 0.1.
Why?
There are some things diferent?
I just test the cityscapes models.
from monodepth.
What data do you use for testing?
from monodepth.
The cityscapes
All testing data in berlin:
berlin/berlin_000000_000019_leftImg8bit.png berlin/berlin_000000_000019_rightImg8bit.png
.....
from monodepth.
The output disparities we provide are only on the KITTI dataset (kitti or eigen split) you are testing on cityscapes which is a different dataset.
We did not upload the output disparities for the cityscapes dataset.
from monodepth.
@mrharicot
Hello, I also download the model_cityscapes model and tested on the cityscapes test dataset and got the disparities_pp.npy, then i used the evaluation code to evaluation the results, but i got the results are not as yours in the paper:
abs_rel, sq_rel, rms, log_rms, d1_all, a1, a2, a3
0.4235, 3159.2678, 18126.822, 1.910, 67.391, 0.338, 0.716, 0.762
I did change the focal to 2262 and the baseline to 0.22.
`
width_to_focal[2048] = 2262
def convert_disps_to_depths_cityscapes(gt_disparities, pred_disparities):
gt_depths = []
pred_depths = []
pred_disparities_resized = []
for i in range(len(gt_disparities)):
gt_disp = gt_disparities[i]
height, width = gt_disp.shape
pred_disp = pred_disparities[i]
pred_disp = width * cv2.resize(pred_disp, (width, height), interpolation=cv2.INTER_LINEAR)
pred_disparities_resized.append(pred_disp)
mask = gt_disp > 0
gt_depth = width_to_focal[width] * 0.22 / (gt_disp + (1.0 - mask))
pred_depth = width_to_focal[width] * 0.22 / pred_disp
gt_depths.append(gt_depth)
pred_depths.append(pred_depth)
return gt_depths, pred_depths, pred_disparities_resized`
I do not know what went wrong,??
from monodepth.
Hi,
We did not test our model on the cityscapes dataset as they do not have reliable depth data.
What results are you comparing it with?
from monodepth.
Related Issues (20)
- Test results not good after training on custom data HOT 6
- disparity map error HOT 1
- Training without CUDA HOT 1
- Question About Disparity Smoothness Loss
- Relative paths don't work for checkpoint_path
- Total parameters
- Can we use any camera for depth estimation ?
- About the kitti weight in kitti_archives_to_download.txt HOT 2
- Load ImageNet weights for ResNet50 HOT 2
- How to create my own dataset? HOT 2
- Non Linearity on Outputted Disparity.
- Run on windows
- How is the uncertainty measured?
- world coordinates
- testing simple.py has bad result HOT 3
- Difference between upconv and iconv
- Test - why don't you evaluate the loss function ?
- Calculating C1 and C2 error for Make3D dataset HOT 1
- How to load the pre-training model
- Is that possble to use the algorithm in Edge devices
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 monodepth.