Giter Club home page Giter Club logo

Comments (9)

agenthong avatar agenthong commented on May 23, 2024

Actually, you can try this.

from manydepth.

wqx854987945 avatar wqx854987945 commented on May 23, 2024

@suyuzhang Hi,have you tried this method in the indoor environment?

from manydepth.

agenthong avatar agenthong commented on May 23, 2024

Hi!

I train this for indoor scenes. But get depth a little bit weird:
fa80d2eea6df7f45d9955d368110001

I'm confused is there any mistake I made?

from manydepth.

ChauChorHim avatar ChauChorHim commented on May 23, 2024

Hi!

I train this for indoor scenes. But get depth a little bit weird: fa80d2eea6df7f45d9955d368110001

I'm confused is there any mistake I made?

Have you changed the max_depth and min_depth in the options.py. It's better if you can share your setting.

from manydepth.

agenthong avatar agenthong commented on May 23, 2024

Hi!
I train this for indoor scenes. But get depth a little bit weird: fa80d2eea6df7f45d9955d368110001
I'm confused is there any mistake I made?

Have you changed the max_depth and min_depth in the options.py. It's better if you can share your setting.

Hi!

I only change the max_depth to 10 in options.py, and the min_depth is 0.1. So what else should I pull the change(like some max_depth settings in training code)?

from manydepth.

LeeBY68 avatar LeeBY68 commented on May 23, 2024

Hi!
I train this for indoor scenes. But get depth a little bit weird: fa80d2eea6df7f45d9955d368110001
I'm confused is there any mistake I made?

Have you changed the max_depth and min_depth in the options.py. It's better if you can share your setting.

Hi!

I only change the max_depth to 10 in options.py, and the min_depth is 0.1. So what else should I pull the change(like some max_depth settings in training code)?

Which indoor dataset do you use?
The results are the predicted depth using the KITTI trained model? Or you train the model in the indoor dataset, the final results are these?

from manydepth.

daniyar-niantic avatar daniyar-niantic commented on May 23, 2024

Hi. Have you changed intrinsics?

from manydepth.

lhx0416 avatar lhx0416 commented on May 23, 2024

Hi!
I train this for indoor scenes. But get depth a little bit weird: fa80d2eea6df7f45d9955d368110001
I'm confused is there any mistake I made?

Have you changed the max_depth and min_depth in the options.py. It's better if you can share your setting.

Hi!

I only change the max_depth to 10 in options.py, and the min_depth is 0.1. So what else should I pull the change(like some max_depth settings in training code)?

Hi, hello. Have you figured out the cause of this issue? I've also encountered a similar problem.nianticlabs/monodepth2#483

from manydepth.

lhx0416 avatar lhx0416 commented on May 23, 2024

Hi. Have you changed intrinsics?

hello , I met the same issue with him. i changed the intrinsics , and changed the weight\height in option.py,however i the result as follows: RGB image(top) depth map predict from author provided mono_640*192 (middle) trained by myself(bottm)

279249645-37fffe9b-15f9-467a-bc22-1e282b2881f0

from manydepth.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.