Git Product home page Git Product logo

Comments (2)

swz30 avatar swz30 commented on August 20, 2024

Hi,

We use 2 NVIDIA Tesla V100 GPUs to train the model. With your GPU of 24GB memory, I would suggest either reduce the batch size to 8, Or keep the batch size 16, but change n_feat=32 in the model file (This will make the model lighter but with a minor compromise on accuracy  

MIRNet/networks/MIRNet_model.py

Line 347 in a668d27

def __init__(self, in_channels=3, out_channels=3, n_feat=64, kernel_size=3, stride=2, n_RRG=3, n_MSRB=2, height=3, width=2, bias=False):
)

Since the SIDD training images are of very high resolution, you can first crop patches offline (from the full resolution images) and then train the model on these patches. In our case, we cropped 350 patches of size 256x256 from each image (totalling 350*320 patches).

Regarding the training code, we are aiming to release it in two weeks' time. 

from mirnet.

PangTongyao avatar PangTongyao commented on August 20, 2024

Thank you so much for your reply! I will retry it!

from mirnet.

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.