Giter Site home page Giter Site logo

Comments (8)

Sierkinhane avatar Sierkinhane commented on May 25, 2024

Hi,

  1. I provided res50_cam.pth which was the pre-trained model on VOC2012. Actually, you can try to train such a model or directly use ours (create a directory called cam-baseline-voc12 then put the pretrained res50_cam.pth in it).
  2. resnet50_cam.py is the basic network (baseline cam). res50_cam.pth is the saved model of resnet50_cam.py
  3. run_sample.py will load the pretrained model to train clims.
    btw, welcome to star our repository

from clims.

yangxinhaosmu avatar yangxinhaosmu commented on May 25, 2024

Hi,

  1. I provided res50_cam.pth which was the pre-trained model on VOC2012. Actually, you can try to train such a model or directly use ours (create a directory called cam-baseline-voc12 then put the pretrained res50_cam.pth in it).
  2. resnet50_cam.py is the basic network (baseline cam). res50_cam.pth is the saved model of resnet50_cam.py
  3. run_sample.py will load the pretrained model to train clims.
    btw, welcome to star our repository

from clims.

yangxinhaosmu avatar yangxinhaosmu commented on May 25, 2024

Hi,

  1. I provided res50_cam.pth which was the pre-trained model on VOC2012. Actually, you can try to train such a model or directly use ours (create a directory called cam-baseline-voc12 then put the pretrained res50_cam.pth in it).
  2. resnet50_cam.py is the basic network (baseline cam). res50_cam.pth is the saved model of resnet50_cam.py
  3. run_sample.py will load the pretrained model to train clims.
    btw, welcome to star our repository

1.感谢,我目前的理解是先用res50_cam.pth的模型去初始化resnet50_clims里的CLIMS对吗?
2.还有一个问题就是如果我想CLIP的image encoder之前加一些模块(比如对特征表示做增强这种的)的话,可以在resnet50_clims里的CLIMS的stage后面直接加吗?这样的话还能用res50_cam.pth去初始化吗?

from clims.

Sierkinhane avatar Sierkinhane commented on May 25, 2024

可以的,如果你添加了一些模块的话,也可以导入预训练的模型,只要把这里的strict=True换成strict=False

model.load_state_dict(torch.load('cam-baseline-voc12/res50_cam.pth'), strict=True)

from clims.

yangxinhaosmu avatar yangxinhaosmu commented on May 25, 2024

可以的,如果你添加了一些模块的话,也可以导入预训练的模型,只要把这里的strict=True换成strict=False

model.load_state_dict(torch.load('cam-baseline-voc12/res50_cam.pth'), strict=True)

我大概了解了,还有一个小小的问题,就是如果不导入res50_cam.pth的话,训练resnet50_clims大概需要多花多少时间呢?您有记录过吗?

from clims.

Sierkinhane avatar Sierkinhane commented on May 25, 2024

最好导入一下预训练模型,效果会好些,总体训练时间是一样的应该是10epoch

from clims.

yangxinhaosmu avatar yangxinhaosmu commented on May 25, 2024

最好导入一下预训练模型,效果会好些,总体训练时间是一样的应该是10epoch

OK! 感谢同学耐心的指导!!!祝申到理想的PHD!

from clims.

Sierkinhane avatar Sierkinhane commented on May 25, 2024

感谢!

from clims.

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.