Coder Social home page Coder Social logo

Comments (7)

WZMIAOMIAO avatar WZMIAOMIAO commented on July 20, 2024

你可以重新克隆下我的代码,我已经把这个问题修复了,主要问题是在使用torch.tensor()这个方法(我怀疑是没有指认设备的原因),我直接把这个方法替换成对应常数了,例如:

torch.tensor(0)

替换成

0

from deep-learning-for-image-processing.

why228430 avatar why228430 commented on July 20, 2024

谢谢!问题已解决

from deep-learning-for-image-processing.

why228430 avatar why228430 commented on July 20, 2024

看了你的视频收获很多。弱弱问一句,faster-rcnn的视频什么时候更新?

from deep-learning-for-image-processing.

super-wz avatar super-wz commented on July 20, 2024

可能本周吧

from deep-learning-for-image-processing.

why228430 avatar why228430 commented on July 20, 2024
    features = list(features.values())
    # 计算每个预测特征层上的预测目标概率和bboxes regression参数
    # objectness和pred_bbox_deltas都是list
    objectness, pred_bbox_deltas = self.head(features)
    # 生成一个batch图像的所有anchors信息,list(tensor)元素个数等于batch_size
    anchors = self.anchor_generator(images, features)

关于这个地方我有两点不理解:(1)骨架网络学习到的特征图包含gt框的信息吗?(2)经过head函数对特征图进行33卷积操作,然后经过2个11卷积分别学习目标前景分数和边界框回归参数,但是这个时候原图上还没有生成anchor,网络是怎么学习的目标前景分数和边界框回归参数的?

from deep-learning-for-image-processing.

WZMIAOMIAO avatar WZMIAOMIAO commented on July 20, 2024

anchors假想是一直存在的,刚开始训练预测时你可以理解为网络瞎预测的(最开始网络并不知道anchors的存在),但计算损失时,由于是已anchors作为参考的,所以在反向传播误差时,网络才慢慢开始理解anchors的存在,并已anchors作为参照进行预测回归参数。

from deep-learning-for-image-processing.

why228430 avatar why228430 commented on July 20, 2024

讲的很明白,谢谢!

from deep-learning-for-image-processing.

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.