Code Monkey home page Code Monkey logo

Comments (3)

ShiqiYu avatar ShiqiYu commented on August 23, 2024
  1. 没区别
  2. 模型不同,v3模型更大一些,比v1准确率更高一点

from libfacedetection.train.

fire717 avatar fire717 commented on August 23, 2024
  1. 没区别
  2. 模型不同,v3模型更大一些,比v1准确率更高一点

谢谢于老师解答,我最近在尝试用keras实现训练,后面训练完想对比下训练效果。
我看这个pytorch的训练annotation是包含了所有的训练集和验证集的,然后测试map是在验证集上进行,也就是说测试的数据在训练的时候用过,这样理解有问题吗?
再次感谢。

from libfacedetection.train.

fengyuentau avatar fengyuentau commented on August 23, 2024
  1. 没区别
  2. 模型不同,v3模型更大一些,比v1准确率更高一点

谢谢于老师解答,我最近在尝试用keras实现训练,后面训练完想对比下训练效果。
我看这个pytorch的训练annotation是包含了所有的训练集和验证集的,然后测试map是在验证集上进行,也就是说测试的数据在训练的时候用过,这样理解有问题吗?
再次感谢。

@fire717 你好。
$libfacedetection.train/data/WIDER_Face_rect/annotations下包含了WIDER Face train和val的标注,但是训练的时候

dataset_rect = FaceRectLMDataset(training_face_rect_dir, img_dim, rgb_mean)

class FaceRectLMDataset(data.Dataset):
"""Face data set with rectangles and/or landmarks
If there is landmark data for that face, the landmarks will be loaded
Otherwise, the landmark values will be zeros
input is image, target is annotation
Arguments:
root (string): filepath to WIDER folder
target_transform (callable, optional): transformation to perform on the
target `annotation`
(eg: take in caption string, return tensor of word indices)
"""
def __init__(self, root, img_dim, rgb_mean):
self.root = root
self.preproc = PreProc(img_dim, rgb_mean)
self.target_transform = AnnotationTransform()
self._annopath = os.path.join(self.root, 'annotations', '%s')
self._imgpath = os.path.join(self.root, 'images', '%s')
self.ids = list()
with open(os.path.join(self.root, 'img_list.txt'), 'r') as f:
self.ids = [tuple(line.split()) for line in f]

是从$libfacedetection.train/data/WIDER_Face_rect/img_list.txt中读取图片和标注文件的列表的,这个文件中所有的图片都是来自于WIDER Face train的。这个你可以自行验证一下。

因此,训练的数据并没有包括WIDER Face的验证集

from libfacedetection.train.

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.