资源分类
》 资源 》算法》FaceAlignment_Multi-task

FaceAlignment_Multi-task

2020-03-26 | |  41 |   0 |   0

FaceAlignment_Multi-task

trying to reproduce the result of TCDCN, but failed.

  1. I think the model is slightly overfitting, train--1e-4 and val--4e-4. regularzation does not make improvement.

  2. the results are poor when come to images cropped by myself(out of test set)

  3. some hyperparameters are hard to choose~~~ may be this is another reason of the poor result~~~

data augmentation

  1. random translation, zoom, rotation, noise, blur, flip, constrast jitter used

  2. small jitter is good. check out face images after augmentation

there are some tricks get verified in this experiment...


上一篇：mtcnn-face-detection

下一篇：deep_alignment_network_pytorch

用户评价
全部评价

热门资源

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • spark-corenlp

    This package wraps Stanford CoreNLP annotators ...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • inferno-boilerplate

    This is a very basic boilerplate example for pe...