Toc
  1. pooling
  2. loss function
    1. CrossEntropy
  3. optimizer
    1. warmup
  4. metrics
    1. perplexity PPL
  5. train
    1. train from scratch
Toc
0 results found
MINGG
DL concept
2021/07/04 AI deep learning

pooling

addition, bi-interaction, and global average pooling

loss function

CrossEntropy

Quantify the difference between two probability distributions.

optimizer

warmup

read:https://www.zhihu.com/question/338066667

metrics

perplexity PPL

refer to https://blog.csdn.net/index20001/article/details/78884646

train

train from scratch

train without pre-training

some about convergence:https://www.zhihu.com/question/64966457

打赏
支付宝
微信
本文作者:MINGG
版权声明:本文首发于MINGG的博客,转载请注明出处!