Common steps for pre-processing a new dataset
Here are the common steps for pre-processing a new dataset:
- Figure out the dimensions and shapes of the problems.
- Reshape the datasets such that each example is now a vector of size(num_px*num_px*3, 1).
- “Stadardize” the data.
本博客所有文章除特别声明外,均采用 CC BY-NC-SA 4.0 许可协议。转载请注明来自 Howie's HomePage!
评论
TwikooValine