Posts

Post has attachment

Public

**Automatic Learning Rate Scheduling That Really Works**

Training deep learning models can be a pain. In particular, there is this perception that one of the reasons it's a pain is because you have to fiddle with learning rates. For example, arguably the most popular strategy for setting learning rates looks like...

Add a comment...

Post has attachment

Public

**Correctly Mirroring Datasets**

I get asked a lot of questions about dlib's landmarking tools . Some of the most common questions are about how to prepare a good training dataset. One of the most useful tricks for creating a dataset is to mirror the data, since this effectively doubles t...

Add a comment...

Post has attachment

Public

**A Global Optimization Algorithm Worth Using**

Here is a common problem, you have some machine learning algorithm you want to use but it has these damn hyperparameters . These are numbers like weight decay magnitude, Gaussian kernel width, and so forth. The algorithm doesn't set them, instead, it's up ...

Add a comment...

Post has attachment

Public

**A Global Optimization Algorithm Worth Using**

Here is a common problem, you have some machine learning algorithm you want to use but it has these damn hyperparameters . These are numbers like weight decay magnitude, Gaussian kernel width, and so forth. The algorithm doesn't set them, instead, it's up ...

Add a comment...

Post has attachment

Public

**A Global Optimization Algorithm Worth Using**

Here is a common problem, you have some machine learning algorithm you want to use but it has these damn hyperparameters . These are numbers like weight decay magnitude, Gaussian kernel width, and so forth. The algorithm doesn't set them, instead, it's up ...

Add a comment...

Post has attachment

Public

**Dlib 19.8 is Out**

Dlib 19.8 is officially out. There are a lot of changes , but the two most interesting ones are probably the new global optimizer and semantic segmentation examples. The global optimizer is definitely my favorite as it allows you to easily find the optima...

Add a comment...

Post has attachment

Public

**

asdfsadfs equation: $$ \lambda + 4 \frac{4}{6} $$ equation: \( \lambda + 4 \frac{4}{6} \) equation: \[ \lambda + 4 \frac{4}{6} \] asdf asdf asdfa Video of optimizer running asdf as dfsfd

asdfsadfs equation: $$ \lambda + 4 \frac{4}{6} $$ equation: \( \lambda + 4 \frac{4}{6} \) equation: \[ \lambda + 4 \frac{4}{6} \] asdf asdf asdfa Video of optimizer running asdf as dfsfd

Add a comment...

Post has attachment

Public

**

asdfa Video of optimizer running asdf

asdfa Video of optimizer running asdf

Add a comment...

Post has attachment

Post has attachment

Wait while more posts are being loaded