Marek

Hi, The runtime of the first image that is processed may be a bit longer. Please calculate the time starting from the second image you process. Also, do not include...

That's definitely slower then it should be. Are you sure it's running on the GPU? Theano should tell you in the first line it prints whether it's using the GPU...

Hi, please explain what you mean by face normalization. Marek

Hi, Yes, you can achieve similar results using DAN. If you want to perform similar normalization on images from CelebA, there is no need to train DAN on them. What...

Hi, You are correct, there is no weight decay in DAN. If I remember correctly, I tried using it, and it did not improve the accuracy. I also conducted some...

Hi, The datasets used for training are provided for research purposes (non commercial) only as detailed on the dataset website linked below. The same rules apply to the models, which...

Hi Roberto, Thanks for checking out our work and contacting us with your doubts. The facial keypoints provided with the 300-W competition are in MATLAB format, which means that the...

Hi Roberto, I got those from the github repository of the [Mnemonic Descent Method](https://github.com/trigeorgis/mdm). Marek

Hi, I assume, that by tracking model you mean the one that is able to predict whether it lost tracking or not. This model was trained by adding a single...

Hi, As mentioned in the previous post, the neural network consists of a single layer, you can see it in the file I linked to. Marek