Noel Tam

GPU usage (data generator

1

[data.py.txt](https://github.com/krasserm/face-recognition/files/2672286/data.py.txt)  I created my own triplet_generator() (see attached txt). However, with reference to picture attached, I am unable to fully utilize of my RTX2070 (8GB) GPU, it does not...

Reproduce using your pretrained model

10

I am trying to reproduce your work via pre-trained model (provided in your [google link](https://drive.google.com/drive/u/0/folders/1w1iF7UuI-drXZ1pNLcLg9pPT9Jmky9cy)). Seem to be missing something. I ran this: ``` bash ./scripts/test.sh ``` but stuck here:...

I need to track heads, instead of person. I have used your tracker, but it keep switching ID even without occlusion. My suspect is tt1.pb was trained on "person" data...

tpe, tpe_pred = build_tpe(n_in, n_out, W_pca.T)

2

HI I'm stuck here. keras merge keep error me out. In [13]: tpe, tpe_pred = build_tpe(n_in, n_out, W_pca.T) D:\xrvision\XRV_projects\Face-identification-with-cnn-triplet-loss\model.py:67: UserWarning: Update your `Dense` call to the Keras 2 API: `Dense(18,...

Regarding orgnised_data.py and load_data.py

1

1. After organise_data.py, it blown up 451 images into tons of thousands images, which I think you are trying to increase dataset, that's ok. What I dun understand is why...

unknown layers, looking for the codes

1

I'm using Netron visualizer to see the architecture of your feature getter weights "tt1.pb", I understand that the bottom part of the network are coded in "network_definition.py" under create_network, since...

Sorry, newbie asking silly question here. Where to place the dataset, how to run your code to organise them accordingly, and how to proceed train and test. No clear how...