How to obtain training and test set?

[atulapra]

I have executed the cvs_to_numpy.py code after downloading fer2013.csv from https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge/data.

Now, it creates two files: data_kike.npy and labels_kike.npy.

From this, please tell me how to get the 4 files:

• data_set_fer2013.npy
• data_labels_fer2013.npy
• test_set_fer2013.npy
• test_labels_fer2013.npy

[denismakogon]

I assume validation data should be obtained here http://www.socsci.ru.nl:8180/RaFD2/RaFD. But data_kike.npy and labels_kike.npy are data_set_fer2013.npy data_labels_fer2013.npy.

[NikAndrush]

@atulapra how you fixed your problem?

[atulapra]

@NikAndrush I did not train the model. I used pre-trained weights I found elsewhere.

[jingyugao]

@atulapra Does the pre-trained weights work well? It seems not very good in my computer

[denismakogon]

@gaodlike with my pretrained model efficiency is nearly 75-80%

[innagorda]

@atulapra can you send any link? I can't find(

[atulapra]

@innagorda You can find the model files in my repo here.

[atulapra]

Issue solved.