Question about this work. about face-emotion-recognition HOT 3 CLOSED

Hello! I do not have the recent version of AffectNet, so I cannot modify the code by myself.
As far as I know, the images are the same as before, only their labels are organized in the csv file. Actually, that's was the reason to create the copy of my code for recent dataset that you mentioned. I believe you could easily convert this code for usage with my TensorFlow's implementation of MobileNet. Just load the labels of validation images that you need and match them with my predictions, but be sure about changes in position of labeling as it is written in train_affectnet_march2021_pytorch.ipynb. If you need to retrain the model, just change the imagedataloader and read labels from csv files with Pandas.

from face-emotion-recognition.

Hi,
Thanks for you reply, I had try create my own csv file by myself as your suggestion in previous closed issue, but it's seem to take a long time. I will try again like what you guide above.
Thank you!

from face-emotion-recognition.

Closing due to inactivity

from face-emotion-recognition.