TFLearn Implementation of DeXpression architecture. Batch normalization is used instead of LRN. Gives a precision of 99.3 percent, recall of 99.2 percent and f1-score of 99.2 percent on CKPlus Dataset for human emotion recognition from frontal facial images.
Cannot feed value of shape (350,) for Tensor 'TargetsData/Y:0', which has shape '(?, 7)'
when i am trying to feed numpy into network is give the above error? how i can solve this.
thanks
Using 10-fold cross-validation on this architecture our best accuracy on the CKP database was around 40% that is on the validation set, ofcourse. I didn't use the code to generate the images because those links are dead. I just resized each image to a 224x244x1 unsigned 8-bit integer.