search

arundasan91 / DeXpression

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.
13 stars 8 forks source link

How to retrievie the picture from each layer? #5

Closed BePhamVietnamese closed 6 years ago

BePhamVietnamese commented 6 years ago

I would like to extract pictures after each layer, same as shown in your papers. Please help me on this.

image

arundasan91 commented 6 years ago

@BePhamVietnamese , just to clarify this is not a paper I published. You can contact the authors and see if they have some code to do that. In Keras, you could extract the activation of each layer (if you name the layer). A quick google search will give you many code snippets that might work.