this is for holding javascript data
chengds edited section_First_Idea_The_first__.tex
over 8 years ago
Commit id: c236118526c431435e91eca0940902c428191150
deletions | additions
diff --git a/section_First_Idea_The_first__.tex b/section_First_Idea_The_first__.tex
index 9359551..31594a7 100644
--- a/section_First_Idea_The_first__.tex
+++ b/section_First_Idea_The_first__.tex
...
When we launched the first trait we noticed that all the network layers, both weights and data were set to zeros. To overcome this problem we decrease the learning rate and build the training files using random permutation of the images.
Then we test the fine-tuned model building a deploy.prototxt file that takes as input images and predict the traits of them. Testing the net we noticed that the net
wasn't was not able to learn
to much...maybe much. Maybe the task is to
hard... hard. We pretend to generalize a personality trait form 45000 images a predict a float number given a new image.