deletions | additions       diff --git a/section_First_Idea_The_first__.tex b/section_First_Idea_The_first__.tex  index 53fc9c1..3ac5f1d 100644  --- a/section_First_Idea_The_first__.tex  +++ b/section_First_Idea_The_first__.tex 
...
Flickr datasets as  data and the traits scores, both self and attributed as target, and fine-tune the  Imagenet model of classifying 1000 classes of objects into our task of predicting  the personality trait given an image. The initial goal was indeed to surgery the prototxt changing the last layer so that the net has to learn it for the new task  and changing the classification layer to a regression layer. We divide the dataset into 75% for the training set and the remaining 25% for the testing set. Some  observation: we can't build the files containing the list of images of training and  testing together with all the labels for the train. To work with the regression we build a txt file containing the path of the images and a hdf5 file for the 10  labels of the traits as they are   oat number and not integer. 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  able to learn to much...maybe the task is to hard... We pretend to generalize a  personality trait form 45000 images a predict a oat float  number given a new image.