search

RockyXu66 / Faster_RCNN_for_Open_Images_Dataset_Keras

Faster R-CNN for Open Images Dataset by Keras
474 stars 340 forks source link

Do training for graphs also require ImageNet dataset #14

Open kunakl07 opened 5 years ago

kunakl07 commented 5 years ago

Hi @RockyXu66 ,read your article on medium,it was amazing I have a doubt that you wanted to detect realtime objects so you trained your model on ImageNet;But I want to detect patterns in graphs,so even I need to initialize my model with ImageNet dataet and apply transfer learning,and then train this models on graphs and and predict output? Or should I create new model consisting of only labelled images of graphs I want to classify and not preinitialized images on ImageNet?

kunakl07 commented 5 years ago

and @RockyXu66 do you think both the methods would make a difference i.e. 1)Pretrained model generated from transfer learning and then training our labelled graphs on it to detect patterns 2)Directly training our data on Graphs and no pretrained model like imagent And which according to you would be better