Lab Assignment 10 - nikky4222/BigDataSpring2017 GitHub Wiki

Big Data Assignment 10

---

Student id:16231555
Class id:18
Name:Lakshmi Nikitha Kona

---

Task 1
Write a TensorFlow program for the following Task.
a.Retrain Inception Model final layer for Image Dataset that is not covered in class. Report accuracy etc.
b.Visualizations (Tensor Board): training, loss, weights etc. and validation
c.Report Confusion Matrix for training and validation/testing.In the Wiki Page, include a brief description of your dataset and your approach/results for this task.

---

Transfer Learning
Transfer learning is the improvement of learning in a new task through the transfer of knowledge from a related task that has already been learned. While most machine learning algorithms are designed to address single tasks, the development of algorithms that facilitate transfer learning is a topic of ongoing interest in the machine-learning community. This chapter provides an introduction to the goals, formulations, and challenges of transfer learning. It surveys current research in this area, giving an overview of the state of the art and outlining the open problems. The survey covers transfer in both inductive learning and reinforcement learning, and discusses the issues of negative transfer and task mapping in depth.

Data Set
Pictures of objects belonging to 101 categories. About 40 to 800 images per category. Most categories have about 50 images. Collected in September 2003 by Fei-Fei Li, Marco Andreetto, and Marc 'Aurelio Ranzato. The size of each image is roughly 300 x 200 pixels. We have carefully clicked outlines of each object in these pictures, these are included under the 'Annotations.tar'. There is also a matlab script to view the annotaitons, 'show_annotations.m'.

Data Set Accuracy
We have taken 3 classes from caltech and we used those to retrain the inception model and the outputs are displayed below.


Visualizations

All the visualizations for the the inception model are displayed below.
Graph



Accuracy,Entropy & Activations





Task 2
Develop a Web-based Application for Visual Question Answering that is relevant to your own project including the following features.a Web application for Visual Question answering
b.Connect the web application to TensorFlow AP.

---

Web Page



Prediction 1



Prediction 2