Lab Assignment 10 Inception model & Web based Application for Visual Question Answering - rashmitripathi/Big_Data_Analytics_And_Apps GitHub Wiki
### 1.TensorFlow Programming: Write a TensorFlow program for the following Task.
Inception Model is a deep convolutional neural network architecture which was responsible for setting the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge . The main hallmark of this architecture is the improved utilization of the computing resources inside the network. This was achieved by a carefully crafted design that allows for increasing the depth and width of the network while keeping the computational budget constant.
a. Retrain Inception Model final layer for Image Dataset that is not covered in class. Report accuracy etc.
My dataset is of cars images. They are respectively categorized as SUV,sports and Jeep.
Test Accuracy as shown in screenshot is 89.5% on 200 iterations
b. Visualizations (Tensor Board): training, loss, weights etc. and validation
Screenshots are below:
c. Report Confusion Matrix for training and validation/testing.
Source code for confusion matrix:
Output:
### 2.Develop a Web-based Application for Visual Question Answering that is relevant to your own project.
Running application through pycharm terminal using Flask as shown below
Home Page
Predictions
Integration with Google Conversation API
References
Class Tutorial