How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
June 2020 - present
- Research Assistant
- 3D Pose, Computer Vision, Medical Data
April 2018 - March 2020
Inspiring Lab Pvt Ltd
- Computer Vision (Real Time Vehicle Tracking and Recognition System)
June 2016 - November 2017
Wolfmatrix Pvt Ltd
- Web Developer
- Full Stack developer
This is depolyment report of Help Nepal Network LTSP e-library in rural government school of Nepal, Syangja, Malunga-1
This term paper on Virtual Private Network (VPN) was written in fourth semester in Kathmandu University as a partial fulfillment of course Communication and Networking in 2014. This consists of compilation from various resources and implementation in windows using free VPN. This work was supervised by lecturer Sushil Nepal.
I am having problem with resnet50 with 10 class classification of handwritten number from 0-9 in Nepali. My validation accuracy is very good 97% but I am having problem with the prediction. After very bad prediction on new data, I have even tried to predict with the same datasets with which I have trained the model but I can not get good prediction.
1. What is the reason of having very bad prediction of having 97% VALIDATION accuracy?
2. Which is the best classifier for 10 class classification?
3. What is the best classifier for 50 class classification?
Note: I need classifier that has good accuracy for real time data (number plate detection and prediction).
I am having problem with prediction with my model trained on resnet50. I have 10 classes of Nepali numbers from (0 ...9). I have trained the model for 100 epochs with around 40,000 data . What is the issue with my model? I am having overfit? Or, the model I have used to train is just too complex for 10 class. I have also tried this model to predict on the training set but the prediction accuracy is very very poor around (10%).
I want to know the difference between classifiers and when they are used. I came across naive bayes which I have found to be much appropriate with small training data set. Can anyone explain me with some clear examples and comparison how is naive bayes different than other classifiers? + How do we choose best classifiers in real examples?
Volunteers of Kathmandu University Open Source Community are responsible for following events: 1) E-Library SetUp in new Districts 2) E-Library Monitoring 3) Training of Trainee 4) E-Library Content Update