sakshamarora's Blog

Phase 3 - Weekly Check-in 10

sakshamarora
Published: 08/03/2020

End of Week 9  - 03/08/2020


What did you do this week?

This week, I planned on how DFFML will be able to provide a way that will make it very easy to work with Deep Neural Networks. I will be having further discussions with the mentors regarding how we can add support for connecting neural networks and make advanced and intricate architectures. 

What is coming up next?

Next, I will working be on Custom Neural Networks mainly focused on Computer Vision based experiments and examples!

Did you get stuck anywhere?

No, this week was mostly planning for the project ahead.


Thank you for reading!

View Blog Post

Dynamic Loading - Weekly Check-in 9

sakshamarora
Published: 07/27/2020

End of Week 8  - 27/07/2020


What did you do this week?

Picking up from last week, I implemented dynamic loading of all the pre-trained torchvision models for image classification. This method creates the ``Model`` classes on the fly using type(), sys.modules and setattr() and loads the weights only for the model that is being used! I discussed with my mentor on more computer vision operations and examples that will be a great addition to DFFML. 

What is coming up next?

After having a discussion with my mentor, we decided that we will work on exposing the optimization and loss function options available in PyTorch and layer support for making custom neural networks in a separate pull request next!

Did you get stuck anywhere?

No, this week went by smoothly!


Thank you for reading!

View Blog Post

Convolutional Neural Networks - Weekly Check-in 8

sakshamarora
Published: 07/20/2020

End of Week 7  - 20/07/2020


What did you do this week?

This week I started working on adding pre-trained Convolutional Neural Networks using the PyTorch Library! I have currently added VGG16 and ResNet18 pre-trained Models and will add more after further discussion with my mentor. 

What is coming up next?

I will work on exposing the optimizing options available in the PyTorch library through DFFML to get the best results using the added models .

Did you get stuck anywhere?

I got a little confused on whether to split the train data into training and validation sets or not. Eventually I went with providing a splitting argument to split train data into validation and training data sets.


Thank you for reading!

View Blog Post

Image Classification - Weekly Check-in 7

sakshamarora
Published: 07/13/2020

End of Week 6  - 13/07/2020


What did you do this week?

I added example usage for using the OpenCV image processing operations to pre-process data before feeding into a Scikit-Learn classification model using DFFML's Command Line Interface. The dataset I used is the FLOWER17 dataset, to classify 17 flower species using their color, shape and texture as their feature maps to feed to the model! Although the accuracy isn't quiet good right now but it can get better if more pre-processing is done on the dataset especially if it's a multi-label classification problem. I've also started working to add pre-trained Convolutional Neural Networks.

What is coming up next?

Next, I will be adding pre-trained CNNs for the purpose of Image classification using Transfer Learning to DFFML.

Did you get stuck anywhere?

I had some issues with the performance of my laptop while training and testing on a large dataset of images. I have since shifted to using the Google Cloud Platform as suggested by my mentor and things have been going a lot smoother and faster now! :D


Thank you for reading!

View Blog Post

Phase 2 - Weekly Check-in 6

sakshamarora
Published: 07/06/2020

End of Week 5  - 06/07/2020

The first phase of GSoC ended and I'm very happy that I passed my first evaluation! At the beginning I was scared and unsure about a lot of things but I was able to make it through thanks to the very supportive mentors and fellow students who helped me! I always tried to give my best in any kind of task and I will continue giving my best in the upcoming weeks!


What did you do this week?

This week was a little slow but I did a lot of research on how we can get better accuracy with traditional Computer Vision techniques and what all processing operations are important to achieve this.

What is coming up next?

Next task is to discuss with my mentors and suggest on how the project will be going forward in this phase! I will be adding image processing operations if necessary and will discuss on the possibility of adding deep learning or OpenCV based models to get the best results while doing different computer vision tasks.

Did you get stuck anywhere?

As I was busy making my road-map ahead for the second phase, so I didn't have any major places I got stuck except some errors related to OpenCV functions but I eventually fixed them or went into the depths of internet to find the solution. :P


Thank you for reading!

View Blog Post