Using the captions for image inpainting (Part 2)

In this series of posts I will detail how I incorporated the image captions to my model in order to perform image inpainting. Link to Part 1 of Using the captions for image inpainting.

In this second part, I finish the implementation and show results of using the captions. Furthermore, I will expand on some elements I previously mentioned could help my performance (running the optimization for image reconstruction multiple times)!

This post relates to the class project for my Deep Learning class. For more information regarding this project, or for all other post related, please follow this link. For the summary/plan of my project, refer to this post.

Read More »

Using the captions for image inpainting (Part 1)

In this series of posts I will detail how I incorporated the image captions to my model in order to perform image inpainting.

In this part, I cover the approach I used and the implementation I will going for. The next part (Part 2) will include results and in addition, I will expand on some elements I previously mentioned could help my performance!

This post relates to the class project for my Deep Learning class. For more information regarding this project, or for all other post related, please follow this link. For the summary/plan of my project, refer to this post.Read More »

Applying Temporal Difference Methods to Machine Learning — Part 3

In this third Part of Applying Temporal Difference Methods to Machine Learning, I will be experimenting with the intra-sequence update variant of TD learning. It is a method where after each time step, the parameters are updated rather than waiting at the end of the sequence.

This post relates to my class project for the Reinforcement Learning class COMP767 I am taking at McGill. For previous work and more information, you can refer to Part 1 and Part 2 of this project.

Read More »

Applying Temporal Difference Methods to Machine Learning — Part 1

In this post I detail my project for the course Reinforcement Learning (COMP767) taken at McGill, applying Temporal Difference (TD) methods in a Machine Learning setting.

This concept was first discussed by Sutton when he introduced this family of learning algorithms. I aim to go over what was discussed in the paper and see how it performs on a traditional machine learning problem.

In this part, I will be covering the concepts underlying this application.Read More »

Image Reconstruction with pre-trained GAN using perceptual and contextual losses

In this post I detail my implementation and some initial results for image reconstruction using a pre-trained Generative Adversarial Network (GAN). I will be using the approach recommended in Yeh et al. by using a perceptual and contextual loss in the reconstruction stage. This post is related to my Deep Learning (IFT6266) course project class.

As usual, more information with regards to my broader plan and summary of the project can be found here, more details on the project here and all the code used can be found in this GitHub repo.Read More »