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 »

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 »

Generative Adversarial Network in anticipation of Image Inpainting

Relating to my IFT6266 course project, I detail the implementation of a Deep Convolutional Generative Adversarial Network (DCGAN), where I hope to get a strong model that understands (or at least gets close to) the distribution behind the real images. The goal as detailed in this post, is to have a competent model in order to be able to use it effectively for reconstructing images.Read More »

Conditional Inpainting – Preprocessing data to speed up training

My original implementation for extracting a batch of data for training is not the most efficient to say the least as it greatly affects training time. Below I will detail the changes I have made to preprocess the images to accelerate training time. I’d like to thank Francis Dutil for discussing his approach with me and providing his code for inspiration.Read More »