Day 15

At our morning meeting today a RIT student came in to present his senior project. He’s studying different environmental factors that can affect OCR (optical character recognition) so he can use a neural network to predict whether a photo can be processed by OCR before it’s actually done (so you can save time if your photo isn’t good enough). It was pretty interesting.

I spent my entire day debugging. I left yesterday with the algorithm outputting that there were zero files in the place that I specified, but I wrote additional code today that made it work. Then I had issues accessing the actual training set because the data augmentation wasn’t working, but eventually I got that to work too. I fixed some other small errors and tried to run it, but I guess it was too much to handle because the computer froze. Hoping it was just processing things slowly, I went to lunch. 

During lunch I went to the last seminar, which was pretty long (1 hr 25 min) but really interesting. It was on imaging historical documents- a lot of ancient texts are written over even older writing that has been scraped off or erased, and it’s amazing how they were able to “cancel out” the overlying words and turn the faint, practically invisible background writing into such sharp and easy-to-read text. We got to see several imaging results from ancient documents like the Archimedes Palimpsest and the Martellus Map. 

When I got back the program had been stopped due to its unresponsiveness, but the internet browser, etc. had crashed so I ended up restarting the computer, after which everything seemed fine. I then ran into another problem because the tensor sizes aren’t matching in dimension 2, which is apparently a difficult one to solve because it can be any small error within the model code. So I tried isolating different parts and testing them... it’s strange because the sizes are off by one, which I think could possibly be a rounding error somewhere. Changing the padding and strides affects the sizes, but I don’t think that’s the root of the problem. I got dimension 2 to match, but now dimension 3 doesn’t match (19 and 23). I might look into it this weekend. Even though it sounds frustrating, debugging is the more fun part of the process since it involves more problem-solving.  

Overall it was a pretty quiet day- either the computer towers were quieter or I’ve just become immune to the incessant humming because they didn't even bother me today.

Comments

Post a Comment

Popular posts from this blog

Day 30 (Last Day!!)

It's hard to believe it's over. This morning we had our presentations in the auditorium, and everyone did really well. I remembered pretty much everything I wanted to say, and I think I explained my topic thoroughly. The presentations ended at almost exactly 11, and after closing remarks, photographs, and conversations, I stayed behind at RIT for a while and sent my files with the final code to my advisors. At noon my lab (which also includes two other graduate students) went out to lunch to celebrate, which was really nice because we ended up talking a lot (and not about debugging!) and I got to know them better. It's a little bittersweet because now my involvement is over, but it was a really rewarding experience and I learned how to do something new (many things actually). Overall, although it was stressful at times, I'm glad I ended up having so much autonomy with my project because it really taught me a lot about myself and about making mistakes. I'm going
Read more

Problem Statement

Amy Ruan Problem Statement           Image-to-image translation is a widely applicable area of computer vision; with it, street scenes can be generated from label maps, color pictures from grayscale ones, full objects from outlines, and photographic images from paintings. In short, image-to-image translation is the transformation of one type of scene representation into another. The development of generative adversarial networks (GANs) has facilitated this process, since its structure composes of two networks- the generator and the discriminator- that are trained to compete against each other until the generator has learned to mimic the data it was trained on, which results in clear and realistic output images in image-to-image translation.           Image-to-image translation and GANs have the potential to solve many problems. Autonomous vehicles, for example, must be able to perceive their surroundings even in the dark. While methods exist that translate nighttime photographs into RG
Read more

Day 28

I tested the model from yesterday and it looks surprisingly similar to the best one- the color of the sky is a little split between pink and blue but is blended in most of the images, and overall the objects look a little sharper. The graphs for the loss don’t make that much sense though, and the PSNR for the RGB images fluctuates a lot. This morning we ran through our presentations in the auditorium. We started at 9 am and didn’t finish until 11:50, but we had a lot of time in between each one for feedback. Mine was second and went 16 minutes (better time than I thought) and I got a lot of good advice too. Sometimes I forget that other people haven’t seen my presentation/topic before so I have to remember to explain/define everything. At lunch Jocelyn, Hannah, and I went out to eat and then to Abbott's. We also saw a beaver by the RIT entrance!  In the afternoon I worked on my presentation some more- I cut out some of the graphs as Joe suggested and also made the diagrams clear
Read more