Day 9

Today we went to Jocelyn and Hannah’s lab and saw the GRIT machine (goniometer at RIT). Their project involves comparing wet and dry sieving techniques and analyzing grain size distribution.

As for me, I finished my program!! I played around some more with the hyperparameters and network structure, and I'm pretty happy with the results.

I don't think anyone wants to see all 50 epochs, so here are the "highlights" which were printed at the end (the final program doesn't have these long decimals).

Best Training Loss: 0.18281204998493195
Best Training Accuracy: 0.724375
Best Validation Loss: 0.1286986619234085
Best Validation Accuracy: 0.8325

After that I worked on the testing code. At first I tried to loop over the testing Data Loader, but I couldn't open and print the images since they were already transformed. So I decided to use the files themselves- I made three more directories for the three folders in the testing folder, looped through them to get the files, and then looped through the files to open the images and save them for later. Then I could put them through the data augmentation process and input them into the model (which outputs an index corresponding to a class label). The last thing was to print out the photos with the labels which wasn't too bad either. 

Then the actual testing of course, and as promised, the results- the algorithm was able to correctly label 12 out of the 15 photos, so an overall accuracy of 80%. I’ve included some of the correctly labelled outputs below.


Here are the three that it got wrong:

(Actual: Venturia... an understandable mistake I suppose)
(Actual: Venturia, although it has small dots like cedar-apple rust)

(Actual: Cedar, not sure why it got this one wrong...)

It’s interesting to note that it identified all the healthy plants correctly.

After I finished all of that, I started writing a summary (to add to my summary paper from last week, although this exercise wasn’t image-to-image translation). My advisors need the weekend to prepare the code/project that they want me to work on, so I guess I’ll just be finishing up my summary and researching my topic tomorrow.

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