Day 7

This morning, Ron sent me some instructions on building a neural network in keras, saving me from having nothing to do for the entire day. Nice! I kept the experiment running in the background while I worked on the neural network. Fortunately (or unfortunately) keras made it very easy to create a sophisticated and successful model. I finished testing everything I needed to by midday. Nice? After lunch, there was still stuff to do. As per usual, I did some reading. I highly recommend the notes from Andrej Karpathy's class on using CNNs for visual recognition (link).
In my Day 2 blog post, I mentioned trying to help Nate format his data to be compatible with the SVM. We are seven days into the internship, and nothing has changed. I figured out how to format my data for the image classification pipeline (one of our internship projects) two days ago, and this format happens to be different. Explaining this format and my implementation to Nate was pretty difficult, and I had a nagging feeling that there had to be an easier way. I'd better get used to it, huh.
Today I also realized that I haven't posted any cool visualizations on my blog yet. The only things I have to show from the lab are lines of code, spreadsheets, and visualizations. Of the three, the last is probably the most interesting for everybody. Without further ado:
My first experiment consists of testing many kinds of feature extractors to see how they perform within a given image classification pipeline. So far, this is the best (a 4-layer multiloss convolutional autoencoder stack trained on 50 samples per class). On the left are the "ground truth" labels for the Pavia University dataset. Each color (other than the dark blue background) corresponds to a label, such as asphalt, meadows, gravel, etc. The middle image shows which pixels the model was trained on (they might be hard to see), and the rightmost image is what the model predicted by learning from the pixels in the middle image. On average, the model applied labels with 94.46% accuracy. Among the most noticeable inconsistencies are in the meadows at the bottom and the intersection on the right.

Comments

Post a Comment

Popular posts from this blog

Outline

Motivation/Background: HSI classification What is HSI? Comparison to RGB The advantages of HSI over other kinds of data Instant, remote, nondestructive data collection Hundreds of data points per pixel What is classification? Introduce using toy data set, like CUB-200 Applications of HSI classification Cancer detection Art authentication Food quality analysis Remote sensing Urban development agricultural monitoring environmental assessment Problems faced High dimensionality Scarcity of labeled data Method: MCAE and Ladder Network Feature Extractors Baseline: PCA Inspiration: Autoencoder Our proposed method: MCAE Classifiers Baseline: SVM Inspiration: Neural network Our proposed method: Ladder network Results : State-of-the-art Comparison Comparison of MCAE against PCA and state-of-the-art Comparison of Ladder Network against SVM and state-of-the-art
Read more

Day 2

Day 2 started with a very brief meeting where we went over the schedule for the next six weeks. Abstract, outline, presentation; two weeks per task. It was at this point that I realized the difficulty of making technical topics sound interesting, then I immediately dismissed the problem as one for my future self. Today was dedicated to Support Vector Machine (SVM) creation, evaluation, and optimization. I was unaware of many of the wonderful functions included in the provided libraries, and ended up doing the data reformatting less elegantly. It still worked, so I left it. When I finished up my SVM code, I tried to help Nate with the errors he was running into. The keyword here is "tried." Note that it's not easy to explain concepts that you figured out hours earlier and happen to be more complicated than they should be. Nate was a good sport about it though, and with Ron's help, he had a good idea of the solution by the end of the day. For the last part of the day,
Read more

Day 28

Week 6 of the internship; the final presentation is on Thursday. It doesn't feel like week 6, but that's probably because I missed almost all of week 4. Regardless, there was much work to do before Thursday, so Nate and I rehearsed our presentations twice in front of the lab. Many revisions were made, and I'm feeling much more prepared for the real deal. Thank you to everybody who was willing to listen to four lame high school presentations about the same topic in the same day. Your contribution will make the very same presentations significantly less lame on Thursday. Apart from presentation-related stuff, Ron and I ran some ladder network and SMCAE experiments all day. Ron tackled the ladder network with PELU activation (which was apparently very difficult) and I continued with adjusting initial layer sizes on the ladder network and doing SMCAE runs with fixed component count PCA as a feature scaler. The results aren't looking too hot, but I'll withhold judgem
Read more