What did you personally accomplish this week on the project? Give files or photos that demonstrate your progress. Prove to the reader that you put sufficient effort into the project over the course of the week (12+ hours.
Over the past two weeks, I made a large pivot in the way that I addressed model architecture and training. Our model was insufficiently accurate and I believe it was due to three things. First, I tried to train one ResNet50 model to classify three things (clothing type, color, and usage), which was difficult to get high accuracy on because this is a very complicated task. Furthermore, I treated the task as multilabel classification, where each of the labels(each clothing type, color, and usage) is either true or false. This is partially incorrect because each item only belongs to one clothing type, base color, and usage category. Also, I was adding additional layers onto the pretrained ResNet50, which was harming the training because I was adding layers of random weights to pre-calibrated weights of the ResNet50. I decided to pivot to having 3 individual ResNet50 models classify for each category. Based on our research, which is discussed in more detail in our design report, having 3 ResNet50 models is within our range for total model size and classification time. I then saved each model onto my computer so I can later upload them to the Jetson.
I then changed my code to train 3 different models, which is located on our Github. I then downloaded the frontend repo, which is located here, and began familiarizing myself with the structure to start helping Gabriella with the frontend.
Is your progress on schedule or behind? If you are behind, what actions will be taken to catch up to the proiect schedule?
My progress is on schedule.
What deliverables do you hope to complete in the next week?
I hope to help Riley figure out using the OpenCV library on the Jetson Nano so we can start integrating our models in. I also hope to help Gabriella make progress on the frontend.
