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.
I tried two different approaches to training a model. The first was to use a four-layer convolutional neural network architecture, which was able to achieve a training accuracy of just below 70%. The code for this is located here. I then pivoted to using the ResNet50 pretrained model to determine which one would give me the best accuracy.
I was able to achieve a training accuracy of just under 80% for clothing type and color classification, which is what our use-case requirements outlined, so we will be proceeding with the ResNet model. The training is almost complete—certain clothing categories, like blazers and sweatpants, have <50 images while other categories, like tops, have >500. I need to even this out to improve the accuracy of our model by ensuring the training data is balanced. This requires me to manually label images of blazers/sweatpants with the color since I was unable to find any datasets online that have the clothing type images we need labelled with the color. My goal is to get >100 images of each clothing type into the dataset which requires more images of blazers and sweatpants. I think this will get our testing accuracy to 80%.
When training, I realized that the model was able to achieve high accuracy for clothing type and color classification but really struggled to classify the usage of clothing (formal, casual, sports). I realized that this is due to the difference in classifying clothing type/color and something more subjective like usage. Machine learning models can recognize patterns in pixel values, which help classify color, or patterns in shape, which help classify clothing type, but usage is much more subjective and has less to do with the quantitative value of an image (the array of pixel values that the model will process). We have decided to pivot to attempting to classify the usage of clothing but having the user validate our classification(and provide the correct usage if ours is correct (subject to change after discussing during capstone lab).
I also realized that creating predefined outfits isn’t necessary because our SQL queries handle the outfit generation and don’t need to be based on predefined clothing type combinations. Since this removes one of my tasks, our team decided that I could work on the frontend instead since Gabriella has mostly been focusing on the backend and our classification model is done.
I also worked on peer reviews and our design report this week.
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 finish the design report. I am working on increasing the size of our dataset and believe I can finish it and the training by early next week.
