Author: yoojoonl

Team Status Report for 5/1/2021

This week our team focused on integrating all our parts together. We ran into a few difficulties in integrating our code. However, we worked through the issues and got most of our code integrated. Potential problems we see looking into the future are running into bugs when testing due to edge cases arising that we did not account for. However, with good testing we can find these edge cases and make sure they don’t become a problem.

Our hardware which we saw as one of the biggest risks initially is working well. There is in a video below that shows it working. https://drive.google.com/file/d/1nLV_yfrHJHVyOtZJjgG1TjcCs474YqKd/view?usp=sharing

Outside of that we are finishing up the work on our final presentation. After that we need to do some final touch ups and then begin work on our final demo and video.

Fred’s Status Report for 5/1/2021

This week

I finished assembling the hardware and got it working with our servo controller. The new gears worked well and fit together and we can rotate our rack now. I began testing the hardware as well.

Link to video demo: https://drive.google.com/file/d/1nLV_yfrHJHVyOtZJjgG1TjcCs474YqKd/view?usp=sharing

I finished integrating the user preference model after making a few changes to it. It now works with the rest of our code.

I also worked to help integrate our code. I focused mainly on the matching and database parts. I finished the integration and added some new functions to make it work better with the rest of our code.

For Next Week:

Finish testing the hardware portion of our project

Finish working on our final presentation

Began planning and preparing for our final demo and video portion

Henry’s Status Report for 5/1/2021

This week I worked on:

  • Validation section of the final presentation. Wrote about validation on each component and system validation.
  • Software integrated. Integrated visualizer API with user interface (aka main). Some new issues were found during integration, which we are fixing right now.

For next week:

  • Work on the final video and final report, and post presentation.

I am on schedule.

Team Status Report for 4/24/2021

Our project has been going well and it looks like we are on pace to finish in time. We are putting the finishing touches on a lot of our project and are going to start testing and integrating all of the separate pieces now. We have to start working together to make sure all the pieces fit together well.

This is a potential risk bringing everything together. Making sure that all the individual parts of the hardware and the software fit together and then the software and hardware work well together is something that may be difficult. However, with good coordination among the team this is definitely something that we can accomplish.

Our schedule is looking good and without any major issues the schedule should progress smoothly.

Fred’s Status Report for 4/24/2021

This Week

Finished the user preference model. The final method allows users to store their feedback about outfits they are shown and the matching api can call the retrieve method to get the feedback about the outfits

I also worked on updating the hardware. The last gears were too small so we 3d printed bigger gears. After getting the gears I readjusted the base in order to fit the bigger gears.

For Next Week

Finish assembling the hardware and work to test it fully to make sure it is functional.

Work with the group to integrate the user preference model into the matching api.

Henry’s Status Report for 4/24/2021

This week I worked on:

  • Software Integration of Visualizer
    • Integrated all components of the visualizer API. It was running very slowly as there’s a fixed cost every time we use the ML model for classification. To fix this, I created batch classification methods. They increased the runtime per image from 4000 ms to 10 ms.
    • Webscraper integration required an algorithm to determine how well two given labels (one for user’s clothes and one for online clothes) matched. I created my own algorithm that took a weighted average with more weight given to more confident labels. It also uses L2 error for color.
  • Validation Testing for Visualizer
    • Validation testing on the image and labels storage made me realize 1. storage hits were extremely unlikely because the keys was based on specific labels and color. and 2. the storage was too large to fit in memory.
      • 1. color keys is now rounded to closest color our of 125. Only most confident label is used for storage.
      • 2. Instead of an in-memory storage, it will be on-disk with memory-caching using DiskCache.
    • Core functionality of Visualizer is quite good, as seen in interim demo.
  • Final Presentation
    • started working on the final presentation.

For next week:

  • Complete software integration with matching api, user preference model, and user interface.
  • Complete software validation.
  • Keep working on Final Presentation

I am on schedule.

Henry’s Status Report for 4/10/2021

This week I worked on:

  • created new clothing classification model to reduce overfitting. Added stronger preprocessing, dropout layer, batch normalization layer, and trained for less epochs. The new model achieved ~70% validation accuracy.
  • created top-5 accuracy test on test data set. Overall 91% top-5 accuracy (yay! this meets our requirements of 90%)
  • Started software integration of visualizer API. Integrated clothing detection and classification, working on integrating webscrapper right now.
  • Helped Fred with hardware design. We required high precision in assembly so I suggested using laser cut components to aid in assembly. For next week:
  • Finish visualizer software integration and create validation tests for software component.
    • measure accuracy on images scraped from online
    • measure runtime of system
    • measure if storage costs are within our initial predictions

I am on schedule.