I did not get much done this week since I was sick. I did participate in final presentations and peer review. I also participated in build once with working through a problem we had with GitHub, helping test the ultrasonic sensor, and trying to get access to more GPIO pins. Read more…
Last week, I focused on making sure the camera could detect trash items at the robot’s rather high height and reliably communicate information to the Pi with a basic path planning algorithm. Unfortunately, since the images the camera were trained on were mostly flat rather than at the height of Read more…
This week, I was successfully able to generate bounding boxes using the optimized tensorrt (trt) model. As seen in the below screenshot, inferencing runs at an average rate of 115 FPS (~8.7ms) on a live camera feed when jetson_clocks is enabled. As the camera can only support a max of Read more…
This past week, I spent most of my time on the build and integration of our robot as it was the most important component left to get working for our interim demo, with the overall code seemingly in a good spot. I helped construct and integrate the remaining acrylic boards Read more…
This week I mostly took it easy after spending ~30hrs on capstone last week. I was able to collect a bunch of water bottles and soda cans for future testing, however. While I did work on some code for using a trt model instead, a couple hours wasn’t long enough Read more…
Over this past week (and the last few days of spring break), I have many updates. I was successfully able to complete training of the YOLOv7-tiny model and ended with great results! The below charts summarize the training, validation, and testing results across all classes. Training Results (@ 0.01 confidence) Read more…
These past weeks, I spent quite a bit of my time creating my own custom dataset, both by taking pictures in the real world and by Frankenstein-ing existing datasets together to make one big dataset. This dataset can be found here . It contains a total of 9688 images, which Read more…
This past week, I spent most of my time coalescing the datasets of the trash items we wish to detect into respective classes and also thinking/researching ways to further tune the YOLOv7 and YOLOv7-tiny models. As I’m worried about wasting compute resources, I want to be careful about how many training Read more…
This past week, I spent most of my time setting up Google Colab and training the YOLOv7 and YOLOv7-tiny models. As expected, the YOLOv7 has been tuning well, but the metrics for the YOLOv7-tiny model are not so stellar. Since I’m ahead of schedule, I’ve been focusing on finding ways Read more…
This week, I presented our project proposal. I also spent time further researching different pre-trained ML model options and looking into different datasets available for use. As a part of this process, I took a closer look at the existing YOLO versions, and noticed that YOLOv5, YOLOv6, and YOLOv8 were Read more…