This week proved to be both very fruitful and very frustrating. So in terms of finishing the backend I was able to get it wired to the point where it was entirely ready for the model. Here the key was 3 fold: being able to store frames without impacting recording Read more…
This week we started to integrate the lua model onto the nano board, but as most things have gone for us this year we ran into some issues, one of which being the fact that the model has too many layers for the nano to handle. This is a major Read more…
This week there was some real concerning realization that our group had to face, including the fact that the originally planned CNN model struggles to learn. One thing I attempted was changing the size of the input packet to be of size 1 instead of a stack of 5 images, Read more…
This week was a big week for us in terms of getting off the ground with our Nano development. We got our camera working with the Nano and now have our backend up and running on the board and are able to interface with the camera. While there are still Read more…
This week was probably one of the most productive so far. With the RPi Camera V2 in we were able to meet and I was able to start working on getting that working with my software. To get it to run with OpenCV we did run into a hiccup where Read more…
Apologies for the delayed post, parents were in town for my birthday and I forgot to post this early. Regardless this week I’ve largely wrapped up the backend, I solved the issue of videos not saving properly so now the only thing left is to add in a averaging kernel Read more…
This week there was a realization that the CNN model was not working as intended and was really not learning during the training. I trained on a smaller batch size and was getting the same weird results, I am about to start training it with a larger batch size and Read more…
This week has largely up to this point been focused around getting a new Jetson Nano and getting the project to a good point for the upcoming demo. As I’m typing this I have the Jetson Nano SD card image downloading and am preparing to get the Nano up and Read more…
This week there were plenty of hurdles for the deblurnet CNN and I’m sure there will be more to come. The training code was finally finished and the data was properly split into frames of 128×128 and all that was left was to deploy the ec2 instance and begin training. Read more…
This week was a bit hectic for me. Given my housemates positive COVID test much of my early week got thrown into disarray and so I spent a lot of time getting everything in order from academics to athletics. In terms of progress made on my sections of the project Read more…