DAY 5: CONDENSED MODEL

Based on the TensorFlow Transfer Learning Model, I created a condensed version that is shorter, but fits the same purpose.

Since the first time I used this model, the accuracy has always reached 100% after the first epoch. I was curious as to what would happen if I added a new image with a different background to see if it would lower the accuracy, but it didn’t change.

Then, I ran the condensed model with animal images first, then the student images so that it “retrains” the model. The animal images were processed more quickly (since there are significantly fewer images), and the accuracy took 3 epochs to reach 100%. After this, I tested my student images again but it still reached 100% accuracy after 41 seconds in the first epoch.

DAY 2+3: OPENING JIRAS

While troubleshooting ML-490, I ran into some new issues and thus created 2 Jiras to document them.

The first Jira was created as an improvement. The ECL Workunit status only displays the “loss” value, and doesn’t show information about accuracy.

The second Jira was created because kubernetes was not terminating after GNN training, even when the workunit was aborted.

DAY 1: DEBUG JIRA

Last week, I opened a Jira (ML-490) and I’m continuing to get it resolved. The HPCC GNN model will not run more than 255 images on Azure, but I have over 4,000 images that need to be tested.

I made a Kubernetes cluster on Azure then ran the model. I also updated GitHub with all of my recent code.

Plan for the week:

1. Debug ML-490
2. Train with GPU on Azure
3. Update Jupyter Notebook (with all 4,577 images and MobileNet V2 model)
4. Configure model to predict image for client application (on the robot)