Hello everyone, I hope you are all having a lovely day.
I did my 7th session with Go Girl on Skype today. We had our usual check-in before we screen-shared our homework. I experimented using the speech to text command on Snap! I said ‘Hello’ to the microphone, but it didn’t pick up the text nor show an error message.
In today’s session, we focused on adding machine learning models to programs.
Ken demonstrated a program where you can train to recognise images from a camera. Below is an example of Ken training to lean left or right.
I had a turn at leaning in front of my camera. It presented 4 examples to the left and 6 examples of leaning to the right. It was fun to do.
Ken showed another example by changing the labels ‘leaning to the left’ and ‘leaning to the right’ to ‘covering my face’ and ‘smiling’. It had 27 examples of covering the face, but no examples of smiling. The machine recognised the hand, but perhaps didn’t distinguish the difference between the two labels.
Our homework is to experiment and train the program to recognise different things. If you are training the program to recognise two things e.g. cats and dogs, it would be ideal to add a third bucket for everything else. A bucket is a collection of all the images with the same label. I’m excited to do the homework.
Our next session will be on Tuesday 30th as Go Girl will be taking a break this Friday.
I’m looking forward to it and I will see you in the next blog post!