Changes between Version 46 and Version 47 of Other/Summer/2023/Features

Timestamp:

Jul 19, 2023, 4:23:45 PM (12 months ago)

Author:

KatieLew

Comment:

—

Other/Summer/2023/Features

@@ -44 +44 @@
 [[Image(0.0.mov, width=200, height=200)]] [[Image(0.1.mov, width=200, height=200)]] [[Image(0.3.mov, width=200, height=200)]] [[Image(0.9.mov, width=200, height=200)]] [[Image(Screen Shot 2023-07-19 at 11.40.37 AM.png​, width=120, height=100)]]
 
-[[Image(Screen Shot 2023-07-19 at 10.44.07 AM.png, width=400, height=125)]] [[Image(Screen Shot 2023-07-19 at 10.46.33 AM.png, width = 400, height = 125)​]]
+[[Image(Screen Shot 2023-07-19 at 10.44.07 AM.png, width=400, height=125)]] [[Image(Screen Shot 2023-07-19 at 10.46.33 AM.png, width = 200, height = 100)]]
 
-=== Week 4
+=== Week 4/5
 
 * **Validate results:** We discovered that there was a mistake in our training data, so last week's training results were null. There was a bias in the input data, and irrelevant learning happened. 
 
-* **Retrain model** We retrained the machine learning model using simpler test cases, like the black-white frame test. With simple black and white classes, our model obtained 100% accuracy. With more complicated classes, our model obtained 98% accuracy.
+* **Retrain model:** We retrained the machine learning model using simpler test cases, like the black-white frame test. With simple black and white classes, our model obtained 100% accuracy. With more complicated classes, our model obtained 98% accuracy.
 
-* **Reformat tar files **
+* **Reformat tar files: ** We altered the program to reformat the training data. Instead of combining the frames of the random bee simulator into a video format, we compiled the data into a tar file, which consists of a png, a class, and a metadata file for each frame in the simulation. We will use these tar files as training data for the model. 
 
-[[Image(Screen Shot 2023-07-19 at 11.36.05 AM.png, width=200, height=100)]] 
-[[Image(Screen Shot 2023-07-19 at 10.46.33 AM.png)]]
+=== Week 6
 
-=== Week 5
+* **Time Varying Features: ** In order to train the model to capture time varying features (and hence motion), we increased the channels while keeping the same kernel size. This works for small movements in the training data. 
+
+* **Clockwise-Anticlockwise Test: ** With the time varying features accounted for we began to train the model with patterns of motion, instead of simple black and white frames. For instance, we created training data with one class of frames that move in a clockwise direction and one class of frames that move in a counterclockwise direction. Can the model detect left turns?
+
+* **Entropy v. Accuracy Graphs: ** We created a graph from our model output data to derive the relation between entropy versus accuracy.