Changes between Version 56 and Version 57 of Other/Summer/2023/Features


Ignore:
Timestamp:
Aug 7, 2023, 7:11:56 PM (11 months ago)
Author:
KatieLew
Comment:

—

Legend:

Unmodified
Added
Removed
Modified

  • Other/Summer/2023/Features

    v56 v57  
    77
    88
    9 '''Katherine Lew'''[[BR]]Rising Sophomore pursuing BS in Finance and Computer Science
     9'''Katherine Lew'''[[BR]]Rising Sophomore pursuing BS in Finance and Computer Science 
    1010
    1111
    … …  
    7272* Testing complicated patterns: We tested training data with more complicated patterns of movement. For instance, we trained the model with one class of frames moving in a completely random pattern and the other moving with a 3-degree bias to the right. After running 10,000 samples, we obtained 50% accuracy. We hypothesize 3 potential causes of the low accuracy: 1) sample size was too small 2) there was a problem in our datasets 3) there was an error in executing the software stack
    7373
    74 * Testing with new bias: To rectify the issue, we changed the bias from 3 degrees to 30 degrees. The model was able to identify the change in bias with a 93% accuracy on 10,000 samples.
     74* Testing with new bias: To rectify the issue, we changed the bias from 3 degrees to 30 degrees. The model was able to identify the change in bias with a 93% accuracy on 10,000 samples.  
    7575
    76 * Automation of model training:
     76[[Image(yesbias_AdobeExpress.gif), width=300, height=300)]][[Image(nobias_AdobeExpress.gif​), width=300, height=300)]]
     77
     78=== Week 8/9 Progress
     79
     80* **Sclurm**: Each training run of a dataset takes about 2-3 hours and generates one point (one accuracy and one bias) on the accuracy v. bias graph. Since many points are necessary to identify a consistent pattern between accuracy and bias, the graph could take days to create. We decided to use Sclurm workload manager to submit multiple jobs to iLab that run in parallel saving massive amounts of time.
     81
     82* **Automation of model training**: We wrote a script that generates several datasets, trains the model using each of those datasets (with Sclurm), and outputs a final graph plotting accuracy v. bias (one point on the graph for each dataset). Since the generation and training process takes hours, this script saves the time required in manually running the model for each dataset.
     83
     84* **Testing the simulator**:
    7785
    7886
    79 
    80 
    81 
    82