I followed your configurations and setup to get the code to work as you do. The issue I am running into is that the models do not predict any values. The only values I see are for the first class"addsiply":
{'accuracy': 0.19970261923824775, 'addisplay': {'f1-score': 0.332920202116503,'precision': 0.19970261923824775, 'recall': 1.0, 'support': 3492},
'addisplay++adware': {'f1-score': 0.0,'precision': 0.0, 'recall': 0.0,'support': 58},
The macro-f1 score stays fixed during the entire running time of the code. Additionally, the confusion matrix looks something like this:
array([[3492, 0, 0, ..., 0, 0, 0],
[ 58, 0, 0, ..., 0, 0, 0],
[ 66, 0, 0, ..., 0, 0, 0],
...,
[ 36, 0, 0, ..., 0, 0, 0],
[ 38, 0, 0, ..., 0, 0, 0],
[ 44, 0, 0, ..., 0, 0, 0]])
I tried most of the "classification_models.keras" models you have like[ResNet50, MobileNet, and others]. But I still see this issue.
I followed your configurations and setup to get the code to work as you do. The issue I am running into is that the models do not predict any values. The only values I see are for the first class"addsiply": {'accuracy': 0.19970261923824775, 'addisplay': {'f1-score': 0.332920202116503,'precision': 0.19970261923824775, 'recall': 1.0, 'support': 3492}, 'addisplay++adware': {'f1-score': 0.0,'precision': 0.0, 'recall': 0.0,'support': 58}, The macro-f1 score stays fixed during the entire running time of the code. Additionally, the confusion matrix looks something like this: array([[3492, 0, 0, ..., 0, 0, 0], [ 58, 0, 0, ..., 0, 0, 0], [ 66, 0, 0, ..., 0, 0, 0], ..., [ 36, 0, 0, ..., 0, 0, 0], [ 38, 0, 0, ..., 0, 0, 0], [ 44, 0, 0, ..., 0, 0, 0]]) I tried most of the "classification_models.keras" models you have like[ResNet50, MobileNet, and others]. But I still see this issue.