search

AlirezaShamsoshoara / Fire-Detection-UAV-Aerial-Image-Classification-Segmentation-UnmannedAerialVehicle

Aerial Imagery dataset for fire detection: classification and segmentation (Unmanned Aerial Vehicle (UAV))
https://ieee-dataport.org/open-access/flame-dataset-aerial-imagery-pile-burn-detection-using-drones-uavs
GNU General Public License v2.0
161 stars 48 forks source link

Test accuracy is not similar with the paper #5

Open willyfh opened 3 years ago

willyfh commented 3 years ago

Following are the results of my execution using your code (no modification in the hyperparameter and model):

model at 40 epoch, (train) bin_accuracy: 0.9577 val_bin_accuracy: 0.9514 test_accuracy : 0.5724729895591736

model at 37 epoch (best model based on val set), (train) bin_accuracy: 0.9568 val_bin_accuracy: 0.9820 test_accuracy : 0.6100730895996094 confusion matrix: [[ 814. 2666.] [ 694. 4443.]]

train and validation accuracy is actually similar enough, but the test accuracy is quite far from the paper.

AlirezaShamsoshoara commented 3 years ago

It shouldn't be like this. I will check it and I will let you know.