Evaluation Metrics for the provided model weights are not same in my execution

[ammuaj]

Hi, I have downloaded the model_weights from model_weights/multi_temporal_crop_classification.pth and executed it on the eval_dataset (549 patches) to calculate the accuracy metrics. However, the accuracy measurement is different from the one shown in this repo.
Could you please confirm that the shared model_weights are the final ones for your result or are they just intermediate model weights ( for fewer epochs)?

Here is the output in my execution

[ammuaj]

Hey, never mind. I figured this out. I was using different smaller validation sets. I get the exact same confusion matrix now. Thanks!