Here, everything is correct. However, when there are many "val_top1" that have the same value, the np.argmax will return the first index for that value. A concrete example is with Caltech101, I got many eval_results["val_top1"] = 100, and the np.argmax(eval_results["val_top1"]) returns the first index where eval_results["val_top1"] = 100. This would make the eval_results["b-test-top1"] much lower, leading to incorrect summarization. Consider the minimal example below:
Hi @Tsingularity @KMnP ,
Thank you for the great work. In the get_df function which summarizes the results. Line 179
Here, everything is correct. However, when there are many "val_top1" that have the same value, the
np.argmax
will return the first index for that value. A concrete example is withCaltech101
, I got manyeval_results["val_top1"] = 100
, and thenp.argmax(eval_results["val_top1"])
returns the first index whereeval_results["val_top1"] = 100
. This would make the eval_results["b-test-top1"] much lower, leading to incorrect summarization. Consider the minimal example below:Am I correct? Or Do I misunderstand something here?
Thanks