How can i get the train images with 0.3 gsd?

[nmxnql]

I want to train the train images with 0.3 gsd like the paper said. And I have run the function rescale_ims() in the simrdwn-master/data_prep/yolt_data_prep_funcs.py ,but the test mAP is not 0.72 like the paper said, I get the 0.42 mAP. Could you please tell me how to generate the train images with 0.3 gsd? Thank you very much.

[avanetten]

What training dataset are you using? A different mAP is to be expected if you are using different data than what was used in the paper.

[nmxnql]

I train the original cowc datasets with 0.15 gsd and get 0.72 mAP, but when I run the rescale_ims() in the simrdwn-master/data_prep/yolt_data_prep_funcs.py to generate the images with 0.3 gsd, I get 0.42 mAP. In your paper, the car mAP is 0.72 when the cowc images' gsd is 0.3. I can't get as good results as in your paper.I don't know why.