improgress

i have the same problem! try to add a roi loss on my objective!

Modify the parameters in the test.py， --load_size 512，and then you will get 512pix image.

of course the traindataset

if 12G , its ok for load_size 600 and crop_size 512

change the "num_threads" to "0"

im a junior, wanna know how to get detectRemoval document from the detectionRemoval.cpython-36m-x86_64-linux-gnu.so ?

OK thanks a lot ------------------ 原始邮件 ------------------ 发件人: ***@***.***>; 发送时间: 2022年9月2日(星期五) 中午12:08 收件人: ***@***.***>; 抄送: ***@***.***>; ***@***.***>; 主题: Re: [saic-mdal/lama] can this code run in the Windows system？ (Issue #148) i think...

thanks a lot，im going to try it！ ------------------ 原始邮件 ------------------ 发件人: "Megvii-BaseDetection/YOLOX" ***@***.***>; 发送时间: 2022年3月8日(星期二) 中午11:13 ***@***.***>; ***@***.******@***.***>; 主题: Re: [Megvii-BaseDetection/YOLOX] how to show the Recall curve after training, it seem that no about...

im so sry... Could you be more specific, please? Still a little confused about how it works...

thanks for your reply! But ..just support coco format? My dataset format is Voc ,and I don’t see some information about AR in voc_evaluator.py.  thanks again！ 发自我的iPhone ------------------ Original ------------------...