MarkAI
MarkAI
Models of VOC dataset are evaluated with native resolutions with shorter side >= 600 but longer side
@bryanyzhu thanks for your reply. i got the bug with the code after i pull the code in the PR #1727 . i will close the #1727 and re-upload the...
@rochou @shaonfu 你们迁移到安卓端了吗
1. Use the labelme . You can get the label image. It is not related to xml file. 2. You need use add_color.py to convert the black image to color...
Traceback (most recent call last): File "train.py", line 96, in net_mem_planned = memonger.search_plan(new_sym, data=dshape) File "/home1/mxnet/memonger.py", line 141, in search_plan sym = make_mirror_plan(sym, threshold=threshold, plan_info=info, **kwargs) File "/home1/mxnet/memonger.py", line 63,...
@niufuren when i modify as you said. Can you give me some solutions. I get the error: Detection time for 1 images: 0.0639 sec Traceback (most recent call last): File...
@zhreshold i want to detect the small objects. The default boxes detect min-size in caffe is 30. how to modify the sizes of priorBox in your code ?
@newwhitecheng can you share your prototxt?
@k-miracle i have the same problem. I train resnet101+end2end, I got the high train accuracy and low loss,but only got a low test accuracy and map. img_pixel_means = (0.0, 0.0,...