Skyninth

Results 4 comments of Skyninth

作者您好，请问NWD损失常量参数为什么设置为1？

同问，想知道这个常数是怎么根据数据集算出来的，能提交一下代码吗

你好，我在yolov5 7.0版本添加了yolox的代码，现在的情况是cls loss不断上涨，导致map一直为0没有结果，请问这个库可以跟随官方更新至最新的7.0版本吗

ok，问题解决了

ImportError: .local/lib/python3.8/site-packages/DCNv3-1.0-py3.8-linux-x86_64.egg/DCNv3.cpython-38-x86_64-linux-gnu.so: undefined symbol: _ZN2at4_ops10select_int4callERKNS_6TensorEll

same problem while using torch==1.10.1+cu111, and ImportError: /~/python3.8/site-packages/DCNv3-1.0-py3.8-linux-x86_64.egg/DCNv3.cpython-38-x86_64-linux-gnu.so: undefined symbol: _ZN2at4_ops5zeros4callEN3c108ArrayRefINS2_6SymIntEEENS2_8optionalINS2_10ScalarTypeEEENS6_INS2_6LayoutEEENS6_INS2_6DeviceEEENS6_IbEE

Inference of mask2former on large images

same problem!! I want to try beit in mask2former, and I set the image size(896,896),and test_cfg=dict(mode='slide', crop_size=(896,896), stride=(640, 640)), train and test pipline is dict(type='Resize', scale=(896, 3584), keep_ratio=True), then get...