sxj731533730
up 好像正在修复这个错误，让nihui大佬歇歇在改，哈哈，你可以试试mnn， 我试了mnn 可以转swin transformer 模型，推理也正确 https://blog.csdn.net/sxj731533730/article/details/122601993
https://blog.csdn.net/sxj731533730/article/details/120973084 最后一步修改比较粗暴 但是可以使用
我的7.2 没有问题
> 请问你解决这个问题了吗？可否提供一些建议，我也是tensorRT 7.0 https://blog.csdn.net/sxj731533730/article/details/121152327?spm=1001.2014.3001.5501
i have solved this problem ,you need run the blow command; sudo su export PATH=/usr/local/cuda-11.1/bin:/usr/local/cuda/bin:$PATH pip install pycuda fininally, you can use the pycuda to run pyj-tensorrtCenterface in root https://blog.csdn.net/sxj731533730/article/details/121152327
因为写入txt 必须是字符类型， 才可以写入
哦 请关闭吧，应该是我转自己数据集问题，我为了修改了你的代码去适应了我的数据集，不该提pull request
将新建的三个文件中的所有network返回类型改成network_state
when i want to test MobileNetv2-SSDLite using my ***.models, i encounter " Check failed: target_blobs.size() == source_layer.blobs_size() (1 vs. 0) Incompatible number of blobs for layer ***" problem, i keep...