open-alcnet
open-alcnet copied to clipboard
codes and trained models for the ALCNet
mxnet报错
OSError: libnccl.so.2: cannot open shared object file: No such file or directory 换了几个版本,一直报这个错,各位大侠有遇到吗,怎么解决的?
Hi Dr. Dai, I have seen your wonderful work on infrared small target detection. I'm wondering if your model could be applied on other infrared images like thermal frames for...
代码运行报错
1. 在运行visualize_local_contrast_networks.py时报错: Traceback (most recent call last): File "visualize_local_contrast_networks.py", line 254, in trainer.validation(0) File "visualize_local_contrast_networks.py", line 227, in validation pred = self.net(exp_img) File "/mistgpu/site-packages/mxnet/gluon/block.py", line 682, in call out =...
您好,我在尝试使用您的代码进行训练时发现,虽然论文以及github的readme里都是使用的SIRST数据集,但是在train_alcnet.py中数据集设置里默认值却是DENTIST和Iceberg,contrast.py里有对数据预处理的代码,也是针对这两个数据集的,我尝试自己修改但是遇到了其他的问题。 train_alcnet.py的参数设置里,选择的是PCMNet,但是只提供了MPCMResNetFPN和ResNetFCN的初始化代码,我尝试直接修改net_choice=‘MPCMResNetFPN’以及从model中导入PCMNet,但是代码都卡在了model.initialize(init=init.MSRAPrelu(), ctx=args.ctx, force_reinit=True),请问该怎么办呢,能不能整理一份可执行的代码,非常感谢
请问论文中定义的nIoU是针对与二值图像吗?而论文中IoU实际就是softIoU得出的值吗???就是IoU针对的是最后获得的预测概率图,未进行阈值处理成二值图像??
## Beep boop. Your images are optimized! Your image file size has been reduced by **82%** 🎉 Details | File | Before | After | Percent reduction | |:--|:--|:--|:--| |...