DRENet icon indicating copy to clipboard operation
DRENet copied to clipboard

The official implementation of DRENet (Degraded Reconstruction Enhancement Network) for tiny ship detection in remote sensing Images

Results 23 DRENet issues
Sort by recently updated
recently updated
newest added

Hi, I tried to train Drenet Model with Pytorch version 1.9.0 but I've got this error : Traceback (most recent call last): File "C:\Users\pauli\Documents\Detection_boat\DRENet\DRENet\train.py", line 521, in train(hyp, opt, device,...

Traceback (most recent call last): File "/home/leo/Desktop/small_object/DRENet/detect.py", line 176, in detect() File "/home/leo/Desktop/small_object/DRENet/detect.py", line 73, in detect pred = model(img, augment=opt.augment)[0][0] File "/home/leo/anaconda3/envs/revolution/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl return self._call_impl(*args, **kwargs)...

您好,陈学长: 国庆节快乐!在假期的时候冒味打扰您了,我代码在pycharm里能运行出来,但由于我电脑算力不行,我放到了云服务器上,用vscode运行,遇到了这些错误 ![image](https://github.com/WindVChen/DRENet/assets/37563989/a5af7a2c-8f68-4906-9bdf-df7031c6165c) 请问这些该如何解决,谢谢!国庆节快乐!

您好,我的数据是768*768,。请问我把concat替换为concatFusionFactor后,运行yolo.py,报如下的错误。应该还要改哪些地方呢? D:\ProgramData\Anaconda3\envs\py38\python.exe D:/1bishe/yolov5-master2/models/yolo.py models\yolo: cfg=yolov5s-biformer2-scale.yaml, batch_size=1, device=0, profile=False, line_profile=False, test=False YOLOv5 2023-12-11 Python-3.8.18 torch-1.13.0+cu117 CUDA:0 (NVIDIA GeForce RTX 3060 Laptop GPU, 6144MiB) from n params module arguments 0 -1 1...

您好,从图中可以看到,我将所有尺寸都设置为640,然后只使用了您的CRMA添加到原生的yolov5 5.0版本中,yaml文件也做了相应的修改,但是还是在验证的时候报了错误,想问一下有可能是什么原因导致? ![val](https://user-images.githubusercontent.com/72743157/226622112-9aaf297e-45a1-4b8b-ad5b-e1d578dd370c.png) ![yaml](https://user-images.githubusercontent.com/72743157/226622127-0cdf67f0-3fbb-41bf-b238-c32a3c750833.png) ![yolo](https://user-images.githubusercontent.com/72743157/226622132-b6e64430-ab83-43ee-b483-24146082c921.png) ![train](https://user-images.githubusercontent.com/72743157/226622032-b0de10d6-620d-42e9-b180-a4580d18e766.png)

师兄您好!有幸阅读了您的论文。想请教两个问题: 一、由于我尝试过直接使用MHSA加入C3中,然后分别将C3-MHSA模块加入到和您的网络差不多的位置,但是发现显存占用很大。而您的模块加了那么多个地方是因为每次使用都把通道数降低了的,从而可以降低显存占用是吗?如下图,head中第一个C3ResAtnMHSA模块,输入512通道,输出32...... 二、我如果直接使用您这个C3ResAtnMHSA模块将入到我的yolov5s改进的网络中,除了修改common和yolo的那两个文件以外,还有别的地方需要修改吗?我的输入图像是768大小的,就会报错。 ![1](https://github.com/WindVChen/DRENet/assets/102776858/2a7895dc-9790-400f-bc8f-32ce0b876e90)

老师学长您好: 请问咱们这个网络在test或者detect中能不能生成标签啊,就是我想不仅要识别还想要定位。 感谢老师学长的解答

Why does detect.py have no results

您好学长,这里其他的对比模型没用写出来吗?比如ssd这些配置文件没用在代码里面吗?

Hello Chen, Thank you very much for taking your time to answer me! I appreciate! When I run the training code train.py, I had the error: Image sizes 512 train,...