deep-learning-for-image-processing
deep-learning-for-image-processing copied to clipboard
deep learning for image processing including classification and object-detection etc.
只在predict.py程序中添加部分代码,没有改动作者的其余代码,同时结合下面这个链接的教程进行实验。我将作者的voc2012的权重加载到predict中,同时将教程中的部分代码加入其中进行实验,发现目标bbox能够正确绘画,但是CAM的结果很奇怪。CAM的结果对于目标部分并没有体现高亮的情况,而非目标的部分即背景反而被高亮了。目前不知道具体原因,求助!! https://github.com/jacobgil/pytorch-grad-cam/blob/master/tutorials/Class%20Activation%20Maps%20for%20Object%20Detection%20With%20Faster%20RCNN.ipynb 实验结果是这样的很奇怪  
请问Vit-pytorch中位置编码怎么实现的呢?好像没有看到position呢?谢谢!!!!
**System information** * Have I written custom code: Yes * OS Platform(e.g., window10 or Linux Ubuntu 16.04): Linux * Python version: 3.8 * Deep learning framework and version(e.g., Tensorflow2.1 or...
**System information** * Have I written custom code: * OS Platform(e.g., window10 or Linux Ubuntu 16.04): * Python version: * Deep learning framework and version(e.g., Tensorflow2.1 or Pytorch1.3): * Use...
**Describe the current behavior** 我在使用网络做分割任务时,CEloss的结果比BCEloss结果更好,请问这个是有什么讲究吗?因为我映像中二分类任务一般使用BCEloss,那么我用CEloss处理二分类任务是不是很奇怪?
Hi, Your repository is very helpful. I was trying to run the Unet model for the multiclass dataset, where every class is labeled with different colors to generate masks. But...
**System information** * Have I written custom code: NO * OS Platform(e.g., window10 or Linux Ubuntu 16.04):window11 * Python version:3.8.13 * Deep learning framework and version(e.g., Tensorflow2.1 or Pytorch1.3):pytorch 1.3...
非常好的项目,感谢我导!! 但是我的生成图片只有bbox没有mask,想请问一下导师要在哪里修改 
  博主您好,我在运行你的faster_rcnn代码的时候,运行train_res50_fpn.py报错,RuntimeError: CUDA out of memory. Tried to allocate 476.00 MiB (GPU 0; 9.77 GiB total capacity; 7.69 GiB already allocated; 242.69 MiB free; 7.92 GiB reserved in total...
Bumps [onnx](https://github.com/onnx/onnx) from 1.13.0 to 1.16.0. Release notes Sourced from onnx's releases. v1.16.0 ONNX v1.16.0 is now available with exciting new features! We would like to thank everyone who contributed...