Lufei-github
Lufei-github
Sorry to bother you again!!! I do some ablation experiments for this paper. But I found some strange results. Firstly, I run your original code for GTA5->Cityscapes. I got the...
尊敬的徐学长，你好！一个小小的问题。您肯定有做过attention机制的消融实验吧！额，请问下您的attention机制能带来多少的精度提升呢？
You say "We concatenated the respect label map with RGB image of corresponding size along class channel as a strong condition to discriminators." But I really don't understand why you...
你好 我发现测试代码首先会在test.py中model = MainNet()处加载预训练模型 (config.py中pretrain_path = './models/pretrained/resnet50-19c8e357.pth'） 然后会在test.py中的epoch = auto_load_resume(model, pth_path, status='test')，又加载一次你训练的模型 那可不可以只加载最终的模型，而不用加载预训练模型呢？
作者你好，我在训练完模型后将其转化为onnx，运行pytoch2onnx后便得到了yolo-fastestv2.onnx。为了验证onnx是否转成功，我利用该转换后的.onnx去读取图片： net = cv2.dnn.readNetFromONNX("yolo-fastestv2.onnx") image = cv2.imread("6826.img") blob = cv2.dnn.blobFromImage(image) net.setInput(blob) out = net.forward() 报错显示cv2.error in function cv::dnn::computeShapeByReshapeMask 然而我用同事转换成功的resnet18.onnx却不会报错 想要请教你遇到过这个问题吗？该如何解决呢？
Both the adv_target_loss and mse_loss are useful for the target images' training,but how to balance the weight of the two?Have you done any experiments or any deep insight in this...
What a wonderful job! And I have a question! Your remove_anything.sh command support give a point to obtain 3 segmentation masks, then use the LaMa to remove it! But as...
一个想法
设计一个车牌检测网络，同时设计出具有分类和回归的能力。回归能力已经具备了！ 是否可以设计出具有多分类的能力？ 比如对车牌单双层分类，对车牌颜色分类，对车牌属于车头车尾分类？而不是在检测时枚举出所有可能的类别，单层_蓝牌_车头_车牌、双层_黄牌_车尾_车牌等等