yiyi-today
yiyi-today
您好，我对您的论文非常感兴趣。您的论文训练时提到“模型在 ImageNet 预训练的 ResNet-18上进行了微调”，请问您具体的微调，是将 ResNet-18特征提取的模型与自己的模型联合起来重新训练，还是将 ResNet-18的某些层冻结后与自己模型联合起来训练？这对我非常重要，非常希望得到您的回答，谢谢！
你好，我对你的论文非常感兴趣。但我学习阈值分割距离图时，遇到了一些困难。请问固定阈值应该怎么选择？
I am very interested in your paper. But when it comes to accuracy assessment, I have some problems. You used "prfs(labels.data.cpu().numpy().flatten(), cd_preds.data.cpu().numpy().flatten(), average='binary', pos_label=1 in train )" for accuracy evaluation,...
Is your proposed method based on a classification method or a Metric-based method? looking forward to your reply, and it is very important to me. Thank you.
您好，我对您的论文非常感兴趣。由于我刚入门，在理解计算预测图时遇到了一些问题，如标题，cd_preds是模型处理得到的结果，cd_preds的维度是[1(B), 2(C), 256(H), 256(W)]，torch.max(cd_preds, 1)是取cd_preds在维度【2(C)】上的最大值，得到了维度为[1,256,256]最大值_和索引号（非0即1）cd_preds1，并将cd_preds1作为最终的预测结果。请问上述我的解析正确吗？cd_preds1作为最终的预测结果的依据是什么？非常希望得到您的回答，谢谢！
**  **I have some questions about 'Criss-Cross Attention'. Here should be C×W×H or C×H×W in the place marked by the red circle？**  **At the same time,** **I have...
You recommend using thop (https://github.com/Lyken17/pytorch-OpCounter) to calculate FLOPs, but the official example of pytorch-OpCounter calculates MACs, does MACs(G)=FLOPs？In addition, why is the Params I calculated slightly different from yours? FC-EF:...
ESRGAN: What type of discriminator is used in the relative discriminator? From your paper, the discriminator type is the same as SRGAN, but it seems different from VGGStyleDiscriminator in discriminator_arch.py...
In 3.1 Spatial Path, there is a sentence "Based on this observation, we propose a Spatial Path to preserve the spatial size of the original input image and encode affluent...
Is your proposed method based on a classification method or a Metric-based method? looking forward to your reply, and it is very important to me. Thank you.