Hello, may I ask if I can use pictures of other sizes for training about retina-vesselnet HOT 8 CLOSED

The author hello, is it convenient to add your WeChat consultation
My E-mail 1165269652 @qq.com

from retina-vesselnet.

I tried to train with a new dataset and different size, it worked well. Remember to change the settings in the segmentation_configs.json file.

from retina-vesselnet.

我尝试使用新的数据集和不同的大小进行训练，效果很好。记住要更改segmentation_configs.json文件中的设置。

好的，谢谢，请问您训练的时候loss和准确率能到多少，我110张图训练了120epoch，两个类别。测试效果不太好，loss=0.3703，准确率百分之五十一左右，请问有什么方法可以用来改进效果，谢谢

from retina-vesselnet.

I trained on the HRF Dataset (45 pictures) for 20 epochs, and achieved an loss~0.12 and an train/val-Accuracy of ~0.95/94.
On what data are you training?

from retina-vesselnet.

我在HRF数据集（45张图片）上训练了20个时间段，损失约0.12，火车/阀门精度约0.95 / 94。
您正在训练什么数据？

您好，我训练的是自己的数据集，想问问您标签是程序自动标注的还是labelme标注的呢，预测结果出来后如何知道血管信息的具体位置呢，谢谢

from retina-vesselnet.

I dont know if i got you right, but you need to generate the masks and the GT-data on your own. The code wont do this for you. Sorry if this does not help you. Using google Translate...

from retina-vesselnet.

我不知道我是否正确，但是您需要自己生成遮罩和GT数据。代码不会为您这样做。抱歉，如果这样对您没有帮助。使用谷歌翻译...

谢谢，现在我的loss降到0.022左右了，可是分类精度依然是0.52/0.53左右，请问是不是我的标签转换问题，您制作自己 的数据集标签的时候是如何制作的呢，我的邮箱[email protected]，谢谢

from retina-vesselnet.

I have update the code. You can find the method on the jupyter notebook. if you still have the problem, open the issue again

from retina-vesselnet.