DeepCrack issues

Testing the pre-trained model

1

I'm trying to test the pre-trained model on some images. What is the input of the model in test_index.txt? The path in train_example.txt is like: /home/yueyuanhao/deepcrack/data/CrackTree/crack_train_image/6192_rot0_crop1_mirror0.jpg /home/yueyuanhao/deepcrack/data/CrackTree/crack_train_mask/6192_rot0_crop1_mirror0.png Do we need...

hamza233

ZeroDivisionError: division by zero

7

hi, i recently tried to run DeepCrack to identify my target, but i faced some problem. The error message is shown below. i think it seems like it didn't read...

ycc66104116

Questions about calculating accuracy in training

In the paper, it is mentioned that adding a sigmoid to the feature map output by the network can convert the feature map into a crack prediction graph. Then I...

plastictime

data annotation

Hi, I'd like to know whether the cracks are annotated as lines (e.g polyline in ESRI ArcGIS) or polygons. It seems that some thin cracks are unsuitable to be annotated...

ShamirC

您好，请问可以提供测试集上的结果吗

3

我们也在做相关的研究，您给的预训练模型无法达到您的最佳结果。所以我们希望可以获得你们在测试集上的最佳结果用于方法之间的对比。谢谢。

zhuhaonan

err when calculate loss in val_op in trainer

hi, I saw a error in val_op when calculate the loss, you take loss devided by cfg.train_batch_size(which is defined as 8 in cfg), but this step is calculate the validation...

moxx799

I encountered a problem about socket connection failure.

4

I don't know why I encountered this kind of problem. I checked the code and found that there is no code related to socket. Is it because the communication between...

JasonChenhx