自己数据集的实现
baomimianbobo opened this issue · comments
Hello, I want to use my own data set to implement on this network. I have JPG original drawing and JSON file in my hand. How can I change my data set to adapt to the network training？
I also want to know it ! Thank you so much.
Long times had gone. Someone can help to solve this problem?
Hello, I am now trying to use my own dataset on this network, too. I have the orignal PNGs and the label, could you please tell me how to change them so that I can train them? Thank you very much for your help!
I made my own data as Cityscapes Dataset format, but my dataset only has 6 classes labeled 0-5.
I change the "self.label_mapping" in lib/datasets/cityscapes.py:
self.label_mapping = {0: 0, 1: 1, 2: 2, 3: 3, 4: 4, 5: 5}
But when I was training, the eval on val is:
[0. 0.00423967 0.35140248 0. 0. 0. ]
Could you tell me how to fix this problem? Was there anything I forgot to modify?
Hello,I am using myself dateset on this netowrk,but the code "import models" appears error.what's the reason of this.
I made my own data as Cityscapes Dataset format, but my dataset only has 6 classes labeled 0-5. I change the "self.label_mapping" in lib/datasets/cityscapes.py: self.label_mapping = {0: 0, 1: 1, 2: 2, 3: 3, 4: 4, 5: 5} But when I was training, the eval on val is: [0. 0.00423967 0.35140248 0. 0. 0. ]
Could you tell me how to fix this problem? Was there anything I forgot to modify?
i got the same problem....
Traceback (most recent call last):
File "tools/train.py", line 232, in
main()
File "tools/train.py", line 135, in main
train_dataset = eval('dataset.'+cfg.DATASET.DATASET)(
File "", line 1, in
AttributeError: module 'dataset' has no attribute 'mycoco（自己的数据集)'，请问这个报错怎么解决呀