-
hi, thanks for sharing the code, cloud please offer the lab2_train_data.h5 and lab2_test_data.h5 files? thanks!
-
训练每2000epoch保存一次权重，但是怎样自动保存找到最好的呢
-
您好，感谢您提供源代码，
我将Cityscapes数据集分别通过两种训练方式，train和trainval的两种方式进行了训练，然后也通过test.py进行了测试，目前对经过trainval的模型通过predict.cy和utils文件夹下的train ID2labelID.py处理后，得到result。但是不知道怎么提交到官网进行评估预测。请问您可以给出详细步骤么，万分感谢。
-
When converting PaddleSeg ENet after export to ONNX, I get the error that some operators are not supported:
```
(.venv) D:\Local\devel\Python\PaddleSeg\PaddleSeg>paddle2onnx --model_dir ENet -
-m…
-
I got a problem when i test the model with cityscapes's dataset like this. How can I solve it?
Traceback (most recent call last):
File "main.py", line 348, in
loaders, w_class, class_encod…
-
Please go to Stack Overflow for help and support:
http://stackoverflow.com/questions/tagged/tensorflow
Also, please understand that many of the models included in this repository are experimenta…
-
Hello all,
I have been going through the issues, most of it seem not less than 3 months old. So has anyone succesfully trained this network achieving near equal scores as reported in the paper.
…
-
Hi,
where can I download the prototxts and the caffemodels to initialize the DNNs available in the launch folder?
Thank you
Walter
-
I would like to ask you, using my own dataset (0 for background, 1,2,3 for foreground), it still use label=label+1 in dt_offset_generation.py on line 61？
-
Hello, I recently encountered a strange phenomenon while using the latest version of mmseg (main branch). Specifically, when I used test.py to visualize test data, I found that it only visualizes one …