-
```
hi,
我想让分词器碰到《传奇3》、“传奇3”等这种词的时候，《
》内部的就不继续分词，而是让内部作为一个词语。
请问这在哪里可以修改一下？
```
Original issue reported on code.google.com by `sling...@gmail.com` on 17 Dec 2013 at 5:37
-
```
hi,
我想让分词器碰到《传奇3》、“传奇3”等这种词的时候，《
》内部的就不继续分词，而是让内部作为一个词语。
请问这在哪里可以修改一下？
```
Original issue reported on code.google.com by `sling...@gmail.com` on 17 Dec 2013 at 5:37
-
```
hi,
我想让分词器碰到《传奇3》、“传奇3”等这种词的时候，《
》内部的就不继续分词，而是让内部作为一个词语。
请问这在哪里可以修改一下？
```
Original issue reported on code.google.com by `sling...@gmail.com` on 17 Dec 2013 at 5:37
-
```
[W reducer.cpp:347] Warning: Grad strides do not match bucket view strides. This may indicate grad was not created according to the gradient layout contract, or that the param's strides changed s…
-
由于没有留邮件，所以我只好发一个Ticket了。我想问一下mmseg4n的效率有多少？我自己才写了一个mmseg的node实现 https://github.com/mountain/nseg
我的这个版本，在我自己的机器上（Intel i3 2.40MHz），效率大概在每秒切分2～3万个词，还是比较低的。相应的C的版本的libmmseg据说可以到50万，不过C的版本没有丰富的词法分析功能，也不…
-
Hi, I've faced a problem when training the model which contains 2 classes, i.e., 'bg' and 'corrosion'. Most of the pixels are bg (background).
the first 100 iterations I got this performance metri…
-
I am trying to convert '.pth' file that generated by publish_model.py to pt file.
and get the errors :
traced_script_module = torch.jit.trace(checkpoint, example, check_trace=False)
File "/ho…
-
Hello,
I am using mmseg version 1.2.2.
I sincerely wonder how to get the validation loss and the accuracy score in the training step.
I found the `val_step` function was not in the` base.py` in…
-
您好，我想在inference的时候将得到的result与gt计算miou等相关指标。现在我使用在potsdam上预训练的权重，在potsdam的验证集上进行推理，然后使用../mmseg/core/evaluation/metrics.py，计算得到的{'aAcc': array(0.04249801), 'IoU': array([0.06536244, 0.00681113, 0.00367…
-
Does mmseg currently support saving checkpoints to Weights and baises ?
I have been using WandbVisBackend for visualisation though.