-
## I have a question
I create a model with some transition and emission probabilities. Then I generate a sequence using the model:
`gen_seq, hidden_states = gen_model.sample(num_obs)`
Then I pr…
-
On Windows 10 using WSL I'm trying to run:
```
~$ colabfold_batch --amber --templates --num-recycle 3 --use-gpu-relax --model-type AlphaFold2-multimer-v2 PDBID_6IWD.csv outputdir/ --cpu
```
us…
-
欢迎您反馈PaddleNLP使用问题，非常感谢您对PaddleNLP的贡献！
在留下您的问题时，辛苦您同步提供如下信息：
- 版本、环境信息
- 使用AIStudio GPU
1）PaddleNLP和PaddlePaddle版本：PaddleNLP 2.3.4，PaddlePaddle 2.2.2.post101
2）系统环境：python3.7.4
- 复现信息：如为报错，请给出复现…
-
Here are three topics related to the postprocessing methods.
## 1. Why use sigmoid here?
https://github.com/maxrmorrison/torchcrepe/blob/9aecc86f5f3ef908bd75656368639686480800e0/torchcrepe/decode.…
-
@nilsroth HMM branch is merged ;) The only thing missing is a little bit of docu about your pre-trained model.
I.e. what dataset was it trained on, what specifications, what to expect with regards…
-
您好：
wordtag = Taskflow("knowledge_mining", model="wordtag", device_id=3,task_path="./custom_task_path/",linking=False)
指定显卡序列3
但在程序运行时仍然要判断0号显卡
Please check whether there is any other process u…
-
Original [issue 93](https://code.google.com/p/cleartk/issues/detail?id=93) created by ClearTK on 2009-04-30T13:59:54.000Z:
right now the constructors for the classifiers require a jar file. This is
n…
-
初始化已解决，原因在于如使用ErnieModel需要初始化vocab_length参数，直接使用预训练模型可解决
```
ernie = ErnieModel.from_pretrained("ernie-1.0")
model = Model(ernie)
```
现问题在于crf层正向计算出现参数类型不适问题
-
When you're done, write your takeaways from the chapter in a comment on this issue, then remove yourself as an Assignee. Last one to do so closes the issue.
-
Hi,Thank you for this perfect code,and I have learned a lot from this code.But when I run this code,I get one problem ：
`Traceback (most recent call last):
File "main.py", line 438, in
train…
ghost updated
2 years ago