980202006

Hi, when I use torch.cuda.amp.autocast, I will get an error on conv2d_gradfix.Conv2d. The weight is fp32. If I only use .half() to convert the weight to fp16, I got nan...

I just want to use dereverberation in ddsp. Can you provide a colad about dereverberation? Thank you!

Whether to check the similarity before audio storage

4

Whether to check the similarity before audio storage? Is there a simple demo for query and other operations ?

File "D:/nuoyi/biaodian/BiLSTM-CRF-ChineseNER.pytorch-master/main.py", line 141, in loss = train() File "D:/nuoyi/biaodian/BiLSTM-CRF-ChineseNER.pytorch-master/main.py", line 79, in train loss, _ = model(word, label, seq_lengths) File "C:\Users\xiongxi\.conda\envs\tf\lib\site-packages\torch\nn\modules\module.py", line 547, in __call__ result = self.forward(*input, **kwargs)...

 I have a question about this code, why do an adain transformation with the content embedding of y_target for y_source content embedding.

为什么要tagset+2

6

self.liner = nn.Linear(hidden_dim*2, tagset_size+2)

关于一些参数的问题

7

请问，args中的bi是什么含义，当我将bi设置为True的时候，运行main_without_fitlog.py,报了如下错误：（batch_size为10，数据集用的是resumeNER） Traceback (most recent call last): File "D:/work/NerAPIS/Batch_Parallel_LatticeLSTM-master/Batch_Parallel_LatticeLSTM-master/main_without_fitlog.py", line 205, in callbacks=callbacks) File "C:\ProgramData\Anaconda3\lib\site-packages\fastNLP\core\trainer.py", line 520, in __init__ batch_size=check_batch_size) File "C:\ProgramData\Anaconda3\lib\site-packages\fastNLP\core\trainer.py", line 920, in _check_code pred_dict = model(**refined_batch_x) File "C:\ProgramData\Anaconda3\lib\site-packages\torch\nn\modules\module.py",...

Error Code 4: Internal Error (Conv_1840: number of kernel weights does not match tensor dimensions)

17

## Description I found out that the required weight count is twice as in the onnx model, but it's not clear how to fix this error ``` [08/17/2022-17:06:41] [TRT] [E]...

not combining utt2uniq as it does not exist

11

Is there any problem with this