Elin

[OS] Why the function of cpu_freq() always getting the cpu default freq?

1

## Summary * OS: Windows11 Home * Architecture: 64bit * Psutil version: 5.8.0 * Python version: 3.9.7(Base on Conda) * Type: BugIssuses ## Description Yeah,pretty confusing that i wanna using...

Why my model export into TensorRT engine but response with an OS Error?

2

### Search before asking - [X] I have searched the YOLOv5 [issues](https://github.com/ultralytics/yolov5/issues) and [discussions](https://github.com/ultralytics/yolov5/discussions) and found no similar questions. ### Question Hi,i want export my self trained model into TensorRT...

Does this issue occur when all extensions are disabled?: Yes/No - VS Code Version: 1.80.0(from command code --version) - OS Version: WSL2 Debian bullseye under Windows11 22H2 Steps to Reproduce:...

[Question & FeatureRequest] Is that possible to convert a torch.nn.Module to TRTMoudle?

1

For example,i got a module class which based on `torch.nn.Moudle()` like this: ```python model = VALLE( N_DIM, NUM_HEAD, NUM_LAYERS, norm_first=True, add_prenet=False, prefix_mode=PREFIX_MODE, share_embedding=True, nar_scale_factor=1.0, prepend_bos=True, num_quantizers=NUM_QUANTIZERS, ).to(device) ``` Is that...

At chap7 Attention RNN training period,here i follow the book to build the model looks like this: ```python notes_in = Input(shape=(None,)) durations_in = Input(shape=(None,)) embedded_size = 100 rnn_units = 256...

Hi there,i'm trying to export VALL-E model into ONNX. To achieve this goal,i have done these things: First,i extract the `promptlang2id()` and `textlang2id()` functions like below: ```python import numpy as...

Hi,i have seen that the basic model of `VALLE` doesn't implement `forward()` function,is that possible to just write infercen code into `forward()` function to make it possible to convert into...

[QUESTION] Invalid data type of cvcuda.nms() function

3

**What is your question?** Here is the question:the `cvcuda.nms()` function from [documentation here](https://cvcuda.github.io/modules/python_modules.html?highlight=nms#cvcuda.nms) need those below attributes to calculate: - src boxes Tensor : `nvcv.Tensor` - scores Tensor : `nvcv.Tensor`...

I found that the output gguf models are not in `chat mode` already? Isn't it? I want to build an agent framework with BitNet,but the model is limited. : (

尝试将torchcrepe前后处理算子合并进来后，导出的ONNX图全没了

2

我想把CREPE的完整计算过程包装为一个ONNX模型，使用了如下代码： ```python from torchcrepe.core import preprocess,postprocess import onnxruntime as ort class TorchCREPE(torch.nn.Module): def __init__(self,model): super().__init__() self.hop_length = 512 self.fmin = 50 self.fmax = 1100 self.sample_rate = 40000 self.model = model...