-
Part of the appeal of using neural networks for real-time detection is their comparatively small compute footprint. Any publication on their efficacy should show this explicitly by showing how through…
-
### Question
While trying to deploy the NER model, often the length of the generated token sequence can not be controlled even though the characters can be limited.
- With that said, I tried to l…
-
When I use the command `sh configs/inference/run.sh`, this error occurs:
```
Traceback (most recent call last): …
-
### Describe the issue
I covert my torch model to onnx, **it is ok**. Then I use my onnx model with
`onnx_model=onnxruntime.InferenceSession("model.onnx")`
and it is error :
```
Traceback (mos…
-
/root/miniconda3/envs/ISNet-cu118/lib/python3.8/site-packages/torch/nn/_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='mean' instead.
warnings.…
-
### Model Series
Qwen2.5
### What are the models used?
Qwen2.5-14B-Instruct-AWQ (and maybe the origin one)
### What is the scenario where the problem happened?
Qwen2.5 14B can't stop ge…
-
paddlepaddle2.1.1-cpu版 paddleclas
用的模型和数据为：https://github.com/PaddlePaddle/PaddleClas/blob/release/2.2/docs/zh_CN/tutorials/quick_start_recognition.md中给出的
识别一张图在：
1、win10下（pc机）：
Inference: 2525…
-
Firstly, I build the model_b1_gpu0_int8.engine file with calibration, and I got the calib.table file.
Then I need to build other batch size of .engine file for different batch inference. Do I need t…
-
Hi. I have a problem with the shape of features.
The Soccernet features I can download have a shape of (2700, 8576), but I do inference of a video I get a shape of (batch_size, 1, 768), being batch…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues and checked the recent builds/commits
### What would your feature do ?
I think I have devised an easy path to mult…