-
rcs3-yolo模型无法导出onnx，报错信息为F.avg_pool2d()的kernel_size参数类型时tensor，不是int型。查询到SEBlock模块中有一个F.avg_pool2d()算子,kernel_size=input_size(3)。
-
## Why?
transformer model is probably heavy size.
onnx have multi platform support and multi language support.
Its good for me.
-
### Describe the issue
Various models result in the error:
Failed to finalize QNN graph. at location qnn_model.cc:152 FinalizeGraphs
### To reproduce
The following AI Hub jobs results in Failed t…
-
### Feature request
I am working with flash linear attention (FLA) model and aiming to process data in a frame-by-frame manner with [batch, frame, feature] input format. Additionally, I am looking …
-
## ❓ Questions
I want to convert the model to onnx and deploy it on the development board. I want to know whether the conversion is similar to the CNN model and can be directly exported through tor…
-
你好，我看您的视频内small的推理速度大约为一秒10帧，但我转换tiny模型后使用cuda加速后只有2帧，这和onnx的版本有关系吗
-
> [E:onnxruntime:Default, env.cc:228 ThreadMain] pthread_setaffinity_np failed for thread: 967793, index: 4, mask: {0, }, error code: 22 error msg: Invalid argument. Specify the number of threads expl…
-
#### Description
I am currently working on deploying the Seamless M4T model for text-to-text translation on a Triton server. I have successfully exported the `text.encoder` to ONNX and traced it …
-
### System Info
```shell
Python 3.9.16
optimum 1.13.2
Ubuntu 20.04.6 LTS
```
### Who can help?
@michaelbenayoun
### Information
- [X] The official example scripts
- [ ] My own modified script…
-
Using this snippet to save pre-trained model locally -
```
from gliner import GLiNER
model = GLiNER.from_pretrained("urchade/gliner_medium")
model.save_pretrained("gliner_medium")
```
post th…