-
### Feature request
I wonder if the task text-classification can to be supported in the ONNX export for clip? Ich want to use the openai/clip-vit-large-path14 model for zero-shot image classification…
-
It would be cool to see this model working with the Transformer.js library. 👍
-
### What happened?
It would be great if [Model2Vec](https://github.com/MinishLab/model2vec) models could be supported, e.g. https://huggingface.co/minishlab/potion-base-8M. They include [ONNX files](…
-
### Context
Neural networks are graphs consisting of nodes called operators. Each operator corresponds to a mathematical function, usually described in framework's documentation or an AI standard, …
-
### Context
Neural networks are graphs consisting of nodes called operators. Each operator corresponds to a mathematical function, usually described in framework's documentation or an AI standard, …
-
### Context
Neural networks are graphs consisting of nodes called operators. Each operator corresponds to a mathematical function, usually described in framework's documentation or an AI standard, su…
-
### What happened?
https://github.com/iree-org/iree/pull/17330 updates our LLVM and torch-mlir commits, pulling in https://github.com/llvm/torch-mlir/pull/3013. Some tests are newly passing, many tes…
-
### Describe the issue
When trying to run KBNet-S (see [here](https://github.com/zhangyi-3/KBNet)) using ONNXRuntime with DirectML, an error occurs during the creation of the session that reads:
```…
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussi…
-
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)。