fonnx
fonnx copied to clipboard
Telosnex
ONNX runtime for Flutter.
can you please add any upscaling gan model inference code example? or try this model [4xSPAN](https://drive.google.com/file/d/1BIiHr5JI-QhQHXWU9QPNqVkMCGg1Y3So/view?usp=sharing) if anyone success, then please drop the code below, i
https://github.com/Telosnex/fonnx/blob/ac30c6fa2bb7f35fcd389b0c421559414b72064b/lib/extensions/vector.dart#L7 Hello, Being an author of ml_linalg library, I found an error here. In fact, `1-*` is already considered in `Vector.distanceTo`: https://github.com/gyrdym/ml_linalg/blob/027ddfab120b1e2d0c4d6b676c31e62615ce2374/lib/src/vector/float32x4_vector.dart#L521 P.S. Your library is awesome!
Hey, I have an app on macos which includes fonnx. After building this app and signing it using codesign, it crashes on startup. It complains about an invalid signature for...
Please give an example how to inference image with pre-trained *.onnx model using your package? Thanks in advance
# Preface I ran the tests on Linux. In both cases, the encoding is probably too long. ## V2 لفشل وشعار بالرّغم. دون مع الهجوم السادس أوراقهم, و أخذ رئيس...
Is there any chance to support newer models? For example, [https://huggingface.co/jinaai/jina-embeddings-v3](https://huggingface.co/jinaai/jina-embeddings-v3) [https://huggingface.co/Snowflake/snowflake-arctic-embed-m-v2.0](https://huggingface.co/Snowflake/snowflake-arctic-embed-m-v2.0) I tried to replace the onnx file and got following error. ``` Opset 5 is under development and...
from txtai.pipeline import HFOnnx # 模型路径 path = "openai/whisper-small" # 将模型导出为 ONNX onnx = HFOnnx() model = onnx(path, "default", "whisper-small.onnx", True) Traceback (most recent call last): File "/root/test.py", line 8,...
1.optimum-cli export onnx --model openai/whisper-small onnx_model/ --monolith 2.optimum-cli onnxruntime quantize --onnx_model onnx_model/ --arm64 -o quauntized_model/ E/[OrtWhisper.kt]( 6184): Error in getTranscription: Error code - ORT_NOT_IMPLEMENTED - message: Could not find an...
There is some model that the input is `tensor: string[unk__1550]` there is no call for createTensor as String, I only found the int and float Tensor  using this Model:...
