Wrong input size at converting and wrong ineference values on popular models (SD, Whisper) about mnn HOT 3 OPEN

An update to this, i have been able to solve the dinamic axis by doing resizeTensor and resizeSession correctly. but the output of the model is too offset from the original one (and exporting the model with fixed dinamic inputs is even worse). it would be nice why, but i have no idea where to look at (and debug options doesn't give me a hint of where the problem could be).

from mnn.

I too have faced low quality outputs after conversion, but for another application: wangzhaode/mnn-llm#150

It probably comes down to the quantization algorithms available on MNN.

from mnn.

An update to this, i have been able to solve the dinamic axis by doing resizeTensor and resizeSession correctly. but the output of the model is too offset from the original one (and exporting the model with fixed dinamic inputs is even worse). it would be nice why, but i have no idea where to look at (and debug options doesn't give me a hint of where the problem could be).

For Onnx models, can use "testMNNFromOnnx.py" to review the converted MNN model outputs.

from mnn.