Speedup Texture to Tensor conversion using Burst/ComputeShader
Is your feature request related to a problem? Please describe.
Currently, only the float input is handled by ComputeShader in TextureToTensor.cs.
We can optimize all types of input tensors by using Burst Compiler or ComputeShader.
https://github.com/asus4/tf-lite-unity-sample/blob/a6a514f2c6e66eab005e55c158bc2afd7ca0efd4/Packages/com.github.asus4.tflite.common/Runtime/TextureToTensor.cs#L38-L66
Additional context
Reference: https://github.com/Unity-Technologies/UnityTextureAccessApiExamples
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.