Amin
Amin
Thanks for explanation. I think the cause you described is correct, in other words, latent variables mainly affect their responsive pixels in the output but they have a wide receptive...
@zhuochenKIDD Are you suggesting that I fix the TensorRT warning and the problem with *Non-Converted Ops* will get resolved automatically? @LakshmiKalaKadali Hi, and thanks for the response. I've converted the...
@pkgoogle Thanks for the response. I'm a bit confused: What was supposed to happen in the course of the conversion? The conversion is basic, i.e., no quantization and just having...
@pkgoogle Yes, now things make more sense to me. Still, it leaves me wondering why I'm getting the "non-converted operations" message even in this situation where I'm not using any...
Running the same code with TensorFlow version 2.16.1 outputs: ``` 2024-05-10 08:16:11.827293: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT 2.16.1 WARNING: All log messages before absl::InitializeLog() is called are...
Hi @pkgoogle, and thanks a lot for your answer. While your workaround might help some people reach their goals, my project is much larger than the simple example I've used...