Nikita Misiura

Having the same issue with similar setup. Looking a bit more into this I see that the output from prepare does not seem right: tf_rep.tensor_dict and tf_rep.graph are just empty....

Seems like I was able to solve this problem by explicitly setting opset_version and dynamic_axes when saving from torch to onnx: torch.onnx.export( model, image, onnx_file, input_names=["input0"], output_names=["output0", "output1"], export_params=True, opset_version=12,...

Are you looking to create a starmask? It's just a difference between original and starless images!

Wait, what code do you use and what TF version do you have? The code in the jupyter notebook uses TF 2.x. There are two versions of the code in...

Adrian, Yeah, you are a bit wrong about jupyter notebooks - those are actually a nice way to run python code. You should look it up - long story short...

Nice! Thank you! I will be sure to check it out ASAP! One problem though is that only small part of the community has the skills to even run Docker...

This solved the problem for me!

Hi! This is a very complicated topic that you just can't hope to describe in a single comment. Answering your specific questions, I'd 1. Keep the image I have as...

What exactly you're trying to download that does not work? Send the link pls. Everything works fine on my end...