Wei Wei

Results 36 comments of Wei Wei

This section should help: https://www.tensorflow.org/recommenders/examples/basic_ranking#testing_the_ranking_model

The fact that both GPU's memory are saturated means it is using both GPUs, just not efficiently. Did you get a warning like this "WARNING:tensorflow:Efficient allreduce is not supported for...

I'm also trying to reproduce the results in the paper. I also had issue getting the same level of quality (PyTorch official example repo also has an implementation; quality isn't...

Unfortunately no. I have tried half a dozen TF/PyTorch implementation on GitHub. None of them could get even close to what was reported in the paper.

直接用OpenCV好了,已经有训练好的ESPCN https://docs.opencv.org/master/d9/de0/group__dnn__superres.html

+1 I'm trying to convert a policy to TFLite and hit the same error. Not being fully 'Saved Model' is a real barrier.

Just tried nightly. Didn't work.

I can convert the model now. Thanks for @thaink 's work.

For vector similarity search, I think you can maintain your own repo (w/o being coupled to Serving), right? It's how Google's ScaNN has done it anyway.