Maarten Vandersteegen

ONNX->"TensorFlow Lite micro" fundamentally broken because of transpose operations

8

**Problem** In my usecase, I need to port a model (only containing conv, relu and maxpool layers) from PyTorch to TensorFlow Lite micro, using the following conversions: PyTorch->ONNX->TensorFLow->Tensorflow Lite micro....

English download link?

2

The pre-trained weights download link links to a 'baidu download' server in Chinese. I'm not able to read Chinese and don't know how to proceed for downloading. Could you please...

I was wondering if the real source code of graffitist is going to be released in future versions, rather than the byte-compiled python code and shared object files. This would...

TFS: User Y has started a build while actually user X did that

2

Version 2.2.0 on TFS SirenOfShame links the wrong person to who started a build. On the TFS webpage, the user who triggered the build is correct. Also the 'checkin' message...

Hi, Was trying to reproduce your results. You have the .prototxt files included in the repo, but could you describe what the steps are you took to generate the .caffemodel...

Deleting channels with TF V2.4.0 and onwards breaks

2

Hi, I tested your repo with the included lenet.py example and this works fine up until and including TF V2.3.0 (I use tf.keras). I also tried TF V2.4.0 and V2.5.0...