André Pedersen

I would recommend printing all node names to debug this further. To print all, try [this](https://github.com/onnx/onnx/issues/2657#issuecomment-618659414). Also, from [this thread](https://github.com/onnx/onnx-tensorflow/issues/1003#issuecomment-1122321192), I had success converting a pytorch model -> onnx ->...

> Triage notes: Probably related to that the keras.applications models do have `compute_output_shape` implemented on the model. I'm quite sure that is the case. I am just wondering why this...

@chenmoneygithub Any update on this? I was planning on using the new architectures with TimeDistributed in a study, but I am unable to until this is solved.

> @andreped a fix for this was pushed yesterday. @hertschuh: Just tried running the [test script](https://github.com/keras-team/keras/issues/16656#issue-1261037447) above using the nightly build. No errors prompted for any of the architectures. Brilliant!...

Might be a silly question. I am not that familiar with tf-nightly vs stable version of TF/Keras. I have often have challenges with imports when using nightly. I experienced the...

I managed to get imports somewhat working by throwing lots of `python` boys in the imports, such that `from tensorflow.python.keras import stuff`. I was able to use the methods within...

I just got an issue with TimeDistributed on one of my trainings. Everything starts and runs, but after a while it failed. This was observed using the `MobileNetV3Small` architecture in...

> * I will close this issue now, we don't keep them around until Tensorflow is released. No worries! Just close the issue. I will test the reinstall suggestion and...

If there is no plan to make a scientific publication of this project, I would suggest linking this repo with Zenodo, which enables researchers to cite this work. It would...

2D support would be of interest to me as well. I have previously experimented with RetinaNets, YOLO networks, and Faster R-CNN. Testing your design is the next step for me,...