Grigory Malivenko

Hello @emanuelcovaci @andreimihalcea97. I fixed some errors related to `slice` layer. It now works with 4 inputs (with assumption that axes are [0, 1, ... ndims] array). Unfortunatelly, @emanuelcovaci, your...

Hello @LaCandela @mengzhi2 . Unfortunately, Keras doesn't support groupped ConvTranspose2d : https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv2DTranspose In future versions I will implement this feature as I did for Conv2d (using lambdas).

Hello @lawo123 . 1. `v0.0.5` is very old, please, try the recent versions 2. 'CUDA driver version is insufficient for CUDA runtime version' means you try to use CUDA version...

hello. You try to import a function not from the package, but from your local file. The easiest way to fix that - to rename `onnx2keras.py`.

Hello @Brave731. Unfortunately, the converter doesn't support `upsample_bilinear` for now due to very different results for the same parameters using PyTorch and Tensorflow. But you can replace your Bilinear upsample...

@xiaozhi2015 @Brave731 you may need to fine-tune you model (or at least to train inserted ConvTranspose2d layer) after replacing upsampling method. For some models you will get very similar results,...

Hello @pawopawo. I set requirements `tensorflow>=2.0`, so it should work. You can also try to install `onnx2keras` using git version: `pip install git+ssh://[email protected]/nerox8664/onnx2keras.git` Here is related issue: https://github.com/tensorflow/tensorflow/issues/31939. Maybe you...

Hello, please, provide more information about your model so I can reproduce it.

Hello. Can you show your model definition? I will implement more ONNX operations later, it takes some time.

Hello. Unfortunately, it's not supported by PyTorch. `RuntimeError: ONNX export failed: Couldn't export operator aten::log_softmax` on PyTorch-ONNX side.