HX L

@bwery , thank you very much for the feedback. MMdnn does not install Keras automatically, so you may try the following command to install it manually: ```cmd pip3 install --user...

@nestyme , thank you very much for the feedback. You need to keep the model module in the same folder when loading the serialized model. Please refer to https://github.com/pytorch/pytorch/issues/18325 and...

@hnuhchen , thank you very much for the feedback. We are looking into this issue.

@duguqiankun , thank you very much for the feedback. TensorFlow 2.0 is not officially released yet now. We will support it in future.

@goncz, thank you very much for the feedback. A quick workaround is that you install the CPU versions of TensorFlow and Caffe. Maybe you could create a Python virtual environment...

@Joejiong , thank you very much for the feedback. Orginally, ONNX is an open neural network exchange format, with a similar motivation for framework interoperability. However, it includes only essential...

@Zrufy , thank you very much for the feedback. Are you using TF mobilenet? It seems to use Relu6 only instead of Elu.

@kyhoolee , thank you very much for the feedback. We will look into this issue.

@merria28 , thank you very much for the feedback. MMdnn does not support the TensorFlow "Less" operator currently. It seems that Caffe does not support any control-flow operators like "Less",...

@zdy0009 , sorry for late response. By default, protobuf is compiled as a static library without the compiler argument "-fPIC" (position-independent code). Please open the file "ext/protobuf/CMakeLists.txt", add "-DCMAKE_POSITION_INDEPENDENT_CODE=ON;" after...