MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.
Platform (like ubuntu 16.04/win10):
mac
Python version:
python3.7
Source framework with version (like Tensorflow 1.4.1 with GPU):
mxnet Cpu
Destination framework with version (like CNTK 2.3 with GPU):
Hi @zhanglaplace, it seems that the reason is indeed that mmdnn does not support arange. We will add this later or maybe you can help us add it? Thanks!
Platform (like ubuntu 16.04/win10): mac Python version: python3.7 Source framework with version (like Tensorflow 1.4.1 with GPU): mxnet Cpu Destination framework with version (like CNTK 2.3 with GPU):
Pre-trained model path (webpath or webdisk path): https://github.com/wayen820/gender_age_estimation_mxnet/tree/master/models/ssr2_megaage_1_1/ Running scripts:
arange op not support?
symbol link:https://github.com/wayen820/gender_age_estimation_mxnet/blob/master/models/ssr2_megaage_1_1/model-ssr-imdb-symbol.json param link:https://github.com/wayen820/gender_age_estimation_mxnet/blob/master/models/ssr2_megaage_1_1/model-ssr-imdb-0030.params