- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
I would like to convert my xception model to openvino IR. But while trying to do the same i get an error
sudo python3 mo.py --input_model /xception_opt_Adam_
bz_16_epoch_8_lr_0.0001.model --output ArgMax --input 1:mul_1 --input_shape "(1,300,1600,3)" --log_level=DEBUG
[ ERROR ] Framework name can not be deduced from the given options: --input_model=/xception_opt_Adam_bz_16_epoch_8_lr_0.0001.model. Use --framework to choose one of caffe, tf, mxnet, kaldi, onnx
Could you please support me in fixing this issue. Does openvino support xception network
regards,
Gina Mathew
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Dear Mathew, Gina
According to the Xception Documentation, Xception uses Depthwise Separable Convolutions which OpenVino does not support at this time. Please see mkl-dnn issue 301 for more discussion on this issue.
Thanks,
Shubha

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page