- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
The Keras model is pretrained with
vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5 and
inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5.
Is there anyway I can convert this trained model to IR, and use a NCS2 as Inference Engine?
Does the Model Optimizer support all kinds TensorFlow2 trained models, or is it only YOLO/SSD network strutures,
and does it accept weights in .h5 format?
Hope you can help me answer these questions, Thanks?
Pih Lung
More info regarding the Keras model see attached files and the url
https://www.kaggle.com/paultimothymooney/interpret-sign-language-with-deep-learning
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi Pih,
The Model Optimizer expects the models to be one of the following supported frameworks:
TensorFlow, Caffe, Kaldi, ONNX or MXnet
Please convert the Keras model to TensorFlow and then use the Model Optimizer.
You may refer Supported Topologies to see the list of topologies supported with TensorFlow* framework.
Also, verify that the model contains the TensorFlow* Supported Operations before converting to IR.
Regards,
Jaivin
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page