- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
I got an error when i was try to convert a Fully Convolutional Network without fix the input images size, so i was wondering if IR support multi-shape images as input during inference process。
A resized image as the input is not the way i want,how can i convert a FCN like network to openvino IR?
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi Eric
You can specify an arbitrary input size as required, then during the inferencing to work with multi-shape images, use the shape inference feature of the inference engine to work with differently-sized inputs. More on shape inference is available here https://docs.openvinotoolkit.org/latest/_docs_IE_DG_ShapeInference.html
Regards
Roy
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi Eric
You can specify an arbitrary input size as required, then during the inferencing to work with multi-shape images, use the shape inference feature of the inference engine to work with differently-sized inputs. More on shape inference is available here https://docs.openvinotoolkit.org/latest/_docs_IE_DG_ShapeInference.html
Regards
Roy

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