- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi all,
I am trying to make a simple network to learn the identity function, i.e., take an input image and give back the same image.
I am using the CIFAR10 dataset for training.
My architecture is as follows:
Input (32 x 32 x 3) -> Conv (8 filters, 5x5 filter size and 2,2 strides with same padding and ReLU activation) -> ConvTranspose (3 filters, 5x5 filter size and 2,2 strides with same padding and no activation).
I get the following error when I try to compile:
/usr/local/bin/ncsdk/Controllers/Parsers/TensorFlowParser/Convolution.py:46: SyntaxWarning: assertion is always true, perhaps remove parentheses?
assert(False, "Layer type not supported by Convolution: " + obj.type)
/usr/local/bin/ncsdk/Controllers/Parsers/Phases.py:322: SyntaxWarning: assertion is always true, perhaps remove parentheses?
assert(len(pred) == 1, "Slice not supported to have >1 predecessors")
mvNCCompile v02.00, Copyright @ Intel Corporation 2017
****** Info: No Weights provided. inferred path: inference.data-00000-of-00001******
shape: (1, 32, 32, 3)
[Error 5] Toolkit Error: Stage Details Not Supported: Wrong deconvolution output shape.
Any help will be greatly appreciated.
The command I am running is as follows:
mvNCCompile inference.meta -s 12 -in Input -on deconv1T/BiasAdd -o inference.graph
- Tags:
- Neural Networks
Link Copied
1 Reply
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Using NCS API v2 fixed this issue.
![](/skins/images/C4F7392A5C68ACA60290C9576F107044/responsive_peak/images/icon_anonymous_message.png)
Reply
Topic Options
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page