- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
I am running into some trouble when trying to use Inference Engine on the NCS through the python API (python 3.7.3, Host Windows 10, ONNX PyTorch)
I don't see this error with this same model for CPU or GPU. The error is in the code of creating exe_net
exec_net = plugin.load(network=net)
Traceback (most recent call last):
File "C:/Users/Hans/Desktop/alexnet_vote/test.py", line 204, in <module>
main(testdata, test_mapping)
File "C:/Users/Hans/Desktop/alexnet_vote/test.py", line 138, in main
exec_net = plugin.load(network=net)
File "ie_api.pyx", line 551, in openvino.inference_engine.ie_api.IEPlugin.load
File "ie_api.pyx", line 561, in openvino.inference_engine.ie_api.IEPlugin.load
RuntimeError: Failed to infer shapes for Reshape layer (38) with error: Invalid reshape mask (dim attribute): number of elements in input: [1,256,6,6] and output: [10,9216] mismatch
<layer id="16" name="38" precision="FP16" type="Reshape"> <input> <port id="0"> <dim>10</dim> <dim>256</dim> <dim>6</dim> <dim>6</dim> </port> <port id="1"> <dim>2</dim> </port> </input> <output> <port id="2"> <dim>10</dim> <dim>9216</dim> </port> </output> </layer>
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Dear Han, Tianyi,
Are you using the latest OpenVino Release 20192.01 ?
with error: Invalid reshape mask (dim attribute): number of elements in input: [1,256,6,6] and output: [10,9216] mismatch
Looking at the error 256*6*6 = 9216. But the first position 1 is batch size. What happens when you re-run model optimizer this time with --batch 10 ?
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