- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
I am trying to compile the LeNet example included with Caffe down to a graph file using mvNCCompile, but I get this error:
[Error 24] Toolkit Error: >1 image inference not supported.
I see that the batch size in the prototxt file I am using is set to 64, has anyone gotten LeNet to compile using mvNCCompile?
Thanks,
Ian
- Tags:
- Caffe
Link Copied
3 Replies
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@iwilmoth At the moment, the NCS only supports a batch size of 1. Edit your prototxt file, set the batch size to 1 and try to compile the graph file again.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@Tome_at_Intel I changed the batch size to 1, but specifying the input node as "data" resulted in this IndexError:
Traceback (most recent call last):
File "/usr/local/bin/mvNCCompile", line 118, in
create_graph(args.network, args.inputnode, args.outputnode, args.outfile, args.nshaves, args.inputsize, args.weights)
File "/usr/local/bin/mvNCCompile", line 101, in create_graph
net = parse_caffe(args, myriad_config)
File "/usr/local/bin/ncsdk/Controllers/CaffeParser.py", line 382, in parse_caffe
input_bottom = net.bottom_names[inputNodeName][0]
IndexError: list index out of range
Removing the input node selection from the arguments passed to mvNCCompile worked, though; LeNet works as it should. Thanks!
Ian
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@iwilmoth Glad it worked out for you.
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