- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
We have a model using conv, deconv, concat layers. But the output from ncsdkv2 and v1 are both incorrect.
And if we are not using explicit_concat parameter when convert the model, the output will become NaN also.
But even with explicit_concat parameters enable, the result is still completely wrong.
We are using caffe model and have a python caffe test application for the expected output.
How we can submit the model for further diagnostic ?
Link Copied
3 Replies
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@ek9852 You can send me a link to your model and I can take a look at it. Please send steps on how to reproduce the issue you experienced also. Thanks.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Can you send me your email address ?
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@ek9852 I sent you a PM.
![](/skins/images/7FC17B7B85029576C25F1E43CE255B51/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