Turn on suggestions

Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.

Showing results for

- Intel Community
- Software
- Software Development SDKs and Libraries
- Intel® Distribution of OpenVINO™ Toolkit
- incorrect shape/size set for 2d output tensor

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

idata

Community Manager

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

08-31-2018
01:43 AM

286 Views

incorrect shape/size set for 2d output tensor

i have a unet style model that includes an 2d output tensor. my minimal example case is the following…

```
imgs (1, 64, 64, 3) #12288
e1 (1, 31, 31, 8) #7688 conv, stride=2
e2 (1, 15, 15, 16) #3600 conv, stride=2
d1 (1, 31, 31, 8) #7688 deconv, stride=2
output (1, 31, 31, 1) #961 1x1 conv, stride=1
```

this model works with one small quirk; when i call queue_inference_with_fifo_elem i get an output tensor of shape `(29791,)`

whereas i expect a shape of `(31,31,1)`

it turns out though the i can slice off the first 31*31 and reshape and it's ok…

```
ncs_positive_prediction = ncs_positive_prediction[:31*31].reshape((31,31,1))
```

…so the data is _there_, but the shape/size is just not being set correctly.

this model, with full reproduction of this case, is described in my movidius_bug_reports repo on github with additional notes in this github issue

Link Copied

2 Replies

idata

Community Manager

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

09-06-2018
04:13 PM

90 Views

idata

Community Manager

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

09-19-2018
11:21 PM

90 Views

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

For more complete information about compiler optimizations, see our Optimization Notice.