- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi, When I run the object_detection_SSD_sample, error is occured as follows.
[ ERROR ] Can't find output layer named bbox_pred
I don't know what should I do in this situation.
I used VOC0712_SSD300 to convert the IR model. I attached .xml file iused.
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Dear Morishige,
can you confirm that you ran the sample: object_detection_sample_ssd? The error you show is more typical from the sample: object_detection_sample which expects a layer called bbox_pred.
Best,
Severine
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Thanks for reply. I can't understand what [bbox_pred] means.
So what should I revise ? Where the typical bbox error occur ?
I ran the sample as follows. There is a error.
1. Download SSD model (downloader.py doesn't work correctly)
2. Convert caffemodel and deploy.prototxt to .xml by using model optimizer.
3. I ran the object_detection_ssd samle by using xml.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Dear Morishige,
I would like to reproduce your error, can you send me the link to the original model (if you took it from the internet)? Or add the .bin to the zip file along with the xml?
Best,
Severine
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
I mistook the command. Sample run correctly.
Error was not object_detection_sample_ssd but object_detection_sample as you said.
Thank you for replying many times.
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page