Changes between Version 12 and Version 13 of expansion/gw16168

Timestamp:

06/18/2026 04:22:57 PM (7 weeks ago)

Author:

Tim Harvey

Comment:

added images

expansion/gw16168

@@ -524 +524 @@
    - Note that without shm the pipeline needs to copy the raw image bytes over a local network-style socket connection. By mounting a dedicated memory path to /dev/shm you can eliminate that transfer (zero-copy): dvPre dumps the processed directly into a designated block of system RAM and dvInf uses a pointer to it
    - you would think that if your original image was 1080x1920 and you resized it to the model size of 640x640 that if you tell dvPost the orig-width=1080 orig-height=1920 that it would scale the bounding boxes properly however in practice it seems it does not unless your image has the same aspect ratio of the model. mapping it as above (telling dvPost that the image is 640x640 and scaling ourselves) resolves this
+   - images:
+
+[[Image(dog.jpg,400px)]]
+[[Image(dog_detect.jpg,400px)]]
+
+[[Image(traffic_jpg,400px)]]
+[[Image(traffic_detect_yolo8n.jpg,400px)]]
+[[Image(traffic_detect_yolo8x.jpg,400px)]]
+
 
  * Video detection with boxing via Python in a headless webapp
@@ -983 +992 @@
 }}}
   - you can provide a webcam device path to enable streaming from a webcam and/or an mp4 directory to enable processing those. A dropdown will allow you to select the input stream and the model and the browser window will show you detections and statistics 
+
+[[Image(vision-webapp.jpg,400px)]]
+
 
 [=#eiq-aaf-connector]
@@ -2068 +2080 @@
  - open a browser to the host port 8080, select a video and submit a query
 
+[[Image(vlm-webapp.jpg,400px)]]