updated docs

Media-4-Machine-Laboratory · Apr 5, 2023 · 238cf5e · 238cf5e
1 parent eea79b9
commit 238cf5e
Show file tree

Hide file tree

Showing 6 changed files with 32 additions and 5 deletions.
diff --git a/README.md b/README.md
@@ -35,7 +35,7 @@ Hello AI World can be run completely onboard your Jetson, including inferencing
 
 #### Inference
 
-* [Classification](docs/imagenet-console-2.md)
+* [Image Classification](docs/imagenet-console-2.md)
 	* [Using the ImageNet Program on Jetson](docs/imagenet-console-2.md)
 	* [Coding Your Own Image Recognition Program (Python)](docs/imagenet-example-python-2.md)
 	* [Coding Your Own Image Recognition Program (C++)](docs/imagenet-example-2.md)

diff --git a/docs/imagenet-camera-2.md b/docs/imagenet-camera-2.md
@@ -1,7 +1,7 @@
 <img src="https://github.com/dusty-nv/jetson-inference/raw/master/docs/images/deep-vision-header.jpg" width="100%">
 <p align="right"><sup><a href="imagenet-example-2.md">Back</a> | <a href="detectnet-console-2.md">Next</a> | </sup><a href="../README.md#hello-ai-world"><sup>Contents</sup></a>
 <br/>
-<sup>Image Recognition</sup></p>  
+<sup>Image Classification</sup></p>  
 
 # Running the Live Camera Recognition Demo
 

diff --git a/docs/imagenet-console-2.md b/docs/imagenet-console-2.md
@@ -1,7 +1,7 @@
 <img src="https://github.com/dusty-nv/jetson-inference/raw/master/docs/images/deep-vision-header.jpg" width="100%">
 <p align="right"><sup><a href="building-repo-2.md">Back</a> | <a href="imagenet-example-python-2.md">Next</a> | </sup><a href="../README.md#hello-ai-world"><sup>Contents</sup></a>
 <br/>
-<sup>Image Recognition</sup></p>  
+<sup>Image Classification</sup></p>  
 
 # Classifying Images with ImageNet
 There are multiple types of deep learning networks available, including recognition, detection/localization, and semantic segmentation.  The first deep learning capability we're highlighting in this tutorial is **image recognition**, using classifcation networks that have been trained on large datasets to identify scenes and objects.

diff --git a/docs/imagenet-example-2.md b/docs/imagenet-example-2.md
@@ -1,7 +1,7 @@
 <img src="https://github.com/dusty-nv/jetson-inference/raw/master/docs/images/deep-vision-header.jpg" width="100%">
 <p align="right"><sup><a href="imagenet-example-python-2.md">Back</a> | <a href="imagenet-camera-2.md">Next</a> | </sup><a href="../README.md#hello-ai-world"><sup>Contents</sup></a>
 <br/>
-<sup>Image Recognition</sup></p>  
+<sup>Image Classification</sup></p>  
 
 # Coding Your Own Image Recognition Program (C++)
 In the previous step, we ran an application that came with the jetson-inference repo.  

diff --git a/docs/imagenet-example-python-2.md b/docs/imagenet-example-python-2.md
@@ -1,7 +1,7 @@
 <img src="https://github.com/dusty-nv/jetson-inference/raw/master/docs/images/deep-vision-header.jpg" width="100%">
 <p align="right"><sup><a href="imagenet-console-2.md">Back</a> | <a href="imagenet-example-2.md">Next</a> | </sup><a href="../README.md#hello-ai-world"><sup>Contents</sup></a>
 <br/>
-<sup>Image Recognition</sup></p>  
+<sup>Image Classification</sup></p>  
 
 # Coding Your Own Image Recognition Program (Python)
 In the previous step, we ran a sample application that came with the `jetson-inference` repo.  

diff --git a/docs/imagenet-tagging.md b/docs/imagenet-tagging.md
@@ -0,0 +1,27 @@
+<img src="https://github.com/dusty-nv/jetson-inference/raw/master/docs/images/deep-vision-header.jpg" width="100%">
+<p align="right"><sup><a href="imagenet-camera-2.md">Back</a> | <a href="detectnet-console-2.md">Next</a> | </sup><a href="../README.md#hello-ai-world"><sup>Contents</sup></a>
+<br/>
+<sup>Image Classification</sup></p>
+
+# Multi-Label Classification for Image Tagging
+
+Multi-label classification models are able to recognize multiple object classes simultaneously for performing tasks like image tagging.  The multi-label DNNs are almost identical in topology to ordinary single-class models, except they use a sigmoid activation layer as opposed to softmax.  There's a pre-trained `resnet18-tagging-voc` multi-label model available that was trained on the Pascal VOC dataset:  
+
+<img src=https://github.com/dusty-nv/jetson-inference/raw/master/docs/images/imagenet_tagging.jpg>
+
+To enable image tagging, you'll want to run imagenet/imagenet.py with `--topK=0` and a `--threshold` of your choosing: 
+
+``` bash
+# C++
+$ imagenet --model=resnet18-tagging-voc --topK=0 --threshold=0.25 "images/object_*.jpg" images/test/tagging_%i.jpg"
+
+# Python
+$ imagenet.py --model=resnet18-tagging-voc --topK=0 --threshold=0.25 "images/object_*.jpg" images/test/tagging_%i.jpg"
+```
+
+Using `--topK=0` means that all the classes with a confidence score exceeding the threshold will be returned.
+
+<p align="right">Next | <b><a href="detectnet-console-2.md">Object Detection</a></b>
+<br/>
+Back | <b><a href="imagenet-camera-2.md">Running the Live Camera Recognition Demo</a></p>
+</b><p align="center"><sup>© 2016-2023 NVIDIA | </sup><a href="../README.md#hello-ai-world"><sup>Table of Contents</sup></a></p>