GstInference/Example pipelines with hierarchical metadata/PC: Difference between revisions
| Line 123: | Line 123: | ||
<div class="container"> | <div class="container"> | ||
<form action="/action_page.php"> | <form action="/action_page.php"> | ||
<div class="row"> | |||
<div class="col-25"> | |||
<label for="platform">Platform</label> | |||
</div> | |||
<div class="col-75"> | |||
<select id="platform" name="platform" onchange="dynamic_backend_dropdown(this.options[this.selectedIndex].value)"> | |||
<option value="" disabled selected>Select your platform</option> | |||
<option value="pc">PC</option> | |||
<option value="jetson">Jetson</option> | |||
</select> | |||
</div> | |||
</div> | |||
<div class="row"> | <div class="row"> | ||
<div class="col-25"> | <div class="col-25"> | ||
| Line 128: | Line 140: | ||
</div> | </div> | ||
<div class="col-75"> | <div class="col-75"> | ||
<select id="backend" name="backend" onchange="backend_selection()"> | <select id="backend" name="backend" onchange="backend_selection(this.options[this.selectedIndex].value)"> | ||
<option value="" disabled selected>Select your backend</option> | <option value="" disabled selected>Select your backend</option> | ||
<option value="tensorflow">TensorFlow</option> | <option value="tensorflow">TensorFlow</option> | ||
<option value="tflite">TFLite</option> | <option value="tflite">TFLite</option> | ||
| Line 148: | Line 159: | ||
<option value="inceptionv4">Inceptionv4</option> | <option value="inceptionv4">Inceptionv4</option> | ||
<option value="mobilenetv2">MobileNetv2</option> | <option value="mobilenetv2">MobileNetv2</option> | ||
<option value="tinyyolov2">TinyYolov2</option> | <option value="tinyyolov2">TinyYolov2</option> | ||
<option value="facenetv1">FaceNet</option> | <option value="facenetv1">FaceNet</option> | ||
</select> | </select> | ||
| Line 323: | Line 332: | ||
}; | }; | ||
function backend_selection() { | function dynamic_backend_dropdown(platform) { | ||
if (platform == "pc") { | |||
document.getElementById("backend").options[3]=new Option("NCSDK","ncsdk"); | |||
} else { | |||
document.getElementById("backend").remove(3); | |||
document.getElementById("backend").value=null; | |||
document.getElementById("backend").placeholder="mew"; | |||
} | |||
} | |||
function backend_selection(backend) { | |||
// Default values from dictionary for Tensorflow models | // Default values from dictionary for Tensorflow models | ||
if( document.getElementById("backend").value == "tensorflow") { | if( document.getElementById("backend").value == "tensorflow") { | ||
Revision as of 23:05, 10 March 2020
 | Make sure you also check GstInference's companion project: R2Inference |
| GstInference |
|---|
 |
| Introduction |
| Getting started |
| Supported architectures |
|
InceptionV1 InceptionV3 YoloV2 AlexNet |
| Supported backends |
|
Caffe |
| Metadata and Signals |
| Overlay Elements |
| Utils Elements |
| Legacy pipelines |
| Example pipelines |
| Example applications |
| Benchmarks |
| Model Zoo |
| Project Status |
| Contact Us |
 |
Sample pipelines
The following section contains a tool for generating simple GStreamer pipelines with one model of a selected architecture using our hierarchical inference metadata. If you are using and older version, you chan check the legacy pipelines section. Please make sure to check the documentation to understand the property usage for each element.
The required elements are:
- Backend
- Model
- Model location
- Labels
- Source
- Sink
The optional elements include:
- inferencefilter
- inferencrop
- inferenceoverlay
Pipeline generator
The following tool will provide simple pipelines according to the selected elements.
Advanced pipelines