TIEVisionLibrary.createNNet
Declaration
function createNNet(modelPath: PAnsiChar; configPath: PAnsiChar = nil; framework: PAnsiChar = nil): TIEVisionNNet; safecall;Description
Create an TIEVisionNNet instance to perform image classification and text detection.
The supported models are:
| Model | Link | Extension |
|---|---|---|
| Caffe | caffe.berkeleyvision.org/ | .caffemodel |
| TensorFlow | www.tensorflow.org/ | .pb |
| Torch | torch.ch/ | .t7 or .net |
| Darknet | pjreddie.com/darknet/ | .weights |
| DLDT | software.intel.com/openvino-toolkit/ | .bin |
| ONNX | onnx.ai/ | .onnx |
| Parameter | Description |
|---|---|
| modelPath | Path to the input model |
| configPath | Optional path to the configuration file |
| framework | Optional framework specification (values: 'caffe', 'tensorflow', 'torch', 'darknet', 'dldt', 'onnx') |
You can download model files from: www.imageen.com/download/
More information on Deep Learning is available at: learnopencv.com/deep-learning-with-opencvs-dnn-module-a-definitive-guide/