imageNet

Image recognition DNN (GoogleNet, AlexNet, ResNet) More...

Classes
class	imageNet
	Image recognition with classification networks, using TensorRT. More...

Macros
#define	DETECTNET_USAGE_STRING
	Command-line options able to be passed to imageNet::Create() More...
#define	IMAGENET_DEFAULT_INPUT   "data"
	Name of default input blob for imageNet model. More...
#define	IMAGENET_DEFAULT_OUTPUT   "prob"
	Name of default output confidence values for imageNet model. More...
#define	IMAGENET_USAGE_STRING
	Command-line options able to be passed to imageNet::Create() More...

Detailed Description

Image recognition DNN (GoogleNet, AlexNet, ResNet)

Macro Definition Documentation

DETECTNET_USAGE_STRING

#define DETECTNET_USAGE_STRING

Value:

"detectNet arguments: \n"                                                               \
                  "  --network NETWORK     pre-trained model to load, one of the following:\n"          \
                  "                            * pednet (default)\n"                                                    \
                  "                            * multiped\n"                                                            \
                  "                            * facenet\n"                                                                     \
                  "                            * ssd-mobilenet-v1\n"                                                    \
                  "                            * ssd-mobilenet-v2\n"                                                    \
                  "                            * ssd-inception-v2\n"                                                    \
                  "                            * coco-airplane\n"                                                       \
                  "                            * coco-bottle\n"                                                                 \
                  "                            * coco-chair\n"                                                          \
                  "                            * coco-dog\n"                                                            \
                  "  --model MODEL         path to custom model to load (.caffemodel, .uff, or .onnx)\n"                                        \
                  "  --prototxt PROTOTXT   path to custom prototxt to load (for .caffemodel only)\n"                                    \
                  "  --class_labels LABELS path to text file containing the labels for each class\n"                                    \
                  "  --threshold THRESHOLD minimum threshold for detection (default is 0.5)\n"                                                  \
                  "  --input_blob INPUT    name of the input layer (default is '" DETECTNET_DEFAULT_INPUT "')\n"                        \
                  "  --output_cvg COVERAGE name of the coverge output layer (default is '" DETECTNET_DEFAULT_COVERAGE "')\n"    \
                  "  --output_bbox BOXES   name of the bounding output layer (default is '" DETECTNET_DEFAULT_BBOX "')\n"       \
                  "  --mean_pixel PIXEL    mean pixel value to subtract from input (default is 0.0)\n"                                  \
                  "  --batch_size BATCH    maximum batch size (default is 1)\n"

Command-line options able to be passed to imageNet::Create()

IMAGENET_DEFAULT_INPUT

#define IMAGENET_DEFAULT_INPUT   "data"

Name of default input blob for imageNet model.

IMAGENET_DEFAULT_OUTPUT

#define IMAGENET_DEFAULT_OUTPUT   "prob"

Name of default output confidence values for imageNet model.

IMAGENET_USAGE_STRING

#define IMAGENET_USAGE_STRING

Value:

"imageNet arguments: \n"                                                        \
                  "  --network NETWORK    pre-trained model to load, one of the following:\n"   \
                  "                           * alexnet\n"                                                              \
                  "                           * googlenet (default)\n"                                  \
                  "                           * googlenet-12\n"                                                         \
                  "                           * resnet-18\n"                                                    \
                  "                           * resnet-50\n"                                                    \
                  "                           * resnet-101\n"                                                   \
                  "                           * resnet-152\n"                                                   \
                  "                           * vgg-16\n"                                                               \
                  "                           * vgg-19\n"                                                               \
                  "                           * inception-v4\n"                                                         \
                  "  --model MODEL        path to custom model to load (.caffemodel, .uff, or .onnx)\n"                         \
                  "  --prototxt PROTOTXT  path to custom prototxt to load (for .caffemodel only)\n"                             \
                  "  --labels LABELS      path to text file containing the labels for each class\n"                             \
                  "  --input_blob INPUT   name of the input layer (default is '" IMAGENET_DEFAULT_INPUT "')\n"  \
                  "  --output_blob OUTPUT name of the output layer (default is '" IMAGENET_DEFAULT_OUTPUT "')\n"        \
                  "  --batch_size BATCH   maximum batch size (default is 1)\n"

Command-line options able to be passed to imageNet::Create()