| cv.Net - MATLAB File Help | Go to online doc for cv.Net |
Create and manipulate comprehensive artificial neural networks
This module contains:
Functionality of this module is designed only for forward pass computations (i. e. network testing). A network training is in principle not supported.
Neural network is presented as directed acyclic graph (DAG), where vertices are Layer instances, and edges specify relationships between layers inputs and outputs.
Each network layer has unique integer id and unique string name inside its network. LayerId can store either layer name or layer id.
| Superclasses | handle |
| Sealed | false |
| Construct on load | false |
| Net | Constructor and importer of trained serialized models from different dnn-frameworks |
| id | Object ID |
| Static | NMSBoxes | Performs non-maximum suppression given boxes and corresponding scores |
| addLayer | Adds new layer to the net | |
| addLayerToPrev | Adds new layer and connects its first input to the first output of previously added layer | |
| addlistener | Add listener for event. | |
| Static | blobFromImages | Creates 4-dimensional blob from image or series of images |
| connect | Connects output of the first layer to input of the second layer | |
| delete | Destructor | |
| deleteLayer | Delete layer for the network | |
| empty | Returns true if there are no layers in the network. | |
| enableFusion | Enables or disables layer fusion in the network | |
| eq | == (EQ) Test handle equality. | |
| findobj | Find objects matching specified conditions. | |
| findprop | Find property of MATLAB handle object. | |
| forward | Runs forward pass | |
| forwardAndRetrieve | Runs forward pass | |
| ge | >= (GE) Greater than or equal relation for handles. | |
| getLayer | Returns layer with specified id or name which the network use | |
| getLayerId | Converts string name of the layer to the integer identifier | |
| getLayerInputs | Returns input layers of specific layer | |
| getLayerNames | Get layer names | |
| getLayerTypes | Returns list of types for layer used in model | |
| getLayersCount | Returns count of layers of specified type | |
| getParam | Returns parameter blob of the layer | |
| getPerfProfile | Returns overall time for inference and timings (in ticks) for layers | |
| getUnconnectedOutLayers | Returns indexes of layers with unconnected outputs | |
| gt | > (GT) Greater than relation for handles. | |
| Static | imagesFromBlob | Parse a 4D blob and output the images it contains |
| Sealed | isvalid | Test handle validity. |
| le | <= (LE) Less than or equal relation for handles. | |
| listener | Add listener for event without binding the listener to the source object. | |
| lt | < (LT) Less than relation for handles. | |
| ne | ~= (NE) Not equal relation for handles. | |
| notify | Notify listeners of event. | |
| Static | readTorchBlob | Loads blob which was serialized as torch.Tensor object of Torch7 framework |
| setHalideScheduler | Compile Halide layers | |
| setInput | Sets the new value for the layer output blob | |
| setInputsNames | Sets outputs names of the network input pseudo layer | |
| setParam | Sets the new value for the learned param of the layer | |
| setPreferableBackend | Ask network to use specific computation backend where it supported | |
| setPreferableTarget | Ask network to make computations on specific target device | |
| Static | shrinkCaffeModel | Convert all weights of Caffe network to half precision floating point |
| ObjectBeingDestroyed | Notifies listeners that a particular object has been destroyed. |