Sfoltimento
Lo sfoltimento riduce il numero di parametri apprendibili in una rete neurale eliminando i filtri meno importanti nei livelli convoluzionali.
Se è possibile addestrare la rete utilizzando la funzione trainnet, sfoltirla utilizzando la funzione compressNetworkUsingTaylorPruning. Se non è possibile addestrare la rete utilizzando la funzione trainnet, creare un loop di sfoltimento personalizzato utilizzando invece un oggetto taylorPrunableNetwork.
Per una panoramica dettagliata delle tecniche di compressione disponibili in Deep Learning Toolbox™ Model Compression Library, vedere Reduce Memory Footprint of Deep Neural Networks.
Funzioni
Argomenti
- Prune Neural Network with Memory Requirement
This example shows how to compress a neural network to a specific size using Taylor pruning. (Da R2026a)
- Prune Neural Network with Accuracy Requirement
This example shows how to compress a neural network with a minimum accuracy requirement using Taylor pruning. (Da R2026a)
- Prune Image Classification Network Using Taylor Scores
Reduce the size of a deep neural network using Taylor pruning.
- Prune Filters in a Detection Network Using Taylor Scores
Reduce network size and increase inference speed by pruning convolutional filters in a you only look once (YOLO) v3 object detection network.
- Prune and Quantize Convolutional Neural Network for Speech Recognition
Compress a convolutional neural network (CNN) to prepare it for deployment on an embedded system.
- Parameter Pruning and Quantization of Image Classification Network
Use parameter pruning and quantization to reduce network size.
Esempi in primo piano
Prune Neural Network with Memory Requirement
Compress a neural network to a specific size using Taylor pruning.
Prune Neural Network with Accuracy Requirement
Compress a neural network with a minimum accuracy requirement using Taylor pruning.
Analyze and Compress 1-D Convolutional Neural Network
Analyze 1-D convolutional network for compression and compress it using Taylor pruning and projection.
