Applicazioni di compressione della rete
Comprimere una rete neurale profonda eseguendo la quantizzazione, la compressione dei parametri apprendibili o lo sfoltimento
Generare codice per le reti di Deep Learning con un ridotto ingombro di memoria e ridotti requisiti computazionali.
Esempi in primo piano
Generate INT8 Code for Deep Learning Network on Raspberry Pi
Generate code for deep learning network that performs inference computations in 8-bit integers.
Generate INT8 Code for Deep Learning Network on Cortex-M Target
Generate code for deep learning network that performs inference computations in 8-bit integers.
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.
Code Generation for Sequence-to-Sequence Classification with Learnables Compression
Generate code for LSTM network with learnables compression.
