MobileNet – Quantised

Reported on 3 benchmarks across 3 tasks · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology3 results

Network PruningonCIFAR-10
Inference Time (ms)· 2020-01-14
4.74
SOTA
Quantisation and Pruning for Neural Network Compression and Regularisation arXiv:2001.04850
Model CompressiononCIFAR-10
Size (MB)· 2020-01-14
2.9
best: 1005.1122 (SST-HT)
Quantisation and Pruning for Neural Network Compression and Regularisation arXiv:2001.04850
2D ClassificationonCIFAR-10
Size (MB)· 2020-01-14
2.9
best: 1005.1122 (SST-HT)
Quantisation and Pruning for Neural Network Compression and Regularisation arXiv:2001.04850