The dataset was replaced with CIFAR100, and the accuracy after quantization was less than 10%

Mxbonn / INQ-pytorch

A PyTorch implementation of "Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights"

164 stars 27 forks source link

The dataset was replaced with CIFAR100, and the accuracy after quantization was less than 10% #15

Open blutofilp opened 2 years ago

blutofilp commented 2 years ago

I retrained resnet18 on cifar100 and quantized its parameters using INQ, but the accuracy decreased seriously after quantization, usually less than 10%. Does anyone have similar problems?