Toybrick
标题:
做混合量化hybrid_quantization
[打印本页]
作者:
fjndfazp
时间:
2020-5-30 17:37
标题:
做混合量化hybrid_quantization
在做common_function_demos\hybrid_quantization里面的混合量化step1之后,会生成一个cfg配置文件,根据下面的解释,我要怎么设置每一层的量化方式?
%YAML 1.2
---
# add layer name and corresponding quantized_dtype to customized_quantize_layers, e.g conv2_3: float32
customized_quantize_layers: {}
比如:截图中的,如果attach_concat_1/out0_0不量化,是不是直接写下面这样?如果有多个层都需要不做量化呢?有没有举例说明一下
customized_quantize_layers: {attach_concat_1/out0_0: float32}
作者:
jefferyzhang
时间:
2020-5-30 17:46
参看rknn-toolkit里的sample,有完整混合量化的sample的
作者:
brunolin
时间:
2021-2-19 13:40
customized_quantize_layers: {
attach_concat_1/out0_0: float32,
layer_000/xxx_000: float32,
layer_111/xxx_111: float32
}
欢迎光临 Toybrick (https://t.rock-chips.com/)
Powered by Discuz! X3.3