标签：数据丢失 rds incr table bat 权重 red img mamicode
01 IFQ-Net: Integrated Fixed-point Quantization Networks for Embedded Vision （1911.08076）
In this paper, we propose a fixed-point network
for embedded vision tasks through converting the floatingpoint data in a quantization network into fixed-point. Furthermore, to overcome the data loss caused by the conversion, we propose to compose floating-point data operations
across multiple layers (e.g. convolution, batch normalization and quantization layers) and convert them into fixedpoint.
量化网络层 将浮点数据转换为固定点数据；
为了减小数据丢失，转换过程跨多个层（卷积 正则化 量化）；
02 DupNet: Towards Very Tiny Quantized CNN with Improved Accuracy for Face
Detection
【
we propose DupNet which consists of two parts.
Firstly, we employ weights with duplicated channels for the
weight-intensive layers to reduce the model size. Secondly,
for the quantization-sensitive layers whose quantization
causes notable accuracy drop, we duplicate its input feature
maps. It allows us to use more weights channels for convolving more representative outputs.
】
【
1) it reduces the model size of a quantized network by duplicated weights for weight-intensive layers;
2)it increases the accuracy through duplicating the input feature maps of its quantization-sensitive layers.
】
1：权重密集层复制权重参数（使用同样的参数，减小模型尺寸）
2：量化密集层复制输入特性映射（增加准确率）
标签：数据丢失 rds incr table bat 权重 red img mamicode
原文地址：https://www.cnblogs.com/Ph-one/p/12495884.html
