From 077d21f0558700a340cfa91f8d999949fdd2532f Mon Sep 17 00:00:00 2001 From: chenzomi Date: Mon, 15 Jun 2020 10:10:22 +0800 Subject: [PATCH] change mobilenet V2 readme. --- example/mobilenetv2/Readme.md | 13 ++----------- example/mobilenetv2_quant/Readme.md | 14 +++----------- 2 files changed, 5 insertions(+), 22 deletions(-) diff --git a/example/mobilenetv2/Readme.md b/example/mobilenetv2/Readme.md index 420ce0327..d3dedb3cb 100644 --- a/example/mobilenetv2/Readme.md +++ b/example/mobilenetv2/Readme.md @@ -1,16 +1,11 @@ # MobileNetV2 Description +MobileNetV2 is a significant improvement over MobileNetV1 and pushes the state of the art for mobile visual recognition including classification, object detection and semantic segmentation. -MobileNetV2 is tuned to mobile phone CPUs through a combination of hardware- aware network architecture search (NAS) complemented by the NetAdapt algorithm and then subsequently improved through novel architecture advances.Nov 20, 2019. +MobileNetV2 builds upon the ideas from MobileNetV1, using depthwise separable convolution as efficient building blocks. However, V2 introduces two new features to the architecture: 1) linear bottlenecks between the layers, and 2) shortcut connections between the bottlenecks1. [Paper](https://arxiv.org/pdf/1801.04381) Howard, Andrew, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang et al. "Searching for MobileNetV2." In Proceedings of the IEEE International Conference on Computer Vision, pp. 1314-1324. 2019. -# Model architecture - -The overall network architecture of MobileNetV2 is show below: - -[Link](https://ai.googleblog.com/2018/04/mobilenetv2-next-generation-of-on.html) - # Dataset Dataset used: imagenet @@ -21,10 +16,6 @@ Dataset used: imagenet - Data format: RGB images. - Note: Data will be processed in src/dataset.py - -# Features - - # Environment Requirements - Hardware（Ascend/GPU） diff --git a/example/mobilenetv2_quant/Readme.md b/example/mobilenetv2_quant/Readme.md index 351fc80d7..01cc7e360 100644 --- a/example/mobilenetv2_quant/Readme.md +++ b/example/mobilenetv2_quant/Readme.md @@ -1,15 +1,10 @@ # MobileNetV2 Description +MobileNetV2 is a significant improvement over MobileNetV1 and pushes the state of the art for mobile visual recognition including classification, object detection and semantic segmentation. -MobileNetV2 is tuned to mobile phone CPUs through a combination of hardware- aware network architecture search (NAS) complemented by the NetAdapt algorithm and then subsequently improved through novel architecture advances.Nov 20, 2019. +MobileNetV2 builds upon the ideas from MobileNetV1, using depthwise separable convolution as efficient building blocks. However, V2 introduces two new features to the architecture: 1) linear bottlenecks between the layers, and 2) shortcut connections between the bottlenecks1. -[Paper](https://arxiv.org/pdf/1905.02244) Howard, Andrew, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang et al. "Searching for MobileNetV2." In Proceedings of the IEEE International Conference on Computer Vision, pp. 1314-1324. 2019. - -# Model architecture - -The overall network architecture of MobileNetV2 is show below: - -[Link](https://ai.googleblog.com/2018/04/mobilenetv2-next-generation-of-on.html) +[Paper](https://arxiv.org/pdf/1801.04381) Howard, Andrew, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang et al. "Searching for MobileNetV2." In Proceedings of the IEEE International Conference on Computer Vision, pp. 1314-1324. 2019. # Dataset @@ -22,9 +17,6 @@ Dataset used: imagenet - Note: Data will be processed in src/dataset.py -# Features - - # Environment Requirements - Hardware（Ascend) -- GitLab