p19647583
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

!2104 change mobilenet V2 readme.md 

Merge pull request !2104 from chenzhongming/r0.3
This commit is contained in:
mindspore-ci-bot 2020-06-15 10:20:47 +08:00 committed by Gitee
parent da9530f7f7 077d21f055
commit 7c77bb8782
2 changed files with 5 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
example/mobilenetv2/Readme.md
View File

@ -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）

14
example/mobilenetv2_quant/Readme.md
View File

@ -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)