p60975123
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

update Model Zoo README and googlenet README

This commit is contained in:
liyanliu 2020-10-26 20:18:15 +08:00
parent 64d078da79
commit 08952b186e
2 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
model_zoo/README.md
View File

@ -27,15 +27,15 @@ In order to facilitate developers to enjoy the benefits of MindSpore framework,
- [AlexNet](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/alexnet/README.md) - [AlexNet](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/alexnet/README.md)
- [LeNet](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/lenet/README.md) - [LeNet](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/lenet/README.md)
- [LeNet_Quant](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/lenet_quant/README.md) - [LeNet_Quant](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/lenet_quant/README.md)
- [MobileNetV2](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/mobilenetv2/README.md)
- [MobileNetV2_Quant](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/mobilenetv2_quant/README.md)
- [MobileNetV3](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/mobilenetv3/README.md)
- [InceptionV3](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/inceptionv3/README.md) - [InceptionV3](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/inceptionv3/README.md)
- [Object Detection and Segmentation](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv) - [Object Detection and Segmentation](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv)
- [DeepLabV3](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/deeplabv3/README.md) - [DeepLabV3](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/deeplabv3/README.md)
- [FasterRCNN](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/faster_rcnn/README.md) - [FasterRCNN](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/faster_rcnn/README.md)
- [YoloV3-DarkNet53](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/yolov3_darknet53/README.md) - [YoloV3-DarkNet53](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/yolov3_darknet53/README.md)
- [YoloV3-ResNet18](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/yolov3_resnet18/README.md) - [YoloV3-ResNet18](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/yolov3_resnet18/README.md)
- [MobileNetV2](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/mobilenetv2/README.md)
- [MobileNetV2_Quant](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/mobilenetv2_quant/README.md)
- [MobileNetV3](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/mobilenetv3/README.md)
- [MaskRCNN](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/maskrcnn/README.md) - [MaskRCNN](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/maskrcnn/README.md)
- [SSD](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/ssd/README.md) - [SSD](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/ssd/README.md)
- [Warp-CTC](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/warpctc/README.md) - [Warp-CTC](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/warpctc/README.md)

2
model_zoo/official/cv/googlenet/README.md
View File

@ -36,7 +36,7 @@ GoogleNet, a 22 layers deep network, was proposed in 2014 and won the first plac
# [Model Architecture](#contents) # [Model Architecture](#contents)
Specifically, the GoogleNet contains numerous inception modules, which are connected together to go deeper. In general, an inception module with dimensionality reduction consists of **1×1 conv**, **3×3 conv**, **5×5 conv**, and **3×3 max pooling**, which are done altogether for the previous input, and stack together again at output. Specifically, the GoogleNet contains numerous inception modules, which are connected together to go deeper. In general, an inception module with dimensionality reduction consists of **1×1 conv**, **3×3 conv**, **5×5 conv**, and **3×3 max pooling**, which are done altogether for the previous input, and stack together again at output. In our model architecture, the kernel size used in inception module is 3×3 instead of 5×5.