Skip to content

M
mindspore

magicwindyyd / mindspore
与 Fork 源项目一致

Fork自 MindSpore / mindspore

通知 1
Star 1
Fork 0
M
mindspore
提交 0a3bf64b 编写于 作者: M mindspore-ci-bot 提交者： Gitee
浏览文件
操作

!2877 modify lenet&alexnet README.md in model_zoo 

Merge pull request !2877 from wukesong/add_lenet_alexnet_readme
上级 e03bd975 5421d818
隐藏空白更改
内联 并排
Showing with 30 addition and 32 deletion
model_zoo/README.md
浏览文件 @ 0a3bf64b
...@@ -134,43 +134,41 @@ In order to facilitate developers to enjoy the benefits of MindSpore framework a ...@@ -134,43 +134,41 @@ In order to facilitate developers to enjoy the benefits of MindSpore framework a
| Parameters | AlexNet | | Parameters | AlexNet |
| -------------------------- | ------- | | -------------------------- | ------- |
| Published Year | | | Published Year | 2012 |
| Paper | | | Paper | [ImageNet Classification with Deep Convolutional Neural Networks](http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-) |
| Resource | | | Resource | Ascend 910 |
| Features | | | Features | support with Ascend, GPU |
| MindSpore Version | | | MindSpore Version | 0.5.0-beta |
| Dataset | | | Dataset | CIFAR10 |
| Training Parameters | | | Training Parameters | epoch=30, batch_size=32 |
| Optimizer | | | Optimizer | Momentum |
| Loss Function | | | Loss Function | SoftmaxCrossEntropyWithLogits |
| Accuracy | | | Accuracy | 88.23% |
| Speed | | | Speed | 1481fps |
| Loss | | | Loss | 0.108 |
| Params (M) | | | Params (M) | 61.10 |
| Checkpoint for Fine tuning | | | Checkpoint for Fine tuning | 445MB(.ckpt file) |
| Model for inference | | | Scripts | https://gitee.com/mindspore/mindspore/tree/master/model_zoo/alexnet|
| Scripts | |
#### [LeNet](#table-of-contents) #### [LeNet](#table-of-contents)
| Parameters | LeNet | | Parameters | LeNet |
| -------------------------- | ----- | | -------------------------- | ----- |
| Published Year | | | Published Year | 1998 |
| Paper | | | Paper | [Gradient-Based Learning Applied to Document Recognition](https://ieeexplore.ieee.org/abstract/document/726791) |
| Resource | | | Resource | Ascend 910 |
| Features | | | Features | support with Ascend, GPU, CPU |
| MindSpore Version | | | MindSpore Version | 0.5.0-beta |
| Dataset | | | Dataset | MNIST |
| Training Parameters | | | Training Parameters | epoch=10, batch_size=32 |
| Optimizer | | | Optimizer | Momentum |
| Loss Function | | | Loss Function | SoftmaxCrossEntropyWithLogits |
| Accuracy | | | Accuracy | 98.52% |
| Speed | | | Speed | 18680fps |
| Loss | | | Loss | 0.004 |
| Params (M) | | | Params (M) | 0.06 |
| Checkpoint for Fine tuning | | | Checkpoint for Fine tuning | 483KB(.ckpt file) |
| Model for inference | | | Scripts | https://gitee.com/mindspore/mindspore/tree/master/model_zoo/lenet|
| Scripts | |
### Object Detection and Segmentation ### Object Detection and Segmentation
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或