meng_chunyang
5 years ago
3 changed files with 22 additions and 1 deletions
Unified View
Diff Options
-
+0 -1RELEASE.md
-
+11 -0mindspore/lite/README.md
-
+11 -0mindspore/lite/README_CN.md
+ 0
- 1
RELEASE.md
View File
| @@ -57,7 +57,6 @@ | |||||
| * Add 93 TFLite op. | * Add 93 TFLite op. | ||||
| * Add 24 Caffe op. | * Add 24 Caffe op. | ||||
| * Add 62 ONNX op. | * Add 62 ONNX op. | ||||
| * Add support for windows. | |||||
| * Add 11 optimized passes, include fusion/const fold. | * Add 11 optimized passes, include fusion/const fold. | ||||
| * Support aware-training and Post-training quantization. | * Support aware-training and Post-training quantization. | ||||
| * CPU | * CPU | ||||
+ 11
- 0
mindspore/lite/README.md
View File
| @@ -54,3 +54,14 @@ For more details please check out our [MindSpore Lite Architecture Guide](https: | |||||
| Load the model and perform inference. [Inference](https://www.mindspore.cn/lite/tutorial/en/master/use/runtime.html) is the process of running input data through the model to get output. | Load the model and perform inference. [Inference](https://www.mindspore.cn/lite/tutorial/en/master/use/runtime.html) is the process of running input data through the model to get output. | ||||
| MindSpore provides a series of pre-trained models that can be deployed on mobile device [example](#TODO). | MindSpore provides a series of pre-trained models that can be deployed on mobile device [example](#TODO). | ||||
| ## MindSpore Lite benchmark test result | |||||
| Base on MindSpore r0.7, we test a couple of networks on HUAWEI Mate30 (Hisilicon Kirin990) mobile phone, and get the test results below for your reference. | |||||
| | NetWork | Thread Number | Average Run Time(ms) | | |||||
| | ------------------- | ------------- | -------------------- | | |||||
| | basic_squeezenet | 4 | 9.10 | | |||||
| | inception_v3 | 4 | 69.361 | | |||||
| | mobilenet_v1_10_224 | 4 | 7.137 | | |||||
| | mobilenet_v2_10_224 | 4 | 5.569 | | |||||
| | resnet_v2_50 | 4 | 48.691 | | |||||
+ 11
- 0
mindspore/lite/README_CN.md
View File
| @@ -64,3 +64,14 @@ MindSpore Lite是MindSpore推出的端云协同的、轻量化、高性能AI推 | |||||
| 主要完成模型推理工作，即加载模型，完成模型相关的所有计算。[推理](https://www.mindspore.cn/lite/tutorial/zh-CN/master/use/runtime.html)是通过模型运行输入数据，获取预测的过程。 | 主要完成模型推理工作，即加载模型，完成模型相关的所有计算。[推理](https://www.mindspore.cn/lite/tutorial/zh-CN/master/use/runtime.html)是通过模型运行输入数据，获取预测的过程。 | ||||
| MindSpore提供了一系列预训练模型部署在智能终端的[样例](#TODO)。 | MindSpore提供了一系列预训练模型部署在智能终端的[样例](#TODO)。 | ||||
| ## MindSpore Lite性能参考数据 | |||||
| 我们在HUAWEI Mate30（Hisilicon Kirin990）手机上，基于MindSpore r0.7，测试了一组端侧常见网络的性能数据，供您参考： | |||||
| | 网络 | 线程数 | 平均推理时间(毫秒) | | |||||
| | ------------------- | ------ | ------------------ | | |||||
| | basic_squeezenet | 4 | 9.10 | | |||||
| | inception_v3 | 4 | 69.361 | | |||||
| | mobilenet_v1_10_224 | 4 | 7.137 | | |||||
| | mobilenet_v2_10_224 | 4 | 5.569 | | |||||
| | resnet_v2_50 | 4 | 48.691 | | |||||