m53297601
/
mindspore
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

!9553 update nasnet readme cn

Browse Source 
From: @pandoublefeng
Reviewed-by: @c_34
Signed-off-by: @c_34
pull/9553/MERGE
mindspore-ci-bot 4 years ago committed by Gitee
parent 186f5394ba 3903e5797a
commit 5518bbeeb0
2 changed files with 128 additions and 78 deletions
Show Stats Download Patch File Download Diff File

47
model_zoo/official/cv/nasnet/README.md
Unescape View File

@ -4,7 +4,7 @@
- [Model Architecture](#model-architecture) - [Model Architecture](#model-architecture)
- [Dataset](#dataset) - [Dataset](#dataset)
- [Environment Requirements](#environment-requirements) - [Environment Requirements](#environment-requirements)
- [Quick Start](#quick-start) - [Quick Start](#quick-start)
- [Script Description](#script-description) - [Script Description](#script-description)
- [Script and Sample Code](#script-and-sample-code) - [Script and Sample Code](#script-and-sample-code)
- [Script Parameters](#script-parameters) - [Script Parameters](#script-parameters)
@ -18,7 +18,6 @@
# [NASNet Description](#contents) # [NASNet Description](#contents)
[Paper](https://arxiv.org/abs/1707.07012): Barret Zoph, Vijay Vasudevan, Jonathon Shlens, Quoc V. Le. Learning Transferable Architectures for Scalable Image Recognition. 2017. [Paper](https://arxiv.org/abs/1707.07012): Barret Zoph, Vijay Vasudevan, Jonathon Shlens, Quoc V. Le. Learning Transferable Architectures for Scalable Image Recognition. 2017.
# [Model architecture](#contents) # [Model architecture](#contents)
@ -27,27 +26,25 @@ The overall network architecture of NASNet is show below:
[Link](https://arxiv.org/abs/1707.07012) [Link](https://arxiv.org/abs/1707.07012)
# [Dataset](#contents) # [Dataset](#contents)
Dataset used: [imagenet](http://www.image-net.org/) Dataset used: [imagenet](http://www.image-net.org/)
- Dataset size: ~125G, 1.2W colorful images in 1000 classes - Dataset size: ~125G, 1.2W colorful images in 1000 classes
- Train: 120G, 1.2W images - Train: 120G, 1.2W images
- Test: 5G, 50000 images - Test: 5G, 50000 images
- Data format: RGB images. - Data format: RGB images.
- Note: Data will be processed in src/dataset.py - Note: Data will be processed in src/dataset.py
# [Environment Requirements](#contents) # [Environment Requirements](#contents)
- Hardware GPU - Hardware GPU
- Prepare hardware environment with GPU processor. - Prepare hardware environment with GPU processor.
- Framework - Framework
- [MindSpore](https://www.mindspore.cn/install/en) - [MindSpore](https://www.mindspore.cn/install/en)
- For more information, please check the resources below： - For more information, please check the resources below：
- [MindSpore Tutorials](https://www.mindspore.cn/tutorial/training/en/master/index.html) - [MindSpore Tutorials](https://www.mindspore.cn/tutorial/training/en/master/index.html)
- [MindSpore Python API](https://www.mindspore.cn/doc/api_python/en/master/index.html) - [MindSpore Python API](https://www.mindspore.cn/doc/api_python/en/master/index.html)
# [Script description](#contents) # [Script description](#contents)
@ -77,7 +74,7 @@ Dataset used: [imagenet](http://www.image-net.org/)
Parameters for both training and evaluating can be set in config.py. Parameters for both training and evaluating can be set in config.py.
``` ```python
'random_seed': 1, # fix random seed 'random_seed': 1, # fix random seed
'rank': 0, # local rank of distributed 'rank': 0, # local rank of distributed
'group_size': 1, # world size of distributed 'group_size': 1, # world size of distributed
@ -102,9 +99,9 @@ Parameters for both training and evaluating can be set in config.py.
## [Training Process](#contents) ## [Training Process](#contents)
#### Usage ### Usage
``` ```bash
GPU: GPU:
# distribute training example(8p) # distribute training example(8p)
sh run_distribute_train_for_gpu.sh DATA_DIR sh run_distribute_train_for_gpu.sh DATA_DIR
@ -112,7 +109,7 @@ GPU:
sh run_standalone_train_for_gpu.sh DEVICE_ID DATA_DIR sh run_standalone_train_for_gpu.sh DEVICE_ID DATA_DIR
``` ```
#### Launch ### Launch
```bash ```bash
# distributed training example(8p) for GPU # distributed training example(8p) for GPU
@ -127,25 +124,23 @@ You can find checkpoint file together with result in log.
### Usage ### Usage
``` ```bash
# Evaluation # Evaluation
sh run_eval_for_gpu.sh DEVICE_ID DATA_DIR PATH_CHECKPOINT sh run_eval_for_gpu.sh DEVICE_ID DATA_DIR PATH_CHECKPOINT
``` ```
#### Launch ### Launch
```bash ```bash
# Evaluation with checkpoint # Evaluation with checkpoint
sh scripts/run_eval_for_gpu.sh 0 /dataset/val ./checkpoint/nasnet-a-mobile-rank0-248_10009.ckpt sh scripts/run_eval_for_gpu.sh 0 /dataset/val ./checkpoint/nasnet-a-mobile-rank0-248_10009.ckpt
``` ```
#### Result ### Result
Evaluation result will be stored in the scripts path. Under this, you can find result like the followings in log. Evaluation result will be stored in the scripts path. Under this, you can find result like the followings in log.
```
acc=73.5%(TOP1) acc=73.5%(TOP1)
```
# [Model description](#contents) # [Model description](#contents)
@ -163,7 +158,6 @@ acc=73.5%(TOP1)
| Optimizer | Momentum | | Optimizer | Momentum |
| Loss Function | SoftmaxCrossEntropyWithLogits | | Loss Function | SoftmaxCrossEntropyWithLogits |
| Loss | 1.8965 | | Loss | 1.8965 |
| Accuracy | 73.5%(TOP1) |
| Total time | 144 h 8ps | | Total time | 144 h 8ps |
| Checkpoint for Fine tuning | 89 M(.ckpt file) | | Checkpoint for Fine tuning | 89 M(.ckpt file) |
@ -173,13 +167,12 @@ acc=73.5%(TOP1)
| -------------------------- | ------------------------- | | -------------------------- | ------------------------- |
| Resource | NV SMX2 V100-32G | | Resource | NV SMX2 V100-32G |
| uploaded Date | 09/24/2020 | | uploaded Date | 09/24/2020 |
| MindSpore Version | 1.0.0 | | MindSpore Version | 1.0.0 |
| Dataset | ImageNet, 1.2W | | Dataset | ImageNet, 1.2W |
| batch_size | 32 | | batch_size | 32 |
| outputs | probability | | outputs | probability |
| Accuracy | acc=73.5%(TOP1) | | Accuracy | acc=73.5%(TOP1) |
# [ModelZoo Homepage](#contents) # [ModelZoo Homepage](#contents)
Please check the official [homepage](https://gitee.com/mindspore/mindspore/tree/master/model_zoo). Please check the official [homepage](https://gitee.com/mindspore/mindspore/tree/master/model_zoo).

159
model_zoo/official/cv/nasnet/README_CN.md
Unescape View File

@ -1,60 +1,86 @@
# NASNet示例 # 目录
<!-- TOC --> <!-- TOC -->
- [NASNet示例](#nasnet示例) - [目录](#目录)
- [概述](#概述) - [NASNet概述](#NASNet概述)
- [要求](#要求) - [模型架构](#模型架构)
- [结构](#结构) - [数据集](#数据集)
- [参数配置](#参数配置) - [环境要求](#环境要求)
- [运行示例](#运行示例) - [脚本说明](#脚本说明)
- [训练](#训练) - [脚本和样例代码](#脚本和样例代码)
- [用法](#用法) - [脚本参数](#脚本参数)
- [运行](#运行) - [训练过程](#训练过程)
- [结果](#结果) - [评估过程](#评估过程)
- [评估](#评估) - [模型描述](#模型描述)
- [用法](#用法-1) - [性能](#性能)
- [启动](#启动) - [训练性能](#训练性能)
- [结果](#结果-1) - [评估性能](#评估性能)
- [ModelZoo主页](#modelzoo主页)
<!-- /TOC --> <!-- /TOC -->
## 概述 # NASNet概述
此为MindSpore中训练NASNet-A-Mobile的示例。 [论文](https://arxiv.org/abs/1707.07012): Barret Zoph, Vijay Vasudevan, Jonathon Shlens, Quoc V. Le. Learning Transferable Architectures for Scalable Image Recognition. 2017.
## 要求 # 模型架构
- 安装[Mindspore](http://www.mindspore.cn/install/en)。 NASNet总体网络架构如下：
- 下载数据集。
## 结构 [链接](https://arxiv.org/abs/1707.07012)
```shell # 数据集
使用的数据集：[imagenet](http://www.image-net.org/)
- 数据集大小：125G，共1000个类、1.2万张彩色图像
- 训练集：120G，共1.2万张图像
- 测试集：5G，共5万张图像
- 数据格式：RGB
* 注：数据在src/dataset.py中处理。
# 环境要求
- 硬件：GPU
- 使用GPU处理器来搭建硬件环境。
- 框架
- [MindSpore](https://www.mindspore.cn/install)
- 如需查看详情，请参见如下资源：
- [MindSpore教程](https://www.mindspore.cn/tutorial/training/en/master/index.html)
- [MindSpore Python API](https://www.mindspore.cn/doc/api_python/en/master/index.html)
# 脚本说明
## 脚本及样例代码
```python
. .
└─nasnet └─nasnet
├─README.md ├─README.md
├─scripts ├─README_CN.md
├─run_standalone_train_for_gpu.sh # 使用GPU平台启动单机训练（单卡） ├─scripts
├─Run_distribute_train_for_gpu.sh # 使用GPU平台启动分布式训练（8卡） ├─run_standalone_train_for_gpu.sh # 使用GPU平台启动单机训练（单卡）
└─Run_eval_for_gpu.sh # 使用GPU平台进行启动评估 ├─run_distribute_train_for_gpu.sh # 使用GPU平台启动分布式训练（8卡）
└─run_eval_for_gpu.sh # 使用GPU平台进行启动评估
├─src ├─src
├─config.py # 参数配置 ├─config.py # 参数配置
├─dataset.py # 数据预处理 ├─dataset.py # 数据预处理
├─loss.py # 自定义交叉熵损失函数 ├─loss.py # 自定义交叉熵损失函数
├─lr_generator.py # 学习率生成器 ├─lr_generator.py # 学习率生成器
├─nasnet_a_mobile.py # 网络定义 ├─nasnet_a_mobile.py # 网络定义
├─eval.py # 评估网络 ├─eval.py # 评估网络
├─export.py # 转换检查点 ├─export.py # 转换检查点
└─train.py # 训练网络 └─train.py # 训练网络
``` ```
## 参数配置 ## 脚本参数
在config.py中可以同时配置训练参数和评估参数。 在config.py中可以同时配置训练参数和评估参数。
``` ```python
'random_seed':1, # 固定随机种子 'random_seed':1, # 固定随机种子
'rank':0, # 分布式训练进程序号 'rank':0, # 分布式训练进程序号
'group_size':1, # 分布式训练分组大小 'group_size':1, # 分布式训练分组大小
@ -75,25 +101,20 @@
'opt_eps':1.0, # epsilon参数 'opt_eps':1.0, # epsilon参数
'rmsprop_decay':0.9, # rmsprop衰减 'rmsprop_decay':0.9, # rmsprop衰减
'loss_scale':1, # 损失规模 'loss_scale':1, # 损失规模
``` ```
## 训练过程
### 用法
## 运行示例 ```bash
### 训练
#### 用法
```
# 分布式训练示例（8卡） # 分布式训练示例（8卡）
sh run_distribute_train_for_gpu.sh DATA_DIR sh run_distribute_train_for_gpu.sh DATA_DIR
# 单机训练 # 单机训练
sh run_standalone_train_for_gpu.sh DEVICE_ID DATA_DIR sh run_standalone_train_for_gpu.sh DEVICE_ID DATA_DIR
``` ```
#### 运行 ### 运行
```bash ```bash
# GPU分布式训练示例（8卡） # GPU分布式训练示例（8卡）
@ -102,20 +123,20 @@ sh scripts/run_distribute_train_for_gpu.sh /dataset/train
sh scripts/run_standalone_train_for_gpu.sh 0 /dataset/train sh scripts/run_standalone_train_for_gpu.sh 0 /dataset/train
``` ```
#### 结果 ### 结果
可以在日志中找到检查点文件及结果。 可以在日志中找到检查点文件及结果。
### 评估 ## 评估过程
#### 用法 ### 用法
``` ```bash
# 评估 # 评估
sh run_eval_for_gpu.sh DEVICE_ID DATA_DIR PATH_CHECKPOINT sh run_eval_for_gpu.sh DEVICE_ID DATA_DIR PATH_CHECKPOINT
``` ```
#### 启动 ### 启动
```bash ```bash
# 检查点评估 # 检查点评估
@ -124,7 +145,43 @@ sh scripts/run_eval_for_gpu.sh 0 /dataset/val ./checkpoint/nasnet-a-mobile-rank0
> 训练过程中可以生成检查点。 > 训练过程中可以生成检查点。
#### 结果 ### 结果
评估结果保存在脚本路径下。路径下的日志中，可以找到如下结果： 评估结果保存在脚本路径下。路径下的日志中，可以找到如下结果：
acc=73.5%(TOP1)
# 模型描述
## 性能
### 训练性能
| 参数 | NASNet |
| -------------------------- | ------------------------- |
| 资源 | NV SMX2 V100-32G |
| 上传日期 | 2020-09-24 |
| MindSpore版本 | 1.0.0 |
| 数据集 | ImageNet |
| 训练参数 | src/config.py |
| 优化器 | Momentum |
| 损失函数 | SoftmaxCrossEntropyWithLogits |
| 损失值 | 1.8965 |
| 总时间 | 8卡运行约144个小时 |
| 检查点文件大小 | 89 M(.ckpt文件) |
### 评估性能
| 参数 | |
| -------------------------- | ------------------------- |
| 资源 | NV SMX2 V100-32G |
| 上传日期 | 2020-09-24 |
| MindSpore版本 | 1.0.0 |
| 数据及 | ImageNet, 1.2W |
| batch_size | 32 |
| 输出 | 概率 |
| 精确度 | acc=73.5%(TOP1) |
# ModelZoo主页
请浏览官网[主页](https://gitee.com/mindspore/mindspore/tree/master/model_zoo)。

Write Preview
Loading…
Cancel
Save