Skip to content
Snippets Groups Projects
Unverified Commit 2702c37e authored by i-robot's avatar i-robot Committed by Gitee
Browse files

!2008 Fix some errors in readme.

Merge pull request !2008 from chenhaozhe/update-readme
parents 34160cbd 5cf55113
No related branches found
No related tags found
No related merge requests found
......@@ -3,15 +3,13 @@
<!-- TOC -->
- [目录](#目录)
- [Eassay-Recognition描述](#essay-recognition描述)
- [模型架构](#模型架构)
- [数据集](#数据集)
- [环境要求](#环境要求)
- [Eassay-Recognition描述](#eassay-recognition描述)
- [模型架构](#模型架构)
- [数据集](#数据集)
- [环境要求](#环境要求)
- [快速入门](#快速入门)
- [脚本说明](#脚本说明)
- [脚本及样例代码](#脚本及样例代码)
- [脚本参数](#脚本参数)
- [训练脚本参数](#训练脚本参数)
- [参数配置](#参数配置)
- [训练过程](#训练过程)
- [训练](#训练)
......@@ -21,8 +19,6 @@
- [性能](#性能)
- [训练性能](#训练性能)
- [评估性能](#评估性能)
- [推理性能](#推理性能)
- [ModelZoo主页](#modelzoo主页)
<!-- /TOC -->
......@@ -42,7 +38,7 @@
# 数据集
[训练样例数据及字符集文件](链接:https://pan.baidu.com/s/1_Nv3lMxZpfxUjRoqoDs8Tghwdb)
[训练样例数据及字符集文件](https://pan.baidu.com/s/1_Nv3lMxZpfxUjRoqoDs8Tghwdb)
提取码:hwdb
......
# Contents
- [Contents](#contents)
- [Predrnn++ Description](#Predrnn++-description)
- [Predrnn++ Description](#predrnn-description)
- [Model Architecture](#model-architecture)
- [Dataset](#dataset)
- [Dataset Prepare](#dataset-prepare)
......@@ -11,8 +11,6 @@
- [Script and Sample Code](#script-and-sample-code)
- [Script Parameters](#script-parameters)
- [Training Script Parameters](#training-script-parameters)
- [Parameters Configuration](#parameters-configuration)
- [Dataset Preparation](#dataset-preparation)
- [Training Process](#training-process)
- [Training](#training)
- [Evaluation Process](#evaluation-process)
......@@ -21,7 +19,6 @@
- [Performance](#performance)
- [Training Performance](#training-performance)
- [Evaluation Performance](#evaluation-performance)
- [Description of MindSpore Version](#description-of-mindspore-version)
- [ModelZoo Homepage](#modelzoo-homepage)
## [Predrnn++ Description](#contents)
......@@ -204,7 +201,7 @@ mse per seq: 478.58854093653633
| Speed | 983ms/step(1pcs) |
| Total time | 22h |
| Checkpoint for Fine tuning | 177.27M (.ckpt file) |
| Scripts | [Link](https://gitee.com/mindspore/models/tree/master/official/cv/Predrnn++) |
| Scripts | [Link](https://gitee.com/mindspore/models/tree/master/official/cv/predrnn++) |
#### [Evaluation Performance](#contents)
......
# Contents
- [PWCnet Description](#PWCnet-description)
- [Contents](#contents)
- [PWCnet Description](#pwcnet-description)
- [Model Architecture](#model-architecture)
- [Dataset](#dataset)
- [pretrained](#pretrained)
- [Environment Requirements](#environment-requirements)
- [Script Description](#script-description)
- [Script and Sample Code](#script-and-sample-code)
- [Running Example](#running-example)
- [Train](#train)
- [Evaluation](#evaluation)
- [Model Description](#model-description)
- [Performance](#performance)
- [Training Performance](#training-performance)
- [Evaluation Performance](#evaluation-performance)
- [ModelZoo Homepage](#modelzoo-homepage)
# [PWCnet Description](#contents)
......@@ -95,8 +101,8 @@ bash scripts/run_ckpt_convert.sh [PYTORCH_FILE_PATH] [MINDSPORE_FILE_PATH]
- Framework
- [MindSpore](https://www.mindspore.cn/install/en)
- For more information, please check the resources below:
- [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 tutorials](https://www.mindspore.cn/tutorials/en/master/index.html)
- [MindSpore Python API](https://www.mindspore.cn/docs/api/en/master/index.html)
# [Script Description](#contents)
......@@ -230,4 +236,4 @@ EPE: 6.9049
# [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/models).
......@@ -2,9 +2,11 @@
<!-- TOC -->
- [GRU](#gru)
- [Paper](#paper)
- [Model Structure](#model-structure)
- [Dataset](#dataset)
- [Environment Requirements](#environment-requirements)
- [Requirements](#requirements)
- [Quick Start](#quick-start)
- [Script Description](#script-description)
- [Dataset Preparation](#dataset-preparation)
......@@ -12,7 +14,9 @@
- [Training Process](#training-process)
- [Inference Process](#inference-process)
- [Export MindIR](#export-mindir)
- [Inference Process](#inference-process)
- [Inference Process](#inference-process-1)
- [Usage](#usage)
- [result](#result)
- [Model Description](#model-description)
- [Performance](#performance)
- [Training Performance](#training-performance)
......@@ -29,7 +33,7 @@ GRU(Gate Recurrent Unit) is a kind of recurrent neural network algorithm, just l
## Paper
1.[Paper](https://arxiv.org/pdf/1607.01759.pdf): "Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation", 2014, Kyunghyun Cho, Bart van Merrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, Yoshua Bengio
1.[Paper](https://arxiv.org/abs/1406.1078): "Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation", 2014, Kyunghyun Cho, Bart van Merrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, Yoshua Bengio
2.[Paper](https://arxiv.org/pdf/1409.3215.pdf): "Sequence to Sequence Learning with Neural Networks", 2014, Ilya Sutskever, Oriol Vinyals, Quoc V. Le
......
......@@ -3,7 +3,7 @@
<!-- TOC -->
- [目录](#目录)
- [PDarts描述](#PDarts描述)
- [PDarts描述](#pdarts描述)
- [模型架构](#模型架构)
- [数据集](#数据集)
- [特性](#特性)
......@@ -15,12 +15,10 @@
- [脚本参数](#脚本参数)
- [训练过程](#训练过程)
- [训练](#训练)
- [分布式训练](#分布式训练)
- [评估过程](#评估过程)
- [评估](#评估)
- [推理过程](#推理过程)
- [导出MindIR](#导出MindIR)
- [在Ascend310执行推理](#在Ascend310执行推理)
- [导出MindIR](#导出mindir)
- [在Ascend310执行推理](#在ascend310执行推理)
- [模型描述](#模型描述)
- [性能](#性能)
- [训练准确率结果](#训练准确率结果)
......@@ -59,17 +57,16 @@
## 混合精度
采用[混合精度](https://www.mindspore.cn/tutorial/training/zh-CN/master/advanced_use/enable_mixed_precision.html)的训练方法使用支持单精度和半精度数据来提高深度学习神经网络的训练速度,同时保持单精度训练所能达到的网络精度。混合精度训练提高计算速度、减少内存使用的同时,支持在特定硬件上训练更大的模型或实现更大批次的训练。
采用[混合精度](https://www.mindspore.cn/docs/programming_guide/zh-CN/r1.6/enable_mixed_precision.html)的训练方法使用支持单精度和半精度数据来提高深度学习神经网络的训练速度,同时保持单精度训练所能达到的网络精度。混合精度训练提高计算速度、减少内存使用的同时,支持在特定硬件上训练更大的模型或实现更大批次的训练。
# 环境要求
- 硬件(Ascend910)
- 准备Ascend AI处理器搭建硬件环境。如需试用昇腾处理器,请发送[申请表](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx)至ascend@huawei.com,审核通过即可获得资源。
- 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/zh-CN/master/index.html)
- [MindSpore Python API](https://www.mindspore.cn/doc/api_python/zh-CN/master/index.html)
- [MindSpore教程](https://www.mindspore.cn/tutorials/zh-CN/master/index.html)
- [MindSpore Python API](https://www.mindspore.cn/docs/api/zh-CN/master/index.html)
# 快速入门
......
# Contents
- [Aug-ViT Description](https://gitee.com/mindspore/models/tree/master/research/cv/AugViT#AugViT-description)
- [Model Architecture](https://gitee.com/mindspore/models/tree/master/research/cv/AugViT#model-architecture)
- [Dataset](https://gitee.com/mindspore/models/tree/master/research/cv/AugViT#dataset)
- [Environment Requirements](https://gitee.com/mindspore/models/tree/master/research/cv/AugViT#environment-requirements)
- Script Description
- Script and Sample Code
- [Training Process](https://gitee.com/mindspore/models/tree/master/research/cv/AugViT#training-process)
- Evaluation Process
- [Evaluation](https://gitee.com/mindspore/models/tree/master/research/cv/AugViT#evaluation)
- Model Description
- Performance
- [Training Performance](https://gitee.com/mindspore/models/tree/master/research/cv/AugViT#evaluation-performance)
- [Inference Performance](https://gitee.com/mindspore/models/tree/master/research/cv/AugViT#evaluation-performance)
- [Description of Random Situation](https://gitee.com/mindspore/models/tree/master/research/cv/AugViT#description-of-random-situation)
- [ModelZoo Homepage](https://gitee.com/mindspore/models/tree/master/research/cv/AugViT#modelzoo-homepage)
## [Aug-ViT Description](https://gitee.com/mindspore/models/tree/master/research/cv/AugViT#contents)
- [Contents](#contents)
- [Aug-ViT Description](#aug-vit-description)
- [Model architecture](#model-architecture)
- [Dataset](#dataset)
- [Environment Requirements](#environment-requirements)
- [Script description](#script-description)
- [Script and sample code](#script-and-sample-code)
- [Eval process](#eval-process)
- [Usage](#usage)
- [Launch](#launch)
- [Result](#result)
- [Description of Random Situation](#description-of-random-situation)
- [ModelZoo Homepage](#modelzoo-homepage)
## [Aug-ViT Description](#contents)
Aug-ViT inserts additional paths with learnable parameters in parallel on the original shortcuts for alleviating the feature collapse. The block-circulant projection is used to implement augmented shortcut, which brings negligible increase of computational cost.
[Paper](https://arxiv.org/abs/2106.15941): Yehui Tang, Kai Han, Chang Xu, An Xiao, Yiping Deng, Chao Xu, Yunhe Wang. Augmented Shortcuts for Vision Transformers. NeurIPS 2021.
## [Model architecture](https://gitee.com/mindspore/models/tree/master/research/cv/AugViT#contents)
## [Model architecture](#contents)
A block of Aug-ViT is show below:
![image-20211026160438718](./fig/augvit.png)
## [Dataset](https://gitee.com/mindspore/models/tree/master/research/cv/AugViT#contents)
## [Dataset](#contents)
Dataset used: [CIFAR-10](https://www.cs.toronto.edu/~kriz/cifar.html)
......@@ -37,7 +35,7 @@ Dataset used: [CIFAR-10](https://www.cs.toronto.edu/~kriz/cifar.html)
- Test: 10000 images
- Data format: RGB images.
## [Environment Requirements](https://gitee.com/mindspore/models/tree/master/research/cv/AugViT#contents)
## [Environment Requirements](#contents)
- Hardware(Ascend/GPU)
- Prepare hardware environment with Ascend or GPU.
......@@ -47,9 +45,9 @@ Dataset used: [CIFAR-10](https://www.cs.toronto.edu/~kriz/cifar.html)
- [MindSpore Tutorials](https://www.mindspore.cn/tutorials/en/master/index.html)
- [MindSpore Python API](https://www.mindspore.cn/docs/api/en/master/index.html)
## [Script description](https://gitee.com/mindspore/models/tree/master/research/cv/AugViT#contents)
## [Script description](#contents)
### [Script and sample code](https://gitee.com/mindspore/models/tree/master/research/cv/AugViT#contents)
### [Script and sample code](#contents)
```bash
AugViT
......@@ -63,7 +61,7 @@ AugViT
└── augvit.py # augvit network
```
## [Eval process](https://gitee.com/mindspore/models/tree/master/research/cv/AugViT#contents)
## [Eval process](#contents)
### Usage
......@@ -84,10 +82,10 @@ After installing MindSpore via the official website, you can start evaluation as
result: {'acc': 0.98} ckpt= ./augvit_c10.ckpt
```
## [Description of Random Situation](https://gitee.com/mindspore/models/tree/master/research/cv/AugViT#contents)
## [Description of Random Situation](#contents)
In dataset.py, we set the seed inside "create_dataset" function. We also use random seed in train.py.
## [ModelZoo Homepage](https://gitee.com/mindspore/models/tree/master/research/cv/AugViT#contents)
## [ModelZoo Homepage](#contents)
Please check the official [homepage](https://gitee.com/mindspore/models).
\ No newline at end of file
......@@ -3,7 +3,7 @@
<!-- TOC -->
- [目录](#目录)
- [Inception_ResNet_v2描述](#Inception_ResNet_v2描述)
- [Inception_ResNet_v2描述](#inception_resnet_v2描述)
- [模型架构](#模型架构)
- [数据集](#数据集)
- [特性](#特性)
......@@ -14,12 +14,13 @@
- [脚本参数](#脚本参数)
- [训练过程](#训练过程)
- [用法](#用法)
- [启动](#启动)
- [结果](#结果)
- [Ascend](#ascend)
- [GPU](#gpu)
- [评估过程](#评估过程)
- [用法](#用法-1)
- [启动](#启动-1)
- [结果](#结果-1)
- [模型导出](#模型导出)
- [模型描述](#模型描述)
- [性能](#性能)
- [训练性能](#训练性能)
......
# Contents
- [STGCN 介绍](#STGCN-介绍)
- [Contents](#contents)
- [STGCN 介绍](#stgcn-介绍)
- [模型架构](#模型架构)
- [数据集](#数据集)
- [环境要求](#环境要求)
......@@ -17,10 +18,13 @@
- [用法](#用法)
- [结果](#结果)
- [模型介绍](#模型介绍)
- [性能](#性能)
- [性能](#性能)
- [评估性能](#评估性能)
- [STGCN on PeMSD7-m (Cheb,n_pred=9)](#stgcn-on-pemsd7-m-chebn_pred9)
- [Inference Performance](#inference-performance)
- [STGCN on PeMSD7-m (Cheb,n_pred=9)](#stgcn-on-pemsd7-m-chebn_pred9-1)
- [随机事件介绍](#随机事件介绍)
- [ModelZoo 主页](#ModelZoo-主页)
- [ModelZoo 主页](#modelzoo-主页)
# [STGCN 介绍](#contents)
......@@ -40,7 +44,7 @@ Dataset used:
PeMED7(PeMSD7-m、PeMSD7-L)
BJER4
由于数据集下载原因,只找到了[PeMSD7-M](https://github.com/hazdzz/STGCN/tree/main/data/train/road_traffic/pemsd7-m)数据集。
由于数据集下载原因,只找到了[PeMSD7-M](https://github.com/hazdzz/STGCN/tree/main/data/pemsd7-m)数据集。
# [环境要求](#contents)
......
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment