معرفی شرکت ها
autodl-gpu-0.1.1
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشترتوضیحات
Automatic Deep Learning, towards fully automated multi-label classification for image, video, text, speech, tabular data.
| ویژگی | مقدار |
|---|---|
| سیستم عامل | - |
| نام فایل | autodl-gpu-0.1.1 |
| نام | autodl-gpu |
| نسخه کتابخانه | 0.1.1 |
| نگهدارنده | [] |
| ایمیل نگهدارنده | [] |
| نویسنده | DeepWisdom |
| ایمیل نویسنده | autodl@fuzhi.ai |
| آدرس صفحه اصلی | https://github.com/DeepWisdom/AutoDL |
| آدرس اینترنتی | https://pypi.org/project/autodl-gpu/ |
| مجوز | Apache 2.0 |
English | [简体中文](./README.md)
<p align="center">
[](https://github.com/DeepWisdom/AutoDL/issues)
[](https://github.com/DeepWisdom/AutoDL/network)
[](https://github.com/DeepWisdom/AutoDL/stargazers)
[](https://github.com/DeepWisdom/AutoDL/blob/master/LICENSE)
[](https://github.com/DeepWisdom/AutoDL#%E5%8A%A0%E5%85%A5%E7%A4%BE%E5%8C%BA)
</p>
# 1. NeurIPS AutoDL Challenge 1'st Solution
**1st** solution for [AutoDL Challenge@NeurIPS](https://autodl.chalearn.org/neurips2019), competition rules can be found at [AutoDL Competition](https://autodl.lri.fr/competitions/162).
### 1.0.1. Motivation
There exists a series of common and tough problems in the real world, such as limited resources (CPU/ memory), skewed data, hand-craft features, model selection, network architecture details tuning, sensitivity of pre-trained models, sensitivity of hyperparameters and so on. How to solve them wholly and efficiently?
### 1.0.2. Solution
AutoDL concentrates on developing generic algorithms for multi-label classification problems in ANY modalities: image, video, speech, text and tabular data without ANY human intervention. **Ten seconds** at the soonest, our solution achieved SOTA performances on all the 24 offline datasets and 15 online datasets, beating a number of top players in the world.
## 1.1. Table of Contents
<!-- TOC -->
- [1. NeurIPS AutoDL Challenge 1'st Solution](#1-neurips-autodl-challenge-1st-solution)
- [1.0.1. Motivation](#101-motivation)
- [1.0.2. Solution](#102-solution)
- [1.1. Table of Contents](#11-table-of-contents)
- [1.2. Features](#12-features)
- [1.3. Evaluation](#13-evaluation)
- [1.4. Installation](#14-installation)
- [1.4.1. With pip](#141-with-pip)
- [1.5. Quick Tour](#15-quick-tour)
- [1.5.1. Run local test tour](#151-run-local-test-tour)
- [1.5.2. Tour of Image Classification](#152-tour-of-image-classification)
- [1.5.3. Tour of Video Classification](#153-tour-of-video-classification)
- [1.5.4. Tour of Speech Classification](#154-tour-of-speech-classification)
- [1.5.5. Tour of Text Classification](#155-tour-of-text-classification)
- [1.5.6. Tour of Tabular Classification](#156-tour-of-tabular-classification)
- [1.6. Public Datasets](#16-public-datasets)
- [1.6.1. Optional: Download public datasets](#161-optional-download-public-datasets)
- [1.6.2. Public datasets sample info](#162-public-datasets-sample-info)
- [1.7. Usage for AutoDL local development and testing](#17-usage-for-autodl-local-development-and-testing)
- [1.8. Contributing](#18-contributing)
- [1.9. Contact us](#19-contact-us)
- [1.10. Join the Community](#110-join-the-community)
- [1.11. License](#111-license)
<!-- /TOC -->
## 1.2. Features
- **Full-AutoML/AutoDL**: Fully automated Deep Learning without ANY human intervention covering the whole pipelines.
- **Generic & Universal**: Supporting ANY modality(image, video, speech, text, tabular) data, and **ANY** classification problems including binary-class, multi-class and multi-label problems.
- **SOTA**: Winner solution of AutoDL challenge, involving both tranditional machine learning models and deep learning model backbones.
- **Out-of-the-Box**: You can use the solution out-of-the-box.
- **Fast**: You can train your model in **ten seconds** at the soonest to get highly competitive performance.
- **Real-time**: You can get the performance feedback(AUC score) in real time.
## 1.3. Evaluation
- **Feedback-phase leaderboard: DeepWisdom Top 1, average rank 1.2, won 4 out of 5 datasets.**
- **Final-phase leaderboard visualization: DeepWisdom Top 1, average rank 1.2, won 7 out of 10 datasets.**
## 1.4. Installation
This repo is tested on Python 3.6+, PyTorch 1.0.0+ and TensorFlow 2.0.
You should install AutoDL in a [virtual environment](https://docs.python.org/3/library/venv.html). If you're unfamiliar with Python virtual environments, check out the [user guide](https://packaging.python.org/guides/installing-using-pip-and-virtual-environments/).
Create a virtual environment with the version of Python you're going to use and activate it.
Now, if you want to use AutoDL, you can install it with pip.
### 1.4.1. With pip
AutoDL can be installed using pip as follows:
```bash
pip install autodl-gpu
pip install autodl-gpu=1.0.0
```
## 1.5. Quick Tour
### 1.5.1. Run local test tour
see [Quick Tour - Run local test tour](https://github.com/DeepWisdom/AutoDL/tree/pip/docs/run_local_test_tutorial_chn.md).
### 1.5.2. Tour of Image Classification
see [Quick Tour - Image Classification Demo](https://github.com/DeepWisdom/AutoDL/tree/pip/docs/image_classification_tutorial_chn.md).
### 1.5.3. Tour of Video Classification
see [Quick Tour - Video Classification Demo](https://github.com/DeepWisdom/AutoDL/pip/docs/video_classification_tutorial_chn.md).
### 1.5.4. Tour of Speech Classification
see [Quick Tour - Speech Classification Demo](https://github.com/DeepWisdom/AutoDL/pip/docs/speech_classification_tutorial_chn.md).
### 1.5.5. Tour of Text Classification
see [Quick Tour - Text Classification Demo](https://github.com/DeepWisdom/AutoDL/pip/docs/text_classification_tutorial_chn.md).
### 1.5.6. Tour of Tabular Classification
see [Quick Tour - Tabular Classification Demo](https://github.com/DeepWisdom/AutoDL/pip/docs/tabular_classification_tutorial_chn.md).
## 1.6. Public Datasets
### 1.6.1. Optional: Download public datasets
```bash
python download_public_datasets.py
```
### 1.6.2. Public datasets sample info
| # | Name | Type | Domain | Size | Source | Data (w/o test labels) | Test labels |
| --- | -------- | ------- | -------- | ------ | ----------- | ---------------------- | ----------------- |
| 1 | Munster | Image | HWR | 18 MB | MNIST | munster.data | munster.solution |
| 2 | City | Image | Objects | 128 MB | Cifar-10 | city.data | city.solution |
| 3 | Chucky | Image | Objects | 128 MB | Cifar-100 | chucky.data | chucky.solution |
| 4 | Pedro | Image | People | 377 MB | PA-100K | pedro.data | pedro.solution |
| 5 | Decal | Image | Aerial | 73 MB | NWPU VHR-10 | decal.data | decal.solution |
| 6 | Hammer | Image | Medical | 111 MB | Ham10000 | hammer.data | hammer.solution |
| 7 | Kreatur | Video | Action | 469 MB | KTH | kreatur.data | kreatur.solution |
| 8 | Kreatur3 | Video | Action | 588 MB | KTH | kreatur3.data | kreatur3.solution |
| 9 | Kraut | Video | Action | 1.9 GB | KTH | kraut.data | kraut.solution |
| 10 | Katze | Video | Action | 1.9 GB | KTH | katze.data | katze.solution |
| 11 | data01 | Speech | Speaker | 1.8 GB | -- | data01.data | data01.solution |
| 12 | data02 | Speech | Emotion | 53 MB | -- | data02.data | dat02.solution |
| 13 | data03 | Speech | Accent | 1.8 GB | -- | data03.data | data03.solution |
| 14 | data04 | Speech | Genre | 469 MB | -- | data04.data | data04.solution |
| 15 | data05 | Speech | Language | 208 MB | -- | data05.data | data05.solution |
| 16 | O1 | Text | Comments | 828 KB | -- | O1.data | O1.solution |
| 17 | O2 | Text | Emotion | 25 MB | -- | O2.data | O2.solution |
| 18 | O3 | Text | News | 88 MB | -- | O3.data | O3.solution |
| 19 | O4 | Text | Spam | 87 MB | -- | O4.data | O4.solution |
| 20 | O5 | Text | News | 14 MB | -- | O5.data | O5.solution |
| 21 | Adult | Tabular | Census | 2 MB | Adult | adult.data | adult.solution |
| 22 | Dilbert | Tabular | -- | 162 MB | -- | dilbert.data | dilbert.solution |
| 23 | Digits | Tabular | HWR | 137 MB | MNIST | digits.data | digits.solution |
| 24 | Madeline | Tabular | -- | 2.6 MB | -- | madeline.data | madeline.solution |
## 1.7. Usage for AutoDL local development and testing
w1. Git clone the repo
```
cd <path_to_your_directory>
git clone https://github.com/DeepWisdom/AutoDL.git
```
2. Prepare pretrained models.
Download model [speech_model.h5](https://github.com/DeepWisdom/AutoDL/releases/download/opensource/thin_resnet34.h5) and put it to `AutoDL_sample_code_submission/at_speech/pretrained_models/` directory.
3. Optional: run in the exact same environment as on the challenge platform with docker.
- CPU
```
cd path/to/autodl/
docker run -it -v "$(pwd):/app/codalab" -p 8888:8888 evariste/autodl:cpu-latest
```
- GPU
```
nvidia-docker run -it -v "$(pwd):/app/codalab" -p 8888:8888 evariste/autodl:gpu-latest
```
4. Prepare sample datasets, using the toy data in `AutoDL_sample_data` or download new datasets.
5. Run local test
```
python run_local_test.py
```
The full usage is
```
python run_local_test.py -dataset_dir='AutoDL_sample_data/miniciao' -code_dir='AutoDL_sample_code_submission'
```
Then you can view the real-time feedback with a learning curve by opening the
HTML page in `AutoDL_scoring_output/`.
Details can be seen in [AutoDL Challenge official starting_kit](https://github.com/zhengying-liu/autodl_starting_kit_stable).
## 1.8. Contributing
Feel free to dive in! [Open an issue](https://github.com/DeepWisdom/AutoDL/issues/new) or submit PRs.
## 1.9. Contact us
[](http://fuzhi.ai/)
## 1.10. Join the Community
Scan QR code and join AutoDL community!
<img src="https://raw.githubusercontent.com/DeepWisdom/AutoDL/pip/assets/WechatIMG15.png" width = "500" height = "200" alt="AutoDL Community" align=center />
## 1.11. License
[Apache License 2.0](https://github.com/DeepWisdom/AutoDL/blob/master/LICENSE)
نیازمندی
| مقدار | نام |
|---|---|
| ==1.16.2 | numpy |
| ==0.24.2 | pandas |
| ==1.15.0 | tensorflow-gpu |
| ==1.0.0 | jupyter |
| ==0.9.0 | seaborn |
| ==1.2.1 | scipy |
| ==3.0.3 | matplotlib |
| ==0.20.3 | scikit-learn |
| ==5.1.1 | pyyaml |
| ==5.6.6 | psutil |
| ==2.9.0 | h5py |
| ==2.2.4 | keras |
| ==1.2.2 | playsound |
| ==0.7.1 | librosa |
| ==3.7.1 | protobuf |
| ==0.90 | xgboost |
| ==2.2.3 | lightgbm |
| ==1.3.1 | torch |
| ==0.4.2 | torchvision |
| ==0.39 | jieba |
| ==3.4.5 | nltk |
| ==2.1.6 | spacy |
| ==3.8.0 | gensim |
| ==16.7.4 | polyglot |
| ==0.2.3 | hyperopt |
| ==0.21 | catboost |
| - | fastai |
| ==0.1.4 | kapre |
| - | keras-radam |
| >=4.4.0 | pytest |
| - | flake8 |
| - | isort |
| - | pytest-xdist |
| - | pytest-cov |
| - | coverage |
| <3,>=2 | typeguard |
| <0.3,>=0.2 | typedapi |
زبان مورد نیاز
| مقدار | نام |
|---|---|
| >=3.6 | Python |
نحوه نصب
نصب پکیج whl autodl-gpu-0.1.1:
pip install autodl-gpu-0.1.1.whl
نصب پکیج tar.gz autodl-gpu-0.1.1:
pip install autodl-gpu-0.1.1.tar.gz