DL架構之MXNet :深度學習架構之MXNet 的簡介、安裝、使用方法、應用案例之詳細攻略
目錄
MXNet 的簡介 1、優缺點 2、相關文章 3、相關連結 MXNet 的安裝 MXNet 的使用方法 1、個人使用總結 2、經典模型集合—MXNet Model Zoo 3、模型分類 MXNet 的應用案例![](https://img.laitimes.com/img/__Qf2AjLwojIjJCLyojI0JCLiYWan5CMwY2M3kjN5ImYjFzN3YTYyImN0M2NhR2M5MTMmJjYi9CX5d2bs92Yl1iclB3bsVmdlR2LcNWaw9CXt92Yu4GZjlGbh5yYjV3Lc9CX6MHc0RHaiojIsJye.gif)
A flexible and efficient library for deep learning.
MXNet 是亞馬遜(Amazon)選擇的深度學習庫,并且也許是最優秀的庫之一。它擁有類似于 Theano 和 TensorFlow 的資料流圖,為多 GPU 配置提供了良好的配置,有着類似于 Lasagne 和 Blocks 更進階别的模型建構塊,并且可以在你可以想象的任何硬體上運作(包括手機)。對 Python 的支援隻是其冰山一角—MXNet 同樣提供了對 R、Julia、C++、Scala、Matlab,和 Javascript 的接口。
MXNet 是一個旨在提高效率和靈活性的深度學習架構。像MXNet這樣的加速庫提供了強大的工具來幫助開發人員利用GPU和雲計算的全部功能。雖然這些工具通常适用于任何數學計算,但MXNet特别強調加速大規模深度神經網絡的開發和部署。特别是,我們提供以下功能:
- 裝置放置:使用MXNet,可以輕松指定每個資料結構的生存位置。
- 多GPU教育訓練:MXNet可以通過可用GPU的數量輕松擴充計算。
- 自動區分:MXNet自動執行曾經陷入神經網絡研究的衍生計算。
- 優化的預定義圖層:雖然您可以在MXNet中編寫自己的圖層,但預定義的圖層會針對速度進行優化,優于競争庫。
MXNet 官方自我評價:MXNet結合了高性能,幹淨的代碼,進階API通路和低級控制,是深度學習架構中獨一無二的選擇。
優點:
- 速度的标杆
- 靈活的程式設計模型:非常靈活。支援指令式和符号式程式設計模型以最大化效率和性能。
- 從雲端到用戶端可移植:可運作于多CPU、多GPU、叢集、伺服器、工作站甚至移動智能手機。
- 多語言支援:支援七種主流程式設計語言,包括C++、Python、R、Scala、Julia、Matlab和JavaScript。事實上,它是唯一支援所有 R 函數的構架。
- 本地分布式訓練:支援在多CPU/GPU裝置上的分布式訓練,使其可充分利用雲計算的規模優勢。
- 性能優化:使用一個優化的C++後端引擎并行I/O和計算,無論使用哪種語言都能達到最佳性能。
- 雲端友好,可直接與S3,HDFS和Azure相容
缺點:
- 最小的社群
- 比 Theano 學習更困難一點
MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
MXnet是一個多語言機器學習(ML)庫,用于簡化ML算法的開發,特别是對于深度神經網絡。它嵌入在宿主語言中,将聲明性符号表達式與指令式張量計算混合在一起。它提供自動微分來推導梯度。MXnet具有計算和記憶體效率高的特點,可以在各種異構系統上運作,從移動裝置到分布式GPU叢集。本文介紹了MXnet的API設計和系統實作,并解釋了如何統一處理符号表達式和張量操作的嵌入。我們的初步實驗表明,在使用多個GPU機器的大規模深度神經網絡應用中,有着很好的結果。
官網位址:
Apache MXNet | A flexible and efficient library for deep learning.GitHub位址01:
https://github.com/dmlc/mxnetGitHub位址02:
https://github.com/apache/incubator-mxnet/tree/master/exampleMXNet - Python API:
http://mxnet.incubator.apache.org/api/python/index.html#python-api-referencePyPi位址:
mxnet · PyPI1、第一次安裝
pip install mxnet
Collecting mxnet
Downloading https://files.pythonhosted.org/packages/d1/b6/38d9ab1b16c456224823e737f1bb95fe3ff056f3834fba01cd157d59b574/mxnet-1.4.0.post0-py2.py3-none-win_amd64.whl (21.9MB)
100% |████████████████████████████████| 21.9MB 34kB/s
Requirement already satisfied: requests<2.19.0,>=2.18.4 in f:\program files\python\python36\lib\site-packages (from mxnet) (2.18.4)
Collecting graphviz<0.9.0,>=0.8.1 (from mxnet)
Downloading https://files.pythonhosted.org/packages/53/39/4ab213673844e0c004bed8a0781a0721a3f6bb23eb8854ee75c236428892/graphviz-0.8.4-py2.py3-none-any.whl
Collecting numpy<1.15.0,>=1.8.2 (from mxnet)
Downloading https://files.pythonhosted.org/packages/dc/99/f824a73251589d9fcef2384f9dd21bd1601597fda92ced5882940586ec37/numpy-1.14.6-cp36-none-win_amd64.whl (13.4MB)
100% |████████████████████████████████| 13.4MB 30kB/s
Requirement already satisfied: certifi>=2017.4.17 in f:\program files\python\python36\lib\site-packages (from requests<2.19.0,>=2.18.4->mxnet) (2018.1.18)
Requirement already satisfied: chardet<3.1.0,>=3.0.2 in f:\program files\python\python36\lib\site-packages (from requests<2.19.0,>=2.18.4->mxnet) (3.0.4)
Requirement already satisfied: urllib3<1.23,>=1.21.1 in f:\program files\python\python36\lib\site-packages (from requests<2.19.0,>=2.18.4->mxnet) (1.22)
Requirement already satisfied: idna<2.7,>=2.5 in f:\program files\python\python36\lib\site-packages (from requests<2.19.0,>=2.18.4->mxnet) (2.6)
tensorflow-gpu 1.4.0 requires enum34>=1.1.6, which is not installed.
tensorflow 1.10.0 has requirement numpy<=1.14.5,>=1.13.3, but you'll have numpy 1.14.6 which is incompatible.
moviepy 0.2.3.2 has requirement decorator==4.0.11, but you'll have decorator 4.3.0 which is incompatible.
moviepy 0.2.3.2 has requirement tqdm==4.11.2, but you'll have tqdm 4.25.0 which is incompatible.
Installing collected packages: graphviz, numpy, mxnet
Found existing installation: numpy 1.15.0rc1+mkl
Uninstalling numpy-1.15.0rc1+mkl:
Could not install packages due to an EnvironmentError: [WinError 5] 拒絕通路。: 'f:\\program files\\python\\python36\\lib\\site-packages\\numpy\\core\\_multiarray_tests.cp36-win_amd64.pyd'
Consider using the `--user` option or check the permissions.
遇到問題:
成功解決Could not install packages due to an EnvironmentError: [WinError 5] 拒絕通路。: 'f:\\program files\\p2、第二次安裝
tensorflow-gpu 1.4.0 requires enum34>=1.1.6, which is not installed.
tensorflow 1.10.0 has requirement numpy<=1.14.5,>=1.13.3, but you'll have numpy 1.14.6 which is incompatible.
moviepy 0.2.3.2 has requirement decorator==4.0.11, but you'll have decorator 4.3.0 which is incompatible.
moviepy 0.2.3.2 has requirement tqdm==4.11.2, but you'll have tqdm 4.25.0 which is incompatible.
後期更新……
DL架構之MXNet :深度學習架構之MXNet 常見使用方法(個人使用)總結之詳細攻略
相關連結:
Alias | Network | # Parameters | Top-1 Accuracy | Top-5 Accuracy | Origin |
alexnet | AlexNet | 61,100,840 | 0.5492 | 0.7803 | Converted from pytorch vision |
densenet121 | DenseNet-121 | 8,062,504 | 0.7497 | 0.9225 | |
densenet161 | DenseNet-161 | 28,900,936 | 0.7770 | 0.9380 | |
densenet169 | DenseNet-169 | 14,307,880 | 0.7617 | 0.9317 | |
densenet201 | DenseNet-201 | 20,242,984 | 0.7732 | 0.9362 | |
inceptionv3 | Inception V3 299x299 | 23,869,000 | 0.7755 | 0.9364 | |
mobilenet0.25 | MobileNet 0.25 | 475,544 | 0.5185 | 0.7608 | Trained with script |
mobilenet0.5 | MobileNet 0.5 | 1,342,536 | 0.6307 | 0.8475 | |
mobilenet0.75 | MobileNet 0.75 | 2,601,976 | 0.6738 | 0.8782 | |
mobilenet1.0 | MobileNet 1.0 | 4,253,864 | 0.7105 | 0.9006 | |
mobilenetv2_1.0 | MobileNetV2 1.0 | 3,539,136 | 0.7192 | 0.9056 | |
mobilenetv2_0.75 | MobileNetV2 0.75 | 2,653,864 | 0.6961 | 0.8895 | |
mobilenetv2_0.5 | MobileNetV2 0.5 | 1,983,104 | 0.6449 | 0.8547 | |
mobilenetv2_0.25 | MobileNetV2 0.25 | 1,526,856 | 0.5074 | 0.7456 | |
resnet18_v1 | ResNet-18 V1 | 11,699,112 | 0.7093 | 0.8992 | |
resnet34_v1 | ResNet-34 V1 | 21,814,696 | 0.7437 | 0.9187 | |
resnet50_v1 | ResNet-50 V1 | 25,629,032 | 0.7647 | 0.9313 | |
resnet101_v1 | ResNet-101 V1 | 44,695,144 | 0.7834 | 0.9401 | |
resnet152_v1 | ResNet-152 V1 | 60,404,072 | 0.7900 | 0.9438 | |
resnet18_v2 | ResNet-18 V2 | 11,695,796 | 0.7100 | ||
resnet34_v2 | ResNet-34 V2 | 21,811,380 | 0.7440 | 0.9208 | |
resnet50_v2 | ResNet-50 V2 | 25,595,060 | 0.7711 | 0.9343 | |
resnet101_v2 | ResNet-101 V2 | 44,639,412 | 0.7853 | 0.9417 | |
resnet152_v2 | ResNet-152 V2 | 60,329,140 | 0.7921 | 0.9431 | |
squeezenet1.0 | SqueezeNet 1.0 | 1,248,424 | 0.5611 | 0.7909 | |
squeezenet1.1 | SqueezeNet 1.1 | 1,235,496 | 0.5496 | 0.7817 | |
vgg11 | VGG-11 | 132,863,336 | 0.6662 | 0.8734 | |
vgg13 | VGG-13 | 133,047,848 | 0.6774 | 0.8811 | |
vgg16 | VGG-16 | 138,357,544 | 0.7323 | 0.9132 | |
vgg19 | VGG-19 | 143,667,240 | 0.7411 | 0.9135 | |
vgg11_bn | VGG-11 with batch normalization | 132,874,344 | 0.6859 | 0.8872 | |
vgg13_bn | VGG-13 with batch normalization | 133,059,624 | 0.6884 | 0.8882 | |
vgg16_bn | VGG-16 with batch normalization | 138,374,440 | 0.7310 | 0.9176 | |
vgg19_bn | VGG-19 with batch normalization | 143,689,256 | 0.7433 | 0.9185 |
| Returns a pre-defined model by name |
ResNet
| ResNet-18 V1 model from “Deep Residual Learning for Image Recognition” paper. |
| ResNet-34 V1 model from |
| ResNet-50 V1 model from |
| ResNet-101 V1 model from |
| ResNet-152 V1 model from |
| ResNet-18 V2 model from “Identity Mappings in Deep Residual Networks” |
| ResNet-34 V2 model from |
| ResNet-50 V2 model from |
| ResNet-101 V2 model from |
| ResNet-152 V2 model from |
| ResNet V1 model from |
| ResNet V2 model from |
| BasicBlock V1 from |
| BasicBlock V2 from |
| Bottleneck V1 from |
| Bottleneck V2 from |
|
VGG
| VGG-11 model from the “Very Deep Convolutional Networks for Large-Scale Image Recognition” |
| VGG-13 model from the |
| VGG-16 model from the |
| VGG-19 model from the |
| VGG-11 model with batch normalization from the |
| VGG-13 model with batch normalization from the |
| VGG-16 model with batch normalization from the |
| VGG-19 model with batch normalization from the |
Alexnet
| AlexNet model from the “One weird trick...” |
DenseNet
| Densenet-BC 121-layer model from the “Densely Connected Convolutional Networks” |
| Densenet-BC 161-layer model from the |
| Densenet-BC 169-layer model from the |
| Densenet-BC 201-layer model from the |
SqueezeNet
| SqueezeNet 1.0 model from the “SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size” |
| SqueezeNet 1.1 model from the official SqueezeNet repo . |
Inception
| Inception v3 model from “Rethinking the Inception Architecture for Computer Vision” |
MobileNet
| MobileNet model from the “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications” paper, with width multiplier 1.0. |
| paper, with width multiplier 0.75. |
| paper, with width multiplier 0.5. |
| paper, with width multiplier 0.25. |
| MobileNetV2 model from the “Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation” |
| |
| |
|
後期繼續更新……