Pretrained models for Pytorch (Work in progress)

最新推荐文章于 2024-06-15 19:38:47 发布
最新推荐文章于 2024-06-15 19:38:47 发布
阅读量616 收藏 1
点赞数
文章标签： 人工智能 git python
原文链接：http://www.cnblogs.com/houjun/p/9822096.html
版权

The goal of this repo is:

  • to help to reproduce research papers results (transfer learning setups for instance),
  • to access pretrained ConvNets with a unique interface/API inspired by torchvision.

News:

  • 04/06/2018: PolyNet and PNASNet-5-Large thanks to Alex Parinov
  • 16/04/2018: SE-ResNet* and SE-ResNeXt* thanks to Alex Parinov
  • 09/04/2018: SENet154 thanks to Alex Parinov
  • 22/03/2018: CaffeResNet101 (good for localization with FasterRCNN)
  • 21/03/2018: NASNet Mobile thanks to Veronika Yurchuk and Anastasiia
  • 25/01/2018: DualPathNetworks thanks to Ross Wightman, Xception thanks to T Standley, improved TransformImage API
  • 13/01/2018: pip install pretrainedmodels, pretrainedmodels.model_names, pretrainedmodels.pretrained_settings
  • 12/01/2018: python setup.py install
  • 08/12/2017: update data url (/! git pull is needed)
  • 30/11/2017: improve API (model.features(input), model.logits(features), model.forward(input), model.last_linear)
  • 16/11/2017: nasnet-a-large pretrained model ported by T. Durand and R. Cadene
  • 22/07/2017: torchvision pretrained models
  • 22/07/2017: momentum in inceptionv4 and inceptionresnetv2 to 0.1
  • 17/07/2017: model.input_range attribut
  • 17/07/2017: BNInception pretrained on Imagenet

Summary

Installation

  1. python3 with anaconda
  2. pytorch with/out CUDA

Install from pip

  1. pip install pretrainedmodels

Install from repo

  1. git clone https://github.com/Cadene/pretrained-models.pytorch.git
  2. cd pretrained-models.pytorch
  3. python setup.py install

Quick examples

  • To import pretrainedmodels:
import pretrainedmodels
  • To print the available pretrained models:
print(pretrainedmodels.model_names)
> ['fbresnet152', 'bninception', 'resnext101_32x4d', 'resnext101_64x4d', 'inceptionv4', 'inceptionresnetv2', 'alexnet', 'densenet121', 'densenet169', 'densenet201', 'densenet161', 'resnet18', 'resnet34', 'resnet50', 'resnet101', 'resnet152', 'inceptionv3', 'squeezenet1_0', 'squeezenet1_1', 'vgg11', 'vgg11_bn', 'vgg13', 'vgg13_bn', 'vgg16', 'vgg16_bn', 'vgg19_bn', 'vgg19', 'nasnetalarge', 'nasnetamobile', 'cafferesnet101', 'senet154',  'se_resnet50', 'se_resnet101', 'se_resnet152', 'se_resnext50_32x4d', 'se_resnext101_32x4d', 'cafferesnet101', 'polynet', 'pnasnet5large']
  • To print the available pretrained settings for a chosen model:
print(pretrainedmodels.pretrained_settings['nasnetalarge'])
> {'imagenet': {'url': 'http://data.lip6.fr/cadene/pretrainedmodels/nasnetalarge-a1897284.pth', 'input_space': 'RGB', 'input_size': [3, 331, 331], 'input_range': [0, 1], 'mean': [0.5, 0.5, 0.5], 'std': [0.5, 0.5, 0.5], 'num_classes': 1000}, 'imagenet+background': {'url': 'http://data.lip6.fr/cadene/pretrainedmodels/nasnetalarge-a1897284.pth', 'input_space': 'RGB', 'input_size': [3, 331, 331], 'input_range': [0, 1], 'mean': [0.5, 0.5, 0.5], 'std': [0.5, 0.5, 0.5], 'num_classes': 1001}}
  • To load a pretrained models from imagenet:
model_name = 'nasnetalarge' # could be fbresnet152 or inceptionresnetv2
model = pretrainedmodels.__dict__[model_name](num_classes=1000, pretrained='imagenet')
model.eval()

Note: By default, models will be downloaded to your $HOME/.torch folder. You can modify this behavior using the $TORCH_MODEL_ZOO variable as follow: export TORCH_MODEL_ZOO="/local/pretrainedmodels

  • To load an image and do a complete forward pass:
import torch
import pretrainedmodels.utils as utils

load_img = utils.LoadImage()

# transformations depending on the model
# rescale, center crop, normalize, and others (ex: ToBGR, ToRange255)
tf_img = utils.TransformImage(model) 

path_img = 'data/cat.jpg'

input_img = load_img(path_img)
input_tensor = tf_img(input_img)         # 3x400x225 -> 3x299x299 size may differ
input_tensor = input_tensor.unsqueeze(0) # 3x299x299 -> 1x3x299x299
input = torch.autograd.Variable(input_tensor,
    requires_grad=False)

output_logits = model(input) # 1x1000
  • To extract features (beware this API is not available for all networks):
output_features = model.features(input) # 1x14x14x2048 size may differ
output_logits = model.logits(output_features) # 1x1000

Few use cases

Compute imagenet logits

$ python examples/imagenet_logits.py -h
> nasnetalarge, resnet152, inceptionresnetv2, inceptionv4, ...
$ python examples/imagenet_logits.py -a nasnetalarge --path_img data/cat.png
> 'nasnetalarge': data/cat.png' is a 'tiger cat'

Compute imagenet evaluation metrics

$ python examples/imagenet_eval.py /local/common-data/imagenet_2012/images -a nasnetalarge -b 20 -e
> * Acc@1 92.693, Acc@5 96.13

Evaluation on imagenet

Accuracy on validation set (single model)

Results were obtained using (center cropped) images of the same size than during the training process.

ModelVersionAcc@1Acc@5
PNASNet-5-LargeTensorflow82.85896.182
PNASNet-5-LargeOur porting82.73695.992
NASNet-A-LargeTensorflow82.69396.163
NASNet-A-LargeOur porting82.56696.086
SENet154Caffe81.3295.53
SENet154Our porting81.30495.498
PolyNetCaffe81.2995.75
PolyNetOur porting81.00295.624
InceptionResNetV2Tensorflow80.495.3
InceptionV4Tensorflow80.295.3
SE-ResNeXt101_32x4dOur porting80.23695.028
SE-ResNeXt101_32x4dCaffe80.1995.04
InceptionResNetV2Our porting80.17095.234
InceptionV4Our porting80.06294.926
DualPathNet107_5kOur porting79.74694.684
ResNeXt101_64x4dTorch779.694.7
DualPathNet131Our porting79.43294.574
DualPathNet92_5kOur porting79.40094.620
DualPathNet98Our porting79.22494.488
SE-ResNeXt50_32x4dOur porting79.07694.434
SE-ResNeXt50_32x4dCaffe79.0394.46
XceptionKeras79.00094.500
ResNeXt101_64x4dOur porting78.95694.252
XceptionOur porting78.88894.292
ResNeXt101_32x4dTorch778.894.4
SE-ResNet152Caffe78.6694.46
SE-ResNet152Our porting78.65894.374
ResNet152Pytorch78.42894.110
SE-ResNet101Our porting78.39694.258
SE-ResNet101Caffe78.2594.28
ResNeXt101_32x4dOur porting78.18893.886
FBResNet152Torch777.8493.84
SE-ResNet50Caffe77.6393.64
SE-ResNet50Our porting77.63693.752
DenseNet161Pytorch77.56093.798
ResNet101Pytorch77.43893.672
FBResNet152Our porting77.38693.594
InceptionV3Pytorch77.29493.454
DenseNet201Pytorch77.15293.548
DualPathNet68b_5kOur porting77.03493.590
CaffeResnet101Caffe76.40092.900
CaffeResnet101Our porting76.20092.766
DenseNet169Pytorch76.02692.992
ResNet50Pytorch76.00292.980
DualPathNet68Our porting75.86892.774
DenseNet121Pytorch74.64692.136
VGG19_BNPytorch74.26692.066
NASNet-A-MobileTensorflow74.091.6
NASNet-A-MobileOur porting74.08091.740
ResNet34Pytorch73.55491.456
BNInceptionOur porting73.52291.560
VGG16_BNPytorch73.51891.608
VGG19Pytorch72.08090.822
VGG16Pytorch71.63690.354
VGG13_BNPytorch71.50890.494
VGG11_BNPytorch70.45289.818
ResNet18Pytorch70.14289.274
VGG13Pytorch69.66289.264
VGG11Pytorch68.97088.746
SqueezeNet1_1Pytorch58.25080.800
SqueezeNet1_0Pytorch58.10880.428
AlexnetPytorch56.43279.194

Notes:

  • the Pytorch version of ResNet152 is not a porting of the Torch7 but has been retrained by facebook.
  • For the PolyNet evaluation each image was resized to 378x378 without preserving the aspect ratio and then the central 331×331 patch from the resulting image was used.

Beware, the accuracy reported here is not always representative of the transferable capacity of the network on other tasks and datasets. You must try them all! :P

Reproducing results

Please see Compute imagenet validation metrics

Documentation

Available models

NASNet*

Source: TensorFlow Slim repo

  • nasnetalarge(num_classes=1000, pretrained='imagenet')
  • nasnetalarge(num_classes=1001, pretrained='imagenet+background')
  • nasnetamobile(num_classes=1000, pretrained='imagenet')
FaceBook ResNet*

Source: Torch7 repo of FaceBook

There are a bit different from the ResNet* of torchvision. ResNet152 is currently the only one available.

  • fbresnet152(num_classes=1000, pretrained='imagenet')
Caffe ResNet*

Source: Caffe repo of KaimingHe

  • cafferesnet101(num_classes=1000, pretrained='imagenet')
Inception*

Source: TensorFlow Slim repo and Pytorch/Vision repo for inceptionv3

  • inceptionresnetv2(num_classes=1000, pretrained='imagenet')
  • inceptionresnetv2(num_classes=1001, pretrained='imagenet+background')
  • inceptionv4(num_classes=1000, pretrained='imagenet')
  • inceptionv4(num_classes=1001, pretrained='imagenet+background')
  • inceptionv3(num_classes=1000, pretrained='imagenet')
BNInception

Source: Trained with Caffe by Xiong Yuanjun

  • bninception(num_classes=1000, pretrained='imagenet')
ResNeXt*

Source: ResNeXt repo of FaceBook

  • resnext101_32x4d(num_classes=1000, pretrained='imagenet')
  • resnext101_62x4d(num_classes=1000, pretrained='imagenet')
DualPathNetworks

Source: MXNET repo of Chen Yunpeng

The porting has been made possible by Ross Wightman in his PyTorch repo.

As you can see here DualPathNetworks allows you to try different scales. The default one in this repo is 0.875 meaning that the original input size is 256 before croping to 224.

  • dpn68(num_classes=1000, pretrained='imagenet')
  • dpn98(num_classes=1000, pretrained='imagenet')
  • dpn131(num_classes=1000, pretrained='imagenet')
  • dpn68b(num_classes=1000, pretrained='imagenet+5k')
  • dpn92(num_classes=1000, pretrained='imagenet+5k')
  • dpn107(num_classes=1000, pretrained='imagenet+5k')

'imagenet+5k' means that the network has been pretrained on imagenet5k before being finetuned on imagenet1k.

Xception

Source: Keras repo

The porting has been made possible by T Standley.

  • xception(num_classes=1000, pretrained='imagenet')
SENet*

Source: Caffe repo of Jie Hu

  • senet154(num_classes=1000, pretrained='imagenet')
  • se_resnet50(num_classes=1000, pretrained='imagenet')
  • se_resnet101(num_classes=1000, pretrained='imagenet')
  • se_resnet152(num_classes=1000, pretrained='imagenet')
  • se_resnext50_32x4d(num_classes=1000, pretrained='imagenet')
  • se_resnext101_32x4d(num_classes=1000, pretrained='imagenet')
PNASNet*

Source: TensorFlow Slim repo

  • pnasnet5large(num_classes=1000, pretrained='imagenet')
  • pnasnet5large(num_classes=1001, pretrained='imagenet+background')
PolyNet

Source: Caffe repo of the CUHK Multimedia Lab

  • polynet(num_classes=1000, pretrained='imagenet')
TorchVision

Source: Pytorch/Vision repo

(inceptionv3 included in Inception*)

  • resnet18(num_classes=1000, pretrained='imagenet')
  • resnet34(num_classes=1000, pretrained='imagenet')
  • resnet50(num_classes=1000, pretrained='imagenet')
  • resnet101(num_classes=1000, pretrained='imagenet')
  • resnet152(num_classes=1000, pretrained='imagenet')
  • densenet121(num_classes=1000, pretrained='imagenet')
  • densenet161(num_classes=1000, pretrained='imagenet')
  • densenet169(num_classes=1000, pretrained='imagenet')
  • densenet201(num_classes=1000, pretrained='imagenet')
  • squeezenet1_0(num_classes=1000, pretrained='imagenet')
  • squeezenet1_1(num_classes=1000, pretrained='imagenet')
  • alexnet(num_classes=1000, pretrained='imagenet')
  • vgg11(num_classes=1000, pretrained='imagenet')
  • vgg13(num_classes=1000, pretrained='imagenet')
  • vgg16(num_classes=1000, pretrained='imagenet')
  • vgg19(num_classes=1000, pretrained='imagenet')
  • vgg11_bn(num_classes=1000, pretrained='imagenet')
  • vgg13_bn(num_classes=1000, pretrained='imagenet')
  • vgg16_bn(num_classes=1000, pretrained='imagenet')
  • vgg19_bn(num_classes=1000, pretrained='imagenet')

Model API

Once a pretrained model has been loaded, you can use it that way.

Important note: All image must be loaded using PIL which scales the pixel values between 0 and 1.

model.input_size

Attribut of type list composed of 3 numbers:

  • number of color channels,
  • height of the input image,
  • width of the input image.

Example:

  • [3, 299, 299] for inception* networks,
  • [3, 224, 224] for resnet* networks.
model.input_space

Attribut of type str representating the color space of the image. Can be RGB or BGR.

model.input_range

Attribut of type list composed of 2 numbers:

  • min pixel value,
  • max pixel value.

Example:

  • [0, 1] for resnet* and inception* networks,
  • [0, 255] for bninception network.
model.mean

Attribut of type list composed of 3 numbers which are used to normalize the input image (substract "color-channel-wise").

Example:

  • [0.5, 0.5, 0.5] for inception* networks,
  • [0.485, 0.456, 0.406] for resnet* networks.
model.std

Attribut of type list composed of 3 numbers which are used to normalize the input image (divide "color-channel-wise").

Example:

  • [0.5, 0.5, 0.5] for inception* networks,
  • [0.229, 0.224, 0.225] for resnet* networks.
model.features

/! work in progress (may not be available)

Method which is used to extract the features from the image.

Example when the model is loaded using fbresnet152:

print(input_224.size())            # (1,3,224,224)
output = model.features(input_224) 
print(output.size())               # (1,2048,1,1)

# print(input_448.size())          # (1,3,448,448)
output = model.features(input_448)
# print(output.size())             # (1,2048,7,7)
model.logits

/! work in progress (may not be available)

Method which is used to classify the features from the image.

Example when the model is loaded using fbresnet152:

output = model.features(input_224) 
print(output.size())               # (1,2048, 1, 1)
output = model.logits(output)
print(output.size())               # (1,1000)
model.forward

Method used to call model.features and model.logits. It can be overwritten as desired.

Note: A good practice is to use model.__call__ as your function of choice to forward an input to your model. See the example bellow.

# Without model.__call__
output = model.forward(input_224)
print(output.size())      # (1,1000)

# With model.__call__
output = model(input_224)
print(output.size())      # (1,1000)
model.last_linear

Attribut of type nn.Linear. This module is the last one to be called during the forward pass.

  • Can be replaced by an adapted nn.Linear for fine tuning.
  • Can be replaced by pretrained.utils.Identity for features extraction.

Example when the model is loaded using fbresnet152:

print(input_224.size())            # (1,3,224,224)
output = model.features(input_224) 
print(output.size())               # (1,2048,1,1)
output = model.logits(output)
print(output.size())               # (1,1000)

# fine tuning
dim_feats = model.last_linear.in_features # =2048
nb_classes = 4
model.last_linear = nn.Linear(dim_feats, nb_classes)
output = model(input_224)
print(output.size())               # (1,4)

# features extraction
model.last_linear = pretrained.utils.Identity()
output = model(input_224)
print(output.size())               # (1,2048)

Reproducing

Hand porting of ResNet152

th pretrainedmodels/fbresnet/resnet152_dump.lua
python pretrainedmodels/fbresnet/resnet152_load.py

Automatic porting of ResNeXt

https://github.com/clcarwin/convert_torch_to_pytorch

Hand porting of NASNet, InceptionV4 and InceptionResNetV2

https://github.com/Cadene/tensorflow-model-zoo.torch

Acknowledgement

Thanks to the deep learning community and especially to the contributers of the pytorch ecosystem.

转载于:https://www.cnblogs.com/houjun/p/9822096.html

MA201506
关注
  • 0
    点赞
  • 踩
  • 1
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
pretrained_models_v1.5.zip
12-03
pointpillars网络深度学习模型，对应https://github.com/traveller59/second.pytorch下的google drive中的pretrained model。
pretrainedmodels 包中的预训练模型
lichaoqi1的博客
03-22 901
预训练模型包使用： import pretrainedmodels print(pretrainedmodels.model_names) #打印 print(pretrainedmodels.pretrained_settings['se_resnet152'])
Pre-trained models fo HumanPose Estiamtion
snailme的博客
11-22 299
Multi-Person Real-time Person Pose Estimation The authors of the paper have shared two models – one is trained on the Multi-Person Dataset ( MPII ) and the other is trained on the COCO dataset. The CO...
深度学习-图像分类经典模型（pretrained model）
gisupc的专栏
04-25 7220
一、来自TensorFlow官网的下载链接 http://download.tensorflow.org/models/inception_resnet_v2_2016_08_30.tar.gz http://download.tensorflow.org/models/vgg_19_2016_08_28.tar.gz Inception V1. FROM: http://downloa...
迁移学习算法中预训练模型（Pre-trained Models）
牛肉胡辣汤
08-31 1364
通过在目标任务的数据集上进行微调（Fine-tuning），即在预训练模型的基础上继续进行训练，可以使模型适应目标任务的特定特征和要求。总之，预训练模型是迁移学习中一种重要的方法，通过利用在大规模数据集上预训练得到的模型，可以为目标任务提供更好的初始模型，并提高模型的性能和收敛速度。以上代码中，使用VGG16预训练模型作为基础模型，冻结了所有预训练模型的参数。以上代码中，使用ResNet预训练模型作为基础模型，替换了最后一层分类器，然后冻结了预训练模型的所有参数，只训练了新添加的分类器的参数。
pretrained-models.pytorch:pytorch预训练的ConvNets
03-31
Pytorch的预训练模型（正在进行中） 此仓库的目标是： 以帮助复制研究论文的结果（例如，转移学习设置）， ... 13/01/2018： pip install pretrainedmodels ， pretrainedmodels.model_names ， pretrainedmodels.pre
segmentation_models.pytorch:具有预训练骨干的细分模型。 火炬
04-28
具有用于图像的神经网络的Python库基于分割。 该库的主要功能是： 高级API（只需两行即可创建神经网络） ... import segmentation_models_pytorch as smp model = smp . Unet ( encoder_name = "resnet34" , # choos
PyTorch-Pretrained-ViT:PyTorch中的视觉变压器（ViT）
05-07
使用pip install pytorch_pretrained_vit安装，并使用以下命令加载经过预训练的ViT： from pytorch_pretrained_vit import ViT model = ViT ( 'B_16_imagenet1k' , pretrained = True ) 或找到Google Colab示例。 ...
Python库 | segmentation_models_pytorch-0.1.2-py3-none-any.whl
04-26
资源分类：Python库 所属语言：Python 使用前提：需要解压 资源全名：segmentation_models_pytorch-0.1.2-py3-none-any.whl 资源来源：官方 安装方法：https://lanzao.blog.csdn.net/article/details/101784059
使用segmentation_models.pytorch图像分割框架实现对人物的抠图.zip
04-09
今天这篇文章向大家展示如何使用segmentation_models.pytorch实现语义分割算法。 通过这篇文章，你可以学到： 1、如何使用segmentation_models.pytorch图像分割框架实现语义分割算法？ 2、如何使用和加载语义分割...
pre-trained models _20170512-110547
04-19
20170512-110547（MS-Celeb-1M数据集训练的模型文件，微软人脸识别数据库，名人榜选择前100万名人，搜索引擎采集每个名人100张人脸图片。预训练模型准确率0.993+-0.004）
pytorch pretrained model
swfa1的专栏
07-24 3026
pytorch pretrained model two methods method 1 比较大小 self._model = models.__dict__[args.arch](pretrained = False, num_classes = args.classes, ...
PyTorch自学系列之 pretrained model usage
ChaoMartin的博客
11-14 848
首先为了尊重他人贡献，本博客参考链接为：https://blog.csdn.net/VictoriaW/article/details/72821329（感谢知识传递者） 楼主使用预训练模型的初衷是：目标识别检测框架在不同的计算机视觉应用中性能的提升很大一部分原因是由于骨干网络的西能提升，为了使用更好的Backbone获取feature map,所以有必要学习如何使用更好的预训练模型。 套路...
论文阅读|Pre-trained Models for Natural language Processing: A Survey
Kolunm的博客
10-22 2213
这篇综述是复旦大学的邱锡鹏教授对近两年的预训练语言模型（PTM）做的综述，文章比较新，边读边译，写点自己的理解。 原文链接：Pre-trained Models for Natural language Processing: A Survey Pre-trained Models for Natural language Processing: A Survey 摘要：最近，预训练模型（P...
Pytorch预训练模型pre-trained Models以及部分修改
最新发布
m0_68850524的博客
06-15 156
用torchvision.models.XXX加载模型时用参数pretrained=True好像可以运行，但是会报红，用weights没问题，下面举了两个例子。返回的是features和avgpool两层，也就是.children返回的是模型的所有顶层模块。网上找到的都是几年前的了，更新一下最近的用法和踩的坑。则是直接用 顶层模块[ ]才能直接取出。参数修改没有研究过，后续需要再来补坑。容器中的前 20 层。
【Python】科研代码学习：三 PreTrainedModel, PretrainedConfig, PreTrainedTokenizer
溢流眼泪的博客
03-08 1523
HF 官网API本文主要从官网API与源代码中学习调用HF的关键模组。
python脚本中出现问题ImportError: No module named 'pretrainedmodels'
panda_33的博客
04-10 8083
#问题 #解决方法 在Anaconda的命令行界面采用如下方式安装： pip install pretrainedmodels
segmentation-models-pytorch版本
11-29
segmentation-models-pytorch是一个用于图像分割任务的库，它提供了一系列经过预训练的深度学习模型和一些用于训练、评估和推理的工具函数。 该库建立在PyTorch框架上，使得用户可以轻松地使用各种强大的图像分割...
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值