Pytorch模型训练到哪里找预训练模型？

使用预训练模型，我们有两种方式

1. 加载torchvison中的模型，然后定义 pretrained=True
2. 采用pretrainedmodels模块

---

torchvision方式

from torchvision.models.resnet import resnet18

net = resnet18(pretrained=True)

---

采用pretrainedmodels方式

安装pretrainedmodels模块

pip install pretrainedmodels

安装好后，我们可以查看可用的预训练模型

import pretrainedmodels

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']
"""

加载预训练模型

import pretrainedmodels

pretrainedmodels.inceptionv3(num_classes=1000, pretrained='imagenet')

---

END