TorchVision_Models

liudongdong1 收录于 Categories Demo

2020-10-16 约 221 字预计阅读 1 分钟 - 次阅读

https://lddpicture.oss-cn-beijing.aliyuncs.com/picture/image-20201129141709288.png

Torchvision.Models contain different models like: image classification, pixelwise semantic segmentation, object detection, instance segmentation, person keypoint detection and video classification.

1. Classification Models

AlexNet VGG ResNet SqueezeNet DenseNet Inception v3GoogLeNet ShuffleNet v2MobileNet v2ResNeXt Wide ResNet MNASNet

1.1. Random weights

import torchvision.models as models
resnet18 = models.resnet18()
alexnet = models.alexnet()
vgg16 = models.vgg16()
squeezenet = models.squeezenet1_0()
densenet = models.densenet161()
inception = models.inception_v3()
googlenet = models.googlenet()
shufflenet = models.shufflenet_v2_x1_0()
mobilenet = models.mobilenet_v2()
resnext50_32x4d = models.resnext50_32x4d()
wide_resnet50_2 = models.wide_resnet50_2()
mnasnet = models.mnasnet1_0()

1.2. Using pretrained weights

import torchvision.models as models
resnet18 = models.resnet18(pretrained=True)
alexnet = models.alexnet(pretrained=True)
squeezenet = models.squeezenet1_0(pretrained=True)
vgg16 = models.vgg16(pretrained=True)
densenet = models.densenet161(pretrained=True)
inception = models.inception_v3(pretrained=True)
googlenet = models.googlenet(pretrained=True)
shufflenet = models.shufflenet_v2_x1_0(pretrained=True)
mobilenet = models.mobilenet_v2(pretrained=True)
resnext50_32x4d = models.resnext50_32x4d(pretrained=True)
wide_resnet50_2 = models.wide_resnet50_2(pretrained=True)
mnasnet = models.mnasnet1_0(pretrained=True)

2. Semantic Segmentation

3. Object Detection, Instance Segmentation, Person Keypoint Detection

4. Video Classification

ResNet 3D 18 ; ResNet MC 18; ResNet (2+1)D

5. 后序Todo

积累学习使用使用torch提供的模型进行具体的实用教程；
如果学习一个，理解完整的工作过程，训练效果以及可能迁移使用的场景；