最新超简单解读torchvision
torchvision
https://pytorch.org/docs/stable/torchvision/index.html#module-torchvision
The torchvision package consists of popular datasets(数据集), model architectures(模型结构), and common image transformations(通用图像转换) for computer vision.
torchvision.get_image_backend
():Gets the name of the package used to load images
torchvision.set_image_backend
(backend): Specifies the package used to load images.
torchvision.set_video_backend
(backend): Specifies the package used to decode videos.
- torchvision.datasets(目前共24个数据集):
MNIST;Fashion-MNIST;KMNIST;EMNIST;QMNIST;FakeData;COCO;LSUN;ImageFolder;DatasetFolder;ImageNet;CIFAR;STL10;SVHN;PhotoTour;SBU;Flickr;VOC;Cityscapes;SBD;USPS;Kinetics-400;HMDB51;UCF101.
- torchvision.io(目前只支持video):
Video
torchvision.io.read_video
(filename, start_pts=0, end_pts=None, pts_unit='pts')
Reads a video from a file, returning both the video frames as well as the audio frames.
- torchvision.models(目前只支持Classification, Semantic Segmentation, Object Detection, Instance Segmentation and Person Keypoint Detection和Video classification三类模型):
The models subpackage contains definitions for the following model architectures for image classification:
Inception v3
ShuffleNet v2
MobileNet v2
You can construct a model with random weights by calling its constructor:
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()
pre-trained models, using the PyTorch torch.utils.model_zoo. These can be constructed by passing pretrained=True:
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)
Instancing a pre-trained model will download its weights to a cache directory. This directory can be set using the TORCH_MODEL_ZOO environment variable. See torch.utils.model_zoo.load_url() for details.
Some models use modules which have different training and evaluation behavior, such as batch normalization. To switch between these modes, use model.train() or model.eval() as appropriate. See train() or eval() for details.
All pre-trained models expect input images normalized in the same way, i.e. mini-batches of 3-channel RGB images of shape (3 x H x W), where H and W are expected to be at least 224. The images have to be loaded in to a range of [0, 1] and then normalized using mean = [0.485, 0.456, 0.406] and std = [0.229, 0.224, 0.225]. You can use the following transform to normalize:
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
The models subpackage contains definitions for the following model architectures for semantic segmentation:
As with image classification models, all pre-trained models expect input images normalized in the same way. The images have to be loaded in to a range of [0,
1] and then normalized using mean
=
[0.485,
0.456,
0.406] and std
=
[0.229,
0.224,
0.225]. They have been trained on images resized such that their minimum size is 520.
The pre-trained models have been trained on a subset of COCO train2017, on the 20 categories that are present in the Pascal VOC dataset. You can see more information on how the subset has been selected in references/segmentation/coco_utils.py. The classes that the pre-trained model outputs are the following, in order:
['__background__', 'aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus',
'car', 'cat', 'chair', 'cow', 'diningtable', 'dog', 'horse', 'motorbike',
'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor']
Object Detection, Instance Segmentation and Person Keypoint Detection:
The models subpackage contains definitions for the following model architectures for detection:
The pre-trained models for detection, instance segmentation and keypoint detection are initialized with the classification models in torchvision.
The models expect a list of Tensor[C, H, W], in the range 0-1. The models internally resize the images so that they have a minimum size of 800. This option can be changed by passing the option min_size to the constructor of the models.
For object detection and instance segmentation, the pre-trained models return the predictions of the following classes:
COCO_INSTANCE_CATEGORY_NAMES = [
'__background__', 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus',
'train', 'truck', 'boat', 'traffic light', 'fire hydrant', 'N/A', 'stop sign',
'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
'elephant', 'bear', 'zebra', 'giraffe', 'N/A', 'backpack', 'umbrella', 'N/A', 'N/A',
'handbag', 'tie', 'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball',
'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 'tennis racket',
'bottle', 'N/A', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl',
'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza',
'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed', 'N/A', 'dining table',
'N/A', 'N/A', 'toilet', 'N/A', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'N/A', 'book',
'clock', 'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush'
]
For person keypoint detection, the pre-trained model return the keypoints in the following order:
COCO_PERSON_KEYPOINT_NAMES = [
'nose',
'left_eye',
'right_eye',
'left_ear',
'right_ear',
'left_shoulder',
'right_shoulder',
'left_elbow',
'right_elbow',
'left_wrist',
'right_wrist',
'left_hip',
'right_hip',
'left_knee',
'right_knee',
'left_ankle',
'right_ankle'
]
We provide models for action recognition pre-trained on Kinetics-400. They have all been trained with the scripts provided in references/video_classification.
All pre-trained models expect input images normalized in the same way, i.e. mini-batches of 3-channel RGB videos of shape (3 x T x H x W), where H and W are expected to be 112, and T is a number of video frames in a clip. The images have to be loaded in to a range of [0, 1] and then normalized using mean = [0.43216, 0.394666, 0.37645] and std = [0.22803, 0.22145, 0.216989].
NOTE
The normalization parameters are different from the image classification ones, and correspond to the mean and std from Kinetics-400.
NOTE
For now, normalization code can be found in references/video_classification/transforms.py, see the Normalizefunction there. Note that it differs from standard normalization for images because it assumes the video is 4d.
Kinetics 1-crop accuracies for clip length 16 (16x112x112)
Network |
Clip acc@1 |
Clip acc@5 |
ResNet 3D 18 |
52.75 |
75.45 |
ResNet MC 18 |
53.90 |
76.29 |
ResNet (2+1)D |
57.50 |
78.81 |
- torchvision.ops(操作符):
torchvision.ops implements operators that are specific for Computer Vision.
支持:
torchvision.ops.nms
(boxes, scores, iou_threshold):Performs non-maximum suppression (NMS) on the boxes according to their intersection-over-union (IoU).
torchvision.ops.roi_align
(input, boxes, output_size, spatial_scale=1.0, sampling_ratio=-1): Performs Region of Interest (RoI) Align operator described in Mask R-CNN
torchvision.ops.roi_pool
(input, boxes, output_size, spatial_scale=1.0): Performs Region of Interest (RoI) Pool operator described in Fast R-CNN
- torchvision.transforms(转换操作)
torchvision.utils.make_grid
(tensor, nrow=8, padding=2, normalize=False, range=None, scale_each=False, pad_value=0), Make a grid of images.
torchvision.utils.save_image
(tensor, fp, nrow=8, padding=2, normalize=False, range=None, scale_each=False, pad_value=0, format=None), Save a given Tensor into an image file.
最新超简单解读torchvision的更多相关文章
- ssh框架整合---- spring 4.0 + struts 2.3.16 + maven ss整合超简单实例
一 . 需求 学了这么久的ssh,一直都是别人整合好的框架去写代码,自己实际动手时才发现框架配置真是很坑爹,一不小心就踏错,真是纸上得来终觉浅! 本文将记录整合struts + spring的过程 , ...
- 程序员,一起玩转GitHub版本控制,超简单入门教程 干货2
本GitHub教程旨在能够帮助大家快速入门学习使用GitHub,进行版本控制.帮助大家摆脱命令行工具,简单快速的使用GitHub. 做全栈攻城狮-写代码也要读书,爱全栈,更爱生活. 更多原创教程请关注 ...
- DCGAN 论文简单解读
DCGAN的全称是Deep Convolution Generative Adversarial Networks(深度卷积生成对抗网络).是2014年Ian J.Goodfellow 的那篇开创性的 ...
- DCGAN 代码简单解读
之前在DCGAN文章简单解读里说明了DCGAN的原理.本次来实现一个DCGAN,并在数据集上实际测试它的效果.本次的代码来自github开源代码DCGAN-tensorflow,感谢carpedm20 ...
- ECharts.js 超简单入门(本质canvas)
ECharts.js 超简单入门(本质canvas) 一.总结 一句话总结:echarts这些图标的本质都是canvas. 二.ECharts.js学习(一) 简单入门 EChart.js 简单入门 ...
- 超简单集成 HMS ML Kit 实现最大脸微笑抓拍
前言 如果大家对 HMS ML Kit 人脸检测功能有所了解,相信已经动手调用我们提供的接口编写自己的 APP 啦.目前就有小伙伴在调用接口的过程中反馈,不太清楚 HMS ML Kit 文档中的 ML ...
- 把C#程序(含多个Dll)合并成一个Exe的超简单方法
开发程序的时候经常会引用一些第三方的DLL,然后编译生成的exe文件就不能脱离这些DLL独立运行了. 但是,很多时候我们本想开发一款只需要一个exe就能完美运行的小工具.那该怎么办呢? 下文介绍一种超 ...
- 记住密码超简单实现(C#)
实现效果如下 实现过程 [Serializable] class User { //记住密码 private string loginID; public string LoginID { get { ...
- 超简单的JNI——NDK开发教程
不好意思各位,我按照网上一些教程进行JNI开发,折腾了半天也没成功,最后自己瞎搞搞定了,其实超简单的,网上的教程应该过时了,最新版的AS就包含了NDK编译的功能,完全不用手动javah,各种包名路径的 ...
随机推荐
- 线程太多导致socket连接池爆满,进程启动不了
Issue: 某部机上跟其它机器的连接有问题,ping可以通,telnet端口不通,可以其它机器可以连接到该机器上的进程. java应用启动不起来,产生以下错误. java.net.SocketExc ...
- AtCoder Regular Contest 069 F Flags 二分,2-sat,线段树优化建图
AtCoder Regular Contest 069 F Flags 二分,2-sat,线段树优化建图 链接 AtCoder 大意 在数轴上放上n个点,点i可能的位置有\(x_i\)或者\(y_i\ ...
- AGC010
AGC010 A [过水已隐藏] B 这题推完了还是不会/kk真的毒瘤 考虑每次会减少的总和是\(n(n+1)/2\),用原来的和除以这个可以得到操作次数\(m\)(不是整数无解) 再考虑相邻两个数\ ...
- NOI2019 Day2游记
开场T1是个最短路优化建图,边向二维矩形内所有点连,本来可以写树套树的,但是卡空间(128MB),后来发现其实是不用把边都建出来的,只需要用数据结构模拟dijkstra的过程,支持二维区间对一个值取m ...
- orm功能封装
封装功能: 查 : select **kwargs.keys() --返回-> obj -转为-->list [{},{}] ---> [obj,obj] class Models( ...
- 利用sftp迁移pve虚拟机
首先在A主机进行虚拟机备份vzdump <vmid>在B主机利用sftp复制备份到A主机cd /var/lib/vz/dump/sftp root@192.168.25.140 回答yes ...
- BigDecimal初始化不要用double类型
在进行单价.总价相关的计算时,就会用到BigDecimal. 在初始化时,一个不小心,就可能给自己挖坑. 示例如下: public class BigDecimalInitTest { public ...
- vs2010怎么更改调试时使用的浏览器
在当前网站的起始网页上右击,在右击菜单中选择 浏览方式 步骤阅读 2
- php error_reporting()关闭报错
错误报告级别:指定了在什么情况下,脚本代码中的错误(这里的错误是广义的错误,包括E_NOTICE注意.E_WARNING警告.E_ERROR致命错误等)会以错误报告的形式输出. 一.常用设置说明 er ...
- 韦东山视频第3课第1节_JNI_P【学习笔记】
一.android系统java调用C方法的大概的流程图如下: 二.下面写一个JNI的程序,java的hello方法在加载native库之后能够调用C方法. 2.1 JNIDemo.java 文件内容如 ...