Shortcuts

torchexpo.vision

Image Classification

https://res.cloudinary.com/torchexpo/image/upload/v1601144171/assets/tasks/image-classification.jpg

Image Classification is a fundamental task that attempts to comprehend an entire image as a whole. The goal is to classify the image by assigning it to a specific label. It refers to images in which only one object appears and is analyzed. In contrast, object detection involves both classification and localization tasks, and is used to analyze more realistic cases in which multiple objects may exist in an image.

Example:
>>> from torchexpo.vision import image_classification
>>>
>>> model = image_classification.squeezenet1_0()
>>> model.extract_torchscript()
>>> model.extract_onnx()

AlexNet

torchexpo.vision.image_classification.alexnet()[source]

AlexNet Model pre-trained on ImageNet

VGG

torchexpo.vision.image_classification.vgg11()[source]

VGG11 Model pre-trained on ImageNet

torchexpo.vision.image_classification.vgg11_bn()[source]

VGG11_BN Model pre-trained on ImageNet

torchexpo.vision.image_classification.vgg13()[source]

VGG13 Model pre-trained on ImageNet

torchexpo.vision.image_classification.vgg13_bn()[source]

VGG13_BN Model pre-trained on ImageNet

torchexpo.vision.image_classification.vgg16()[source]

VGG16 Model pre-trained on ImageNet

torchexpo.vision.image_classification.vgg16_bn()[source]

VGG16_BN Model pre-trained on ImageNet

torchexpo.vision.image_classification.vgg19()[source]

VGG19 Model pre-trained on ImageNet

torchexpo.vision.image_classification.vgg19_bn()[source]

VGG19_BN Model pre-trained on ImageNet

ResNet

torchexpo.vision.image_classification.resnet18()[source]

ResNet18 Model pre-trained on ImageNet

torchexpo.vision.image_classification.resnet34()[source]

ResNet34 Model pre-trained on ImageNet

torchexpo.vision.image_classification.resnet50()[source]

ResNet50 Model pre-trained on ImageNet

torchexpo.vision.image_classification.resnet101()[source]

ResNet101 Model pre-trained on ImageNet

torchexpo.vision.image_classification.resnet152()[source]

ResNet152 Model pre-trained on ImageNet

SqueezeNet

torchexpo.vision.image_classification.squeezenet1_0()[source]

SqueezeNet 1.0 Model pre-trained on ImageNet

torchexpo.vision.image_classification.squeezenet1_1()[source]

SqueezeNet 1.1 Model pre-trained on ImageNet

DenseNet

torchexpo.vision.image_classification.densenet121()[source]

DenseNet-121 Model pre-trained on ImageNet

torchexpo.vision.image_classification.densenet169()[source]

DenseNet-169 Model pre-trained on ImageNet

torchexpo.vision.image_classification.densenet161()[source]

DenseNet-161 Model pre-trained on ImageNet

torchexpo.vision.image_classification.densenet201()[source]

DenseNet-201 Model pre-trained on ImageNet

Inception v3

torchexpo.vision.image_classification.inceptionv3()[source]

Inception v3 Model pre-trained on ImageNet

GoogLeNet

torchexpo.vision.image_classification.googlenet()[source]

GoogLeNet (Inception v1) Model pre-trained on ImageNet

ShuffleNet v2

torchexpo.vision.image_classification.shufflenet_v2_x0_5()[source]

ShuffleNet V2 0.5x Model pre-trained on ImageNet

torchexpo.vision.image_classification.shufflenet_v2_x1_0()[source]

ShuffleNet V2 1.0x Model pre-trained on ImageNet

MobileNet v2

torchexpo.vision.image_classification.mobilenet_v2()[source]

MobileNet V2 Model pre-trained on ImageNet

ResNext

torchexpo.vision.image_classification.resnext50_32x4d()[source]

ResNext-50 32x4d Model pre-trained on ImageNet

torchexpo.vision.image_classification.resnext101_32x8d()[source]

ResNext-101 32x8d Model pre-trained on ImageNet

Wide ResNet

torchexpo.vision.image_classification.wide_resnet50_2()[source]

Wide ResNet-50-2 Model pre-trained on ImageNet

torchexpo.vision.image_classification.wide_resnet101_2()[source]

Wide ResNet-101-2 Model pre-trained on ImageNet

MNASNet

torchexpo.vision.image_classification.mnasnet0_5()[source]

MNASNet 0.5 Model pre-trained on ImageNet

torchexpo.vision.image_classification.mnasnet1_0()[source]

MNASNet 1.0 Model pre-trained on ImageNet

Image Segmentation

https://res.cloudinary.com/torchexpo/image/upload/v1601144171/assets/tasks/image-segmentation.jpg

Image Segmentation (or Semantic Segmentation) is the task of clustering parts of an image together which belong to the same object class. It is a form of pixel-level prediction because each pixel in an image is classified according to a category. Some example benchmarks for this task are Cityscapes, PASCAL VOC and ADE20K. Models are usually evaluated with the Mean Intersection-Over-Union (Mean IoU) and Pixel Accuracy metrics.

Example:
>>> from torchexpo.vision import image_segmentation
>>>
>>> model = image_segmentation.fcn_resnet50()
>>> model.extract_torchscript()
>>> model.extract_onnx()

FCN-ResNet

torchexpo.vision.image_segmentation.fcn_resnet50()[source]

FCN-ResNet50 Model pre-trained on COCO train2017

torchexpo.vision.image_segmentation.fcn_resnet101()[source]

FCN-ResNet101 Model pre-trained on COCO train2017

DeepLabV3-ResNet

torchexpo.vision.image_segmentation.deeplabv3_resnet50()[source]

DeepLabV3-ResNet50 Model pre-trained on COCO train2017

torchexpo.vision.image_segmentation.deeplabv3_resnet101()[source]

DeepLabV3-ResNet101 Model pre-trained on COCO train2017

Read the Docs v: latest
Versions
latest
Downloads
pdf
html
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.