Package: torchvision 0.9.0.9000
Tomasz Kalinowski
torchvision: Models, Datasets and Transformations for Images
Provides access to datasets, models and preprocessing facilities for deep learning with images. Integrates seamlessly with the 'torch' package and its API borrows heavily from the 'PyTorch' vision package.
Authors:
torchvision_0.9.0.9000.tar.gz
torchvision_0.9.0.9000.zip(r-4.7)torchvision_0.9.0.9000.zip(r-4.6)torchvision_0.9.0.9000.zip(r-4.5)
torchvision_0.9.0.9000.tgz(r-4.6-any)torchvision_0.9.0.9000.tgz(r-4.5-any)
torchvision_0.9.0.9000.tar.gz(r-4.7-any)torchvision_0.9.0.9000.tar.gz(r-4.6-any)
torchvision_0.9.0.9000.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
card.svg |card.png
torchvision/json (API)
NEWS
| # Install 'torchvision' in R: |
| install.packages('torchvision', repos = c('https://mlverse.r-universe.dev', 'https://cloud.r-project.org')) |
Bug tracker:https://github.com/mlverse/torchvision/issues
Pkgdown/docs site:https://torchvision.mlverse.org
- collection_catalog - Dataset Collection Catalog
Last updated from:852d6a6fdf. Checks:9 OK. Indexed: yes.
| Target | Result | Time | Files | Syslog |
|---|---|---|---|---|
| linux-devel-x86_64 | OK | 157 | ||
| source / vignettes | OK | 180 | ||
| linux-release-x86_64 | OK | 205 | ||
| macos-release-arm64 | OK | 126 | ||
| macos-oldrel-arm64 | OK | 168 | ||
| windows-devel | OK | 112 | ||
| windows-release | OK | 137 | ||
| windows-oldrel | OK | 104 | ||
| wasm-release | OK | 126 |
Exports:base_loaderbatched_nmsbox_areabox_convertbox_ioucaltech_classescaltech101_datasetcaltech256_datasetcifar10_datasetcifar100_datasetclip_boxes_to_imagecoco_caption_datasetcoco_classescoco_detection_datasetcoco_segmentation_datasetdraw_bounding_boxesdraw_keypointsdraw_segmentation_masksemnist_collectionemnist_dataseteurosat_all_bands_dataseteurosat_dataseteurosat100_datasetfashion_mnist_datasetfer_datasetfgvc_aircraft_datasetflickr30k_caption_datasetflickr8k_caption_datasetflowers102_datasetgeneralized_box_iouget_collection_catalogimage_folder_datasetimagenet_1k_classesimagenet_21k_classesimagenet_21k_dfimagenet_classeskmnist_datasetlfw_pairs_datasetlfw_people_datasetlist_collection_datasetsmagick_loadermnist_datasetmodel_alexnetmodel_convnext_base_1kmodel_convnext_base_22kmodel_convnext_base_detectionmodel_convnext_base_fcnmodel_convnext_base_upernetmodel_convnext_large_1kmodel_convnext_large_22kmodel_convnext_small_22kmodel_convnext_small_22k1kmodel_convnext_small_detectionmodel_convnext_small_fcnmodel_convnext_small_upernetmodel_convnext_tiny_1kmodel_convnext_tiny_22kmodel_convnext_tiny_detectionmodel_convnext_tiny_fcnmodel_convnext_tiny_upernetmodel_deeplabv3_resnet101model_deeplabv3_resnet50model_efficientnet_b0model_efficientnet_b1model_efficientnet_b2model_efficientnet_b3model_efficientnet_b4model_efficientnet_b5model_efficientnet_b6model_efficientnet_b7model_efficientnet_v2_lmodel_efficientnet_v2_mmodel_efficientnet_v2_smodel_facenet_inception_resnet_v1model_facenet_onetmodel_facenet_pnetmodel_facenet_rnetmodel_fasterrcnn_mobilenet_v3_large_320_fpnmodel_fasterrcnn_mobilenet_v3_large_fpnmodel_fasterrcnn_resnet50_fpnmodel_fasterrcnn_resnet50_fpn_v2model_fcn_resnet101model_fcn_resnet50model_inception_v3model_maskrcnn_resnet50_fpnmodel_maskrcnn_resnet50_fpn_v2model_maxvitmodel_mobilenet_v2model_mobilenet_v3_largemodel_mobilenet_v3_large_quantizedmodel_mobilenet_v3_smallmodel_mtcnnmodel_resnet101model_resnet152model_resnet18model_resnet34model_resnet50model_resnext101_32x8dmodel_resnext50_32x4dmodel_vgg11model_vgg11_bnmodel_vgg13model_vgg13_bnmodel_vgg16model_vgg16_bnmodel_vgg19model_vgg19_bnmodel_vit_b_16model_vit_b_32model_vit_h_14model_vit_l_16model_vit_l_32model_wide_resnet101_2model_wide_resnet50_2nmsoxfordiiitpet_binary_datasetoxfordiiitpet_datasetoxfordiiitpet_segmentation_datasetpascal_detection_datasetpascal_segmentation_datasetpascal_voc_classesplaces365_datasetplaces365_dataset_largeqmnist_datasetremove_small_boxesrf100_biology_collectionrf100_damage_collectionrf100_document_collectionrf100_infrared_collectionrf100_medical_collectionrf100_peixos_segmentation_datasetrf100_underwater_collectionsearch_collectiontarget_transform_coco_maskstarget_transform_trimap_maskstensor_image_browsetensor_image_displaytiny_imagenet_datasettransform_adjust_brightnesstransform_adjust_contrasttransform_adjust_gammatransform_adjust_huetransform_adjust_saturationtransform_affinetransform_center_croptransform_color_jittertransform_convert_image_dtypetransform_croptransform_five_croptransform_grayscaletransform_hfliptransform_linear_transformationtransform_normalizetransform_padtransform_perspectivetransform_random_affinetransform_random_applytransform_random_choicetransform_random_croptransform_random_erasingtransform_random_grayscaletransform_random_horizontal_fliptransform_random_ordertransform_random_perspectivetransform_random_resized_croptransform_random_rotationtransform_random_vertical_fliptransform_resizetransform_resized_croptransform_rgb_to_grayscaletransform_rotatetransform_ten_croptransform_to_tensortransform_vflipvggface2_datasetvision_make_gridwhoi_plankton_datasetwhoi_small_coralnet_datasetwhoi_small_plankton_dataset
Dependencies:abindbitbit64callrclicorodescfarverfsgluejpegjsonlitelabelinglifecyclemagrittrotelpngprocessxpsR6rappdirsRColorBrewerRcpprlangsafetensorsscalestifftorchviridisLitewithrzeallot
Readme and manuals
Help Manual
| Help page | Topics |
|---|---|
| Base loader | base_loader |
| Batched Non-maximum Suppression (NMS) | batched_nms |
| Box Area | box_area |
| Box Convert | box_convert |
| box_cxcywh_to_xyxy | box_cxcywh_to_xyxy |
| Box IoU | box_iou |
| box_xywh_to_xyxy | box_xywh_to_xyxy |
| box_xyxy_to_cxcywh | box_xyxy_to_cxcywh |
| box_xyxy_to_xywh | box_xyxy_to_xywh |
| Caltech Class Labels | caltech_classes |
| Caltech Datasets | caltech101_dataset caltech256_dataset caltech_dataset |
| CIFAR datasets | cifar100_dataset cifar10_dataset |
| Clip Boxes to Image | clip_boxes_to_image |
| COCO Caption Dataset | coco_caption_dataset |
| MS COCO Class Labels | coco_classes |
| COCO Detection Dataset | coco_detection_dataset |
| COCO Segmentation Dataset | coco_segmentation_dataset |
| Dataset Collection Catalog | collection_catalog |
| Draws bounding boxes on image. | draw_bounding_boxes draw_bounding_boxes.default draw_bounding_boxes.image_with_bounding_box draw_bounding_boxes.torch_tensor |
| Draws Keypoints | draw_keypoints |
| Draw segmentation masks | draw_segmentation_masks draw_segmentation_masks.default draw_segmentation_masks.image_with_segmentation_mask draw_segmentation_masks.torch_tensor |
| EuroSAT datasets | eurosat100_dataset eurosat_all_bands_dataset eurosat_dataset |
| FER-2013 Facial Expression Dataset | fer_dataset |
| FGVC Aircraft Dataset | fgvc_aircraft_dataset |
| Flickr Caption Datasets | flickr30k_caption_dataset flickr8k_caption_dataset flickr_caption_dataset |
| Oxford Flowers 102 Dataset | flowers102_dataset |
| Generalized Box IoU | generalized_box_iou |
| Get Complete Collection Catalog | get_collection_catalog |
| Create an image folder dataset | image_folder_dataset |
| ImageNet Class Labels | imagenet_1k_classes imagenet_21k_classes imagenet_21k_df imagenet_classes |
| LFW Datasets | lfw_dataset lfw_pairs_dataset lfw_people_dataset |
| List Datasets in a Collection | list_collection_datasets |
| Load an Image using ImageMagick | magick_loader |
| MNIST and Derived Datasets | emnist_collection emnist_dataset fashion_mnist_dataset kmnist_dataset mnist_dataset qmnist_dataset |
| AlexNet Model Architecture | model_alexnet |
| ConvNeXt Implementation | model_convnext model_convnext_base_1k model_convnext_base_22k model_convnext_large_1k model_convnext_large_22k model_convnext_small_22k model_convnext_small_22k1k model_convnext_tiny_1k model_convnext_tiny_22k |
| ConvNeXt Detection Models (Faster R-CNN style) | model_convnext_base_detection model_convnext_detection model_convnext_small_detection model_convnext_tiny_detection |
| ConvNeXt Segmentation Models | model_convnext_base_fcn model_convnext_base_upernet model_convnext_segmentation model_convnext_small_fcn model_convnext_small_upernet model_convnext_tiny_fcn model_convnext_tiny_upernet |
| DeepLabV3 Semantic Segmentation Models | model_deeplabv3 model_deeplabv3_resnet101 model_deeplabv3_resnet50 |
| EfficientNet Models | model_efficientnet model_efficientnet_b0 model_efficientnet_b1 model_efficientnet_b2 model_efficientnet_b3 model_efficientnet_b4 model_efficientnet_b5 model_efficientnet_b6 model_efficientnet_b7 |
| EfficientNetV2 Models | model_efficientnet_v2 model_efficientnet_v2_l model_efficientnet_v2_m model_efficientnet_v2_s |
| MTCNN Face Detection Networks | model_facenet model_facenet_inception_resnet_v1 model_facenet_onet model_facenet_pnet model_facenet_rnet model_mtcnn |
| Faster R-CNN Models | model_fasterrcnn model_fasterrcnn_mobilenet_v3_large_320_fpn model_fasterrcnn_mobilenet_v3_large_fpn model_fasterrcnn_resnet50_fpn model_fasterrcnn_resnet50_fpn_v2 |
| Fully Convolutional Network for Semantic Segmentation | model_fcn_resnet model_fcn_resnet101 model_fcn_resnet50 |
| Inception v3 model | model_inception_v3 |
| Mask R-CNN Models | model_maskrcnn model_maskrcnn_resnet50_fpn model_maskrcnn_resnet50_fpn_v2 |
| MaxViT Model | model_maxvit |
| MobileNetV2 Model | model_mobilenet_v2 |
| MobileNetV3 Model | model_mobilenet_v3 model_mobilenet_v3_large model_mobilenet_v3_large_quantized model_mobilenet_v3_small |
| ResNet implementation | model_resnet model_resnet101 model_resnet152 model_resnet18 model_resnet34 model_resnet50 model_resnext101_32x8d model_resnext50_32x4d model_wide_resnet101_2 model_wide_resnet50_2 |
| VGG implementation | model_vgg model_vgg11 model_vgg11_bn model_vgg13 model_vgg13_bn model_vgg16 model_vgg16_bn model_vgg19 model_vgg19_bn |
| Vision Transformer Implementation | model_vit model_vit_b_16 model_vit_b_32 model_vit_h_14 model_vit_l_16 model_vit_l_32 |
| Non-maximum Suppression (NMS) | nms |
| Oxford-IIIT Pet Classification Datasets | oxfordiiitpet_binary_dataset oxfordiiitpet_dataset |
| Oxford-IIIT Pet Segmentation Dataset | oxfordiiitpet_segmentation_dataset |
| Pascal VOC Segmentation Dataset | pascal_voc_classes |
| Pascal VOC Datasets | pascal_detection_dataset pascal_segmentation_dataset pascal_voc_datasets |
| Places365 Dataset | places365_dataset places365_dataset_large |
| Remove Small Boxes | remove_small_boxes |
| RoboFlow 100 Biology dataset Collection | rf100_biology_collection |
| RoboFlow 100 Damages dataset Collection | rf100_damage_collection |
| RF100 Document Collection Datasets | rf100_document_collection |
| RoboFlow 100 Infrared dataset Collection | rf100_infrared_collection |
| RoboFlow 100 Medical dataset Collection | rf100_medical_collection |
| RF100 Peixos Segmentation Dataset | rf100_peixos_segmentation_dataset |
| RoboFlow 100 Underwater dataset Collection | rf100_underwater_collection |
| Search Collection Catalog | search_collection |
| Target Transform: COCO Polygon Segmentation to Masks | target_transform_coco_masks |
| Target Transform: Trimap to Boolean Masks | target_transform_trimap_masks |
| Display image tensor | tensor_image_browse |
| Display image tensor | tensor_image_display |
| Tiny ImageNet dataset | tiny_imagenet_dataset |
| Adjust the brightness of an image | transform_adjust_brightness |
| Adjust the contrast of an image | transform_adjust_contrast |
| Adjust the gamma of an RGB image | transform_adjust_gamma |
| Adjust the hue of an image | transform_adjust_hue |
| Adjust the color saturation of an image | transform_adjust_saturation |
| Apply affine transformation on an image keeping image center invariant | transform_affine |
| Crops the given image at the center | transform_center_crop |
| Randomly change the brightness, contrast and saturation of an image | transform_color_jitter |
| Convert a tensor image to the given 'dtype' and scale the values accordingly | transform_convert_image_dtype |
| Crop the given image at specified location and output size | transform_crop |
| Crop image into four corners and a central crop | transform_five_crop |
| Convert image to grayscale | transform_grayscale |
| Horizontally flip a PIL Image or Tensor | transform_hflip |
| Transform a tensor image with a square transformation matrix and a mean_vector computed offline | transform_linear_transformation |
| Normalize a tensor image with mean and standard deviation | transform_normalize |
| Pad the given image on all sides with the given "pad" value | transform_pad |
| Perspective transformation of an image | transform_perspective |
| Random affine transformation of the image keeping center invariant | transform_random_affine |
| Apply a list of transformations randomly with a given probability | transform_random_apply |
| Apply single transformation randomly picked from a list | transform_random_choice |
| Crop the given image at a random location | transform_random_crop |
| Randomly selects a rectangular region in an image and erases its pixel values | transform_random_erasing |
| Randomly convert image to grayscale with a given probability | transform_random_grayscale |
| Horizontally flip an image randomly with a given probability | transform_random_horizontal_flip |
| Apply a list of transformations in a random order | transform_random_order |
| Random perspective transformation of an image with a given probability | transform_random_perspective |
| Crop image to random size and aspect ratio | transform_random_resized_crop |
| Rotate the image by angle | transform_random_rotation |
| Vertically flip an image randomly with a given probability | transform_random_vertical_flip |
| Resize the input image to the given size | transform_resize |
| Crop an image and resize it to a desired size | transform_resized_crop |
| Convert RGB Image Tensor to Grayscale | transform_rgb_to_grayscale |
| Angular rotation of an image | transform_rotate |
| Crop an image and the flipped image each into four corners and a central crop | transform_ten_crop |
| Convert an image to a tensor | transform_to_tensor |
| Vertically flip a PIL Image or Tensor | transform_vflip |
| VGGFace2 Dataset | vggface2_dataset |
| A simplified version of torchvision.utils.make_grid | vision_make_grid |
| WHOI Plankton Datasets | whoi_plankton_dataset whoi_small_plankton_dataset |
| Coralnet Dataset | whoi_small_coralnet_dataset |
