Top Orientation Datasets and Models
The datasets below can be used to train fine-tuned models for orientation detection. You can explore each dataset in your browser using Roboflow and export the dataset into one of many formats.
Object Detection
4k images·2 models·157
* Auto-orientation of pixel data (with EXIF-orientation stripping)* Resize to 640x640 (Stretch)* annotate, and create datasets* collaborate with your team on computer vision projects* collect & organize images* export, train, and deploy computer vision models* understand and search unstructured image data* use active learning to improve your dataset over time192021222324252627282930
Object Detection
800 images
* Auto-orientation of pixel data (with EXIF-orientation stripping)* annotate, and create datasets* collaborate with your team on computer vision projects* collect & organize images* export, train, and deploy computer vision models* understand and search unstructured image data* use active learning to improve your dataset over time==============================For state of the art Computer Vision training notebooks you can use with this dataset,PUBG Player Detector - v6 2024-01-10 7:14pmPUBG-Players are annotated in YOLOv8 format.Roboflow is an end-to-end computer vision platform that helps youThe dataset includes 897 images.The following pre-processing was applied to each image:This dataset was exported via roboflow.com on January 10, 2024 at 4:16 PM GMTTo find over 100k other datasets and pre-trained models, visit https://universe.roboflow.comvisit https://github.com/roboflow/notebooks
Object Detection
680 images
* Auto-orientation of pixel data (with EXIF-orientation stripping)* Resize to 640x640 (Stretch)==============================Fruits and Thumb detection - v1 yolov5_v1Fruits-and-Thumb are annotated in YOLO v5 PyTorch format.It includes 687 images.The following pre-processing was applied to each image:This dataset was exported via roboflow.ai on March 4, 2022 at 12:38 PM GMT
Object Detection
600 images
elephantfoxmonkeypigtiger* Auto-orientation of pixel data (with EXIF-orientation stripping)* Resize to 640x640 (Stretch)* annotate, and create datasets* collaborate with your team on computer vision projects* collect & organize images* export, train, and deploy computer vision models* understand and search unstructured image data* use active learning to improve your dataset over time19202122232425
Object Detection
86 images·9
keyboardlaptopphone* Auto-orientation of pixel data (with EXIF-orientation stripping)* Resize to 640x640 (Stretch)* annotate, and create datasets* collaborate with your team on computer vision projects* collect & organize images* export, train, and deploy computer vision models* understand and search unstructured image data* use active learning to improve your dataset over time1920212223==============================E-waste are annotated in YOLOv8 format.For state of the art Computer Vision training notebooks you can use with this dataset,Motherboard
Object Detection
652 images·2 models
whale- Auto-orientation of pixel data (with EXIF-orientation stripping)==============================Aquarium Combined - v2 raw-1024Coastal fishCoralCrabCrbCreatures are annotated in YOLO v5 PyTorch format-DolphinFrogGiant gowramiGold FishGrey Tiger FishGrey mulletGuillemot birdIt includes 638 images-Jelly fishMilky White Koi FishMorone saxatilis
Object Detection
40 images·1 model·9
batterycomputerlaptopmobileremotetelevisionwatch* Auto-orientation of pixel data (with EXIF-orientation stripping)* Resize to 640x640 (Stretch)* annotate, and create datasets* collaborate with your team on computer vision projects* collect & organize images* export, train, and deploy computer vision models* understand and search unstructured image data* use active learning to improve your dataset over time1920212223
Object Detection
9.33k images·1 model
* Auto-orientation of pixel data (with EXIF-orientation stripping)* Resize to 640x640 (Stretch)* annotate, and create datasets* collaborate with your team on computer vision projects* collect & organize images* export, train, and deploy computer vision models* understand and search unstructured image data* use active learning to improve your dataset over time192021222324252627282930
Object Detection
7.22k images·1 model·10
* Auto-orientation of pixel data (with EXIF-orientation stripping)* Equal probability of one of the following 90-degree rotations: none, clockwise, counter-clockwise, upside-down* Random Gaussian blur of between 0 and 2.5 pixels* Resize to 640x640 (Stretch)* annotate, and create datasets* collaborate with your team on computer vision projects* export, train, and deploy computer vision models* understand and search unstructured image data* use active learning to improve your dataset over time222324262729==============================AxeBazookaGunKatana
Object Detection
242 images·1 model·3
Object Detection
6.86k images
- Auto-orientation of pixel data (with EXIF-orientation stripping)- Random rotation of between -10 and +10 degrees- Resize to 640x640 (Stretch)- collaborate with your team on computer vision projects- understand and search unstructured image data- use active learning to improve your dataset over time==============================Orientation 9 models - v4 2025-01-30 12:08pmRoboflow is an end-to-end computer vision platform that helps youThe dataset includes 6890 images-The following augmentation was applied to create 3 versions of each source image:The following pre-processing was applied to each image:The following transformations were applied to the bounding boxes of each image:Unknown-mRm4 are annotated in YOLOv8 Oriented Object Detection format-visit https:--github-com-roboflow-notebooks
Object Detection
3.28k images·1
* Auto-orientation of pixel data (with EXIF-orientation stripping)* Randomly crop between 0 and 20 percent of the image* Resize to 640x640 (Stretch)==============================It includes 3328 images.Liqours are annotated in YOLO v5 PyTorch format.The following augmentation was applied to create 3 versions of each source image:The following pre-processing was applied to each image:This dataset was exported via roboflow.ai on May 23, 2022 at 5:15 PM GMTamarettocamparicointreauginkahlualiquors - v2 datasetv2rumscotch-whiskysweet-vermouthtequilavodka
Object Detection
6.61k images·16
* Auto-orientation of pixel data (with EXIF-orientation stripping)* annotate, and create datasets* collaborate with your team on computer vision projects* collect & organize images* export, train, and deploy computer vision models* understand and search unstructured image data* use active learning to improve your dataset over time013161835==============================Adson_Forceps_Non_ToothAllis ForcepsArmy_navyBabcock ForcepsBandage SciccorsCatheter Tray
Object Detection
8.52k images·1 model
Object Detection
878 images
buscartruckvan* Auto-orientation of pixel data (with EXIF-orientation stripping)* Resize to 640x640 (Stretch)* annotate, and create datasets* collaborate with your team on computer vision projects* collect & organize images* export, train, and deploy computer vision models* understand and search unstructured image data* use active learning to improve your dataset over time-Car-or-Plane-or-Ship are annotated in YOLOv8 format.==============================For state of the art Computer Vision training notebooks you can use with this dataset,Roboflow is an end-to-end computer vision platform that helps youThe dataset includes 698 images.The following pre-processing was applied to each image:This dataset was exported via roboflow.com on September 25, 2024 at 7:38 AM GMTTo find over 100k other datasets and pre-trained models, visit https://universe.roboflow.com
Object Detection
2.56k images
* Auto-orientation of pixel data (with EXIF-orientation stripping)* Resize to 1000x1000 (Stretch)* annotate, and create datasets* collaborate with your team on computer vision projects* collect & organize images* export, train, and deploy computer vision models* understand and search unstructured image data* use active learning to improve your dataset over time192021222324252627282930
Instance Segmentation
2.02k images·2 models
Object Detection
2.45k images·1 model
object* 50% probability of horizontal flip* Auto-orientation of pixel data (with EXIF-orientation stripping)* Resize to 640x640 (Stretch)* annotate, and create datasets* collaborate with your team on computer vision projects* collect & organize images* export, train, and deploy computer vision models* understand and search unstructured image data* use active learning to improve your dataset over time20==============================For state of the art Computer Vision training notebooks you can use with this dataset,Roboflow is an end-to-end computer vision platform that helps youSignals are annotated in YOLO v5 PyTorch format.The dataset includes 2587 images.The following augmentation was applied to create 3 versions of each source image:The following pre-processing was applied to each image:This dataset was exported via roboflow.com on November 25, 2023 at 12:38 AM GMTTo find over 100k other datasets and pre-trained models, visit https://universe.roboflow.com
Object Detection
599 images·1 model
* Auto-orientation of pixel data (with EXIF-orientation stripping)==============================Aquarium Combined - v2 raw-1024Creatures are annotated in YOLO v5 PyTorch format.It includes 638 images.The following pre-processing was applied to each image:This dataset was exported via roboflow.ai on November 18, 2020 at 7:55 PM GMT
Object Detection
806 images·1 model
- Auto-orientation of pixel data (with EXIF-orientation stripping)- Random Gaussian blur of between 0 and 2-5 pixels- Random rotation of between -20 and +20 degrees- Resize to 640x640 (Stretch)- collaborate with your team on computer vision projects- understand and search unstructured image data- use active learning to improve your dataset over time100101102103104105106107108109110111112
Object Detection
1.43k images·1 model
-- 50- probability of horizontal flip- Auto-orientation of pixel data -with EXIF-orientation stripping-- Grayscale -CRT phosphor-- Random Gaussian blur of between 0 and 2-5 pixels- Randomly crop between 0 and 20 percent of the image- annotate- and create datasets- collaborate with your team on computer vision projects- collect - organize images- export- train- and deploy computer vision models- understand and search unstructured image data- use active learning to improve your dataset over time2324262728293031
Object Detection
2.41k images·1 model
* Auto-orientation of pixel data (with EXIF-orientation stripping)* Resize to 640x640 (Stretch)* annotate, and create datasets* collaborate with your team on computer vision projects* collect & organize images* export, train, and deploy computer vision models* understand and search unstructured image data* use active learning to improve your dataset over time1 peso1-peso10peso10pesos_Front20 peso20 pesos20 peso20 pesos20 pesos_Front20peso5 peso==============================
Object Detection
4.96k images·1 model·11
* Auto-orientation of pixel data (with EXIF-orientation stripping)* Resize to 640x640 (Stretch)* annotate, and create datasets* collaborate with your team on computer vision projects* collect & organize images* export, train, and deploy computer vision models* understand and search unstructured image data* use active learning to improve your dataset over time0 are annotated in YOLOv8 format.1920212223242526==============================For state of the art Computer Vision training notebooks you can use with this dataset,No image augmentation techniques were applied.
Object Detection
7.11k images
-- Auto-orientation of pixel data (with EXIF-orientation stripping)- Random rotation of between -10 and +10 degrees- Random shear of between -14° to +14° horizontally and -9° to +9° vertically- Resize to 640x640 (Stretch)- collaborate with your team on computer vision projects- understand and search unstructured image data- use active learning to improve your dataset over time==============================IrgaMushrooms are annotated in YOLOv8 format-Roboflow is an end-to-end computer vision platform that helps youThe dataset includes 11376 images-The following augmentation was applied to create 3 versions of each source image:The following pre-processing was applied to each image:boyroshnikfizaliskastenikapaslentern
Object Detection
1.44k images·1 model·5
* Auto-orientation of pixel data (with EXIF-orientation stripping)* Resize to 640x640 (Stretch)* annotate, and create datasets* collaborate with your team on computer vision projects* collect & organize images* export, train, and deploy computer vision models* understand and search unstructured image data* use active learning to improve your dataset over time192021222324252627282930
Classification
9.56k images·2
* 50% probability of horizontal flip* 50% probability of vertical flip* Auto-orientation of pixel data (with EXIF-orientation stripping)* Equal probability of one of the following 90-degree rotations: none, clockwise, counter-clockwise, upside-down* Random Gaussian blur of between 0 and 1.75 pixels* Random brigthness adjustment of between -25 and +25 percent* Random exposure adjustment of between -15 and +15 percent* Random rotation of between -10 and +10 degrees* Random shear of between -2° to +2° horizontally and -2° to +2° vertically* Randomly crop between 0 and 15 percent of the image* Resize to 640x640 (Stretch)* Salt and pepper noise was applied to 2 percent of pixels* annotate, and create datasets* collaborate with your team on computer vision projects* collect & organize images* export, train, and deploy computer vision models* understand and search unstructured image data* use active learning to improve your dataset over time2930
Object Detection
1.05k images
- Auto-orientation of pixel data (with EXIF-orientation stripping)- Resize to 416x416 (Stretch)- collaborate with your team on computer vision projects- understand unstructured image data- use active learning to improve your dataset over time==============================Image are annotated in YOLO v5 PyTorch format-It includes 5136 images-Roboflow is an end-to-end computer vision platform that helps youThe following pre-processing was applied to each image:ocean_waste - v1 2022-09-19 5:06pm
Object Detection
2.11k images·1 model
* Auto-orientation of pixel data (with EXIF-orientation stripping)* Random rotation of between -15 and +15 degrees* Resize to 640x640 (Fit within)* annotate, and create datasets* collaborate with your team on computer vision projects* collect & organize images* export, train, and deploy computer vision models* understand and search unstructured image data* use active learning to improve your dataset over time==============================For state of the art Computer Vision training notebooks you can use with this dataset,LAP Detection - v5 2024-08-22 3:25pmLAP-number are annotated in YOLOv8 format.Roboflow is an end-to-end computer vision platform that helps youThe dataset includes 6073 images.The following augmentation was applied to create 3 versions of each source image:The following pre-processing was applied to each image:This dataset was exported via roboflow.com on August 22, 2024 at 4:18 PM GMTTo find over 100k other datasets and pre-trained models, visit https://universe.roboflow.comvisit https://github.com/roboflow/notebooks
Object Detection
839 images·1 model
* Auto-orientation of pixel data (with EXIF-orientation stripping)* annotate, and create datasets* collaborate with your team on computer vision projects* collect & organize images* export, train, and deploy computer vision models* understand and search unstructured image data* use active learning to improve your dataset over time==============================For state of the art Computer Vision training notebooks you can use with this dataset,Roboflow is an end-to-end computer vision platform that helps youSpeed are annotated in YOLOv8 format.The dataset includes 865 images.The following pre-processing was applied to each image:This dataset was exported via roboflow.com on December 7, 2023 at 8:01 PM GMTTo find over 100k other datasets and pre-trained models, visit https://universe.roboflow.comspeed - v1 2023-09-23 3:46pmvisit https://github.com/roboflow/notebooks
Object Detection
3.82k images
- Auto-orientation of pixel data (with EXIF-orientation stripping)- Resize to 640x640 (Stretch)- collaborate with your team on computer vision projects- understand and search unstructured image data- use active learning to improve your dataset over time19==============================A1-A2-A3-A4-A5-A are annotated in YOLO v7 PyTorch format-No image augmentation techniques were applied-Roboflow is an end-to-end computer vision platform that helps youThe dataset includes 3842 images-The following pre-processing was applied to each image:mar20 - v1 2024-09-09 6:55amvisit https:--github-com-roboflow-notebooks
Object Detection
3.26k images·2
* Auto-contrast via contrast stretching* Auto-orientation of pixel data (with EXIF-orientation stripping)* Equal probability of one of the following 90-degree rotations: none, clockwise, counter-clockwise, upside-down* Random shear of between -14° to +14° horizontally and -15° to +15° vertically* Resize to 800x800 (Stretch)* Salt and pepper noise was applied to 1.13 percent of pixels* annotate, and create datasets* collaborate with your team on computer vision projects* collect & organize images* export, train, and deploy computer vision models* understand and search unstructured image data* use active learning to improve your dataset over time100101102103104105106107
Object Detection
1.76k images
* 50% probability of horizontal flip* 50% probability of vertical flip* Auto-orientation of pixel data (with EXIF-orientation stripping)* Random Gaussian blur of between 0 and 1.5 pixels* Random exposure adjustment of between -10 and +10 percent* Randomly crop between 0 and 20 percent of the image* Resize to 640x640 (Stretch)* annotate, and create datasets* collaborate with your team on computer vision projects* collect & organize images* export, train, and deploy computer vision models* understand and search unstructured image data* use active learning to improve your dataset over time242526==============================American Sign Language Letters - v2 2024-12-10 12:43pmFor state of the art Computer Vision training notebooks you can use with this dataset,Letters are annotated in YOLOv8 format.
Object Detection
9.76k images
* Auto-orientation of pixel data (with EXIF-orientation stripping)* Resize to 640x640 (Stretch)* annotate, and create datasets* collaborate with your team on computer vision projects* collect & organize images* export, train, and deploy computer vision models* understand and search unstructured image data* use active learning to improve your dataset over time192021222324252627282930
Object Detection
286 images
Classification
1.72k images·3
* 50% probability of horizontal flip* Auto-orientation of pixel data (with EXIF-orientation stripping)* Random Gaussian blur of between 0 and 1.25 pixels* Random brigthness adjustment of between -25 and +25 percent* Random rotation of between -5 and +5 degrees* Random shear of between -5° to +5° horizontally and -5° to +5° vertically* Randomly crop between 0 and 20 percent of the image* Resize to 416x416 (Stretch)* annotate, and create datasets* collaborate with your team on computer vision projects* collect & organize images* export, train, and deploy computer vision models* understand unstructured image data* use active learning to improve your dataset over time22232425==============================American Sign Language Letters - v1 v1
Object Detection
169 images·1
bicyclebuscardogpedestrian crossingpersontraffic lighttreetruck* Auto-orientation of pixel data (with EXIF-orientation stripping)* Resize to 640x640 (Fit (black edges))* annotate, and create datasets* collaborate with your team on computer vision projects* collect & organize images* export, train, and deploy computer vision models* understand and search unstructured image data* use active learning to improve your dataset over time==============================For state of the art Computer Vision training notebooks you can use with this dataset,No image augmentation techniques were applied.
Classification
2.12k images
- Auto-contrast via contrast stretching- Auto-contrast via contrast stretching - collaborate with your team on computer vision projects- Auto-contrast via contrast stretching - collaborate with your team on computer vision projects - use active learning to improve your dataset over time 48 ==============================- Auto-contrast via contrast stretching - collaborate with your team on computer vision projects - use active learning to improve your dataset over time ==============================- Auto-contrast via contrast stretching - collaborate with your team on computer vision projects 48- Auto-contrast via contrast stretching 48 57- Auto-contrast via contrast stretching 48 57 ==============================- Auto-contrast via contrast stretching 48 57 ============================== No image augmentation techniques were applied-- Auto-contrast via contrast stretching 48 57 ============================== No image augmentation techniques were applied- The following pre-processing was applied to each image:- Auto-contrast via contrast stretching 48 57 ============================== The following pre-processing was applied to each image:- Auto-contrast via contrast stretching 48 57 No image augmentation techniques were applied- The following pre-processing was applied to each image:- Auto-contrast via contrast stretching 48 57 The following pre-processing was applied to each image:- Auto-contrast via contrast stretching 48 ============================== No image augmentation techniques were applied-- Auto-contrast via contrast stretching 48 ============================== No image augmentation techniques were applied- The following pre-processing was applied to each image:- Auto-contrast via contrast stretching 48 ============================== The following pre-processing was applied to each image:- Auto-contrast via contrast stretching 57 ==============================- Auto-contrast via contrast stretching 57 ============================== No image augmentation techniques were applied- The following pre-processing was applied to each image:- Auto-contrast via contrast stretching 57 No image augmentation techniques were applied- The following pre-processing was applied to each image:- Auto-contrast via contrast stretching ============================== No image augmentation techniques were applied-- Auto-contrast via contrast stretching ============================== The following pre-processing was applied to each image:
Object Detection
840 images
* Auto-orientation of pixel data (with EXIF-orientation stripping)* Resize to 896x896 (Stretch)==============================Fruits and Thumb detection - v5 v5 for yolov4 darknetFruits-and-Thumb are annotated in YOLO v5 PyTorch format.It includes 859 images.The following pre-processing was applied to each image:This dataset was exported via roboflow.ai on April 15, 2022 at 7:08 AM GMT
Object Detection
798 images·1 model
* Auto-orientation of pixel data (with EXIF-orientation stripping)* Resize to 640x640 (Stretch)* annotate, and create datasets* collaborate with your team on computer vision projects* collect & organize images* export, train, and deploy computer vision models* understand and search unstructured image data* use active learning to improve your dataset over time192021222324252627282930
Object Detection
664 images·2 models
- Auto-orientation of pixel data (with EXIF-orientation stripping)- collaborate with your team on computer vision projects- understand and search unstructured image data- use active learning to improve your dataset over time18192021222324==============================Construction Site Safety - v30 raw-images_latestversionConstruction are annotated in YOLOv11 format-No image augmentation techniques were applied-Roboflow is an end-to-end computer vision platform that helps youThe dataset includes 717 images-The following pre-processing was applied to each image:visit https:--github-com-roboflow-notebooks
Object Detection
520 images
* Auto-orientation of pixel data (with EXIF-orientation stripping)* Resize to 640x640 (Stretch)* annotate, and create datasets* collaborate with your team on computer vision projects* collect & organize images* export, train, and deploy computer vision models* understand and search unstructured image data* use active learning to improve your dataset over time192021222324==============================For state of the art Computer Vision training notebooks you can use with this dataset,Hands are annotated in YOLOv8 format.No image augmentation techniques were applied.Right hand - v41 11K-YOLOv8 v3Roboflow is an end-to-end computer vision platform that helps you
