Feature/sg 996 add reports to s3

README.md

@@ -37,6 +37,7 @@ and calibrate metrics to monitor your unique dataset.
    - [Image Adapter](#image-adapter)
    - [Label Adapter](#label-adapter)
    - [Example](#example)
+- [Pre-computed Dataset Analysis](#pre-computed-dataset-analysis)
 - [License](#license)
 
 ## Features
@@ -262,6 +263,236 @@ SegmentationAnalysisManager(
 )
 ```
 
+
+## Pre-computed Dataset Analysis
+
+<details>
+
+<summary><h3>Detection</h3></summary>
+
+Common Datasets
+
+- [COCO](https://dgreports.deci.ai/detection/COCO/Report.pdf)
+
+- [VOC](https://dgreports.deci.ai/detection/VOC/Report.pdf)
+
+[Roboflow 100](https://universe.roboflow.com/roboflow-100?ref=blog.roboflow.com) Datasets
+
+- [4-fold-defect](https://dgreports.deci.ai/detection/RF100_4-fold-defect/Report.pdf)
+
+- [abdomen-mri](https://dgreports.deci.ai/detection/RF100_abdomen-mri/Report.pdf)
+
+- [acl-x-ray](https://dgreports.deci.ai/detection/RF100_acl-x-ray/Report.pdf)
+
+- [activity-diagrams-qdobr](https://dgreports.deci.ai/detection/RF100_activity-diagrams-qdobr/Report.pdf)
+
+- [aerial-cows](https://dgreports.deci.ai/detection/RF100_aerial-cows/Report.pdf)
+
+- [aerial-pool](https://dgreports.deci.ai/detection/RF100_aerial-pool/Report.pdf)
+
+- [aerial-spheres](https://dgreports.deci.ai/detection/RF100_aerial-spheres/Report.pdf)
+
+- [animals-ij5d2](https://dgreports.deci.ai/detection/RF100_animals-ij5d2/Report.pdf)
+
+- [apex-videogame](https://dgreports.deci.ai/detection/RF100_apex-videogame/Report.pdf)
+
+- [apples-fvpl5](https://dgreports.deci.ai/detection/RF100_apples-fvpl5/Report.pdf)
+
+- [aquarium-qlnqy](https://dgreports.deci.ai/detection/RF100_aquarium-qlnqy/Report.pdf)
+
+- [asbestos](https://dgreports.deci.ai/detection/RF100_asbestos/Report.pdf)
+
+- [avatar-recognition-nuexe](https://dgreports.deci.ai/detection/RF100_avatar-recognition-nuexe/Report.pdf)
+
+- [axial-mri](https://dgreports.deci.ai/detection/RF100_axial-mri/Report.pdf)
+
+- [bacteria-ptywi](https://dgreports.deci.ai/detection/RF100_bacteria-ptywi/Report.pdf)
+
+- [bccd-ouzjz](https://dgreports.deci.ai/detection/RF100_bccd-ouzjz/Report.pdf)
+
+- [bees-jt5in](https://dgreports.deci.ai/detection/RF100_bees-jt5in/Report.pdf)
+
+- [bone-fracture-7fylg](https://dgreports.deci.ai/detection/RF100_bone-fracture-7fylg/Report.pdf)
+
+- [brain-tumor-m2pbp](https://dgreports.deci.ai/detection/RF100_brain-tumor-m2pbp/Report.pdf)
+
+- [cable-damage](https://dgreports.deci.ai/detection/RF100_cable-damage/Report.pdf)
+
+- [cables-nl42k](https://dgreports.deci.ai/detection/RF100_cables-nl42k/Report.pdf)
+
+- [cavity-rs0uf](https://dgreports.deci.ai/detection/RF100_cavity-rs0uf/Report.pdf)
+
+- [cell-towers](https://dgreports.deci.ai/detection/RF100_cell-towers/Report.pdf)
+
+- [cells-uyemf](https://dgreports.deci.ai/detection/RF100_cells-uyemf/Report.pdf)
+
+- [chess-pieces-mjzgj](https://dgreports.deci.ai/detection/RF100_chess-pieces-mjzgj/Report.pdf)
+
+- [circuit-elements](https://dgreports.deci.ai/detection/RF100_circuit-elements/Report.pdf)
+
+- [circuit-voltages](https://dgreports.deci.ai/detection/RF100_circuit-voltages/Report.pdf)
+
+- [cloud-types](https://dgreports.deci.ai/detection/RF100_cloud-types/Report.pdf)
+
+- [coins-1apki](https://dgreports.deci.ai/detection/RF100_coins-1apki/Report.pdf)
+
+- [construction-safety-gsnvb](https://dgreports.deci.ai/detection/RF100_construction-safety-gsnvb/Report.pdf)
+
+- [coral-lwptl](https://dgreports.deci.ai/detection/RF100_coral-lwptl/Report.pdf)
+
+- [corrosion-bi3q3](https://dgreports.deci.ai/detection/RF100_corrosion-bi3q3/Report.pdf)
+
+- [cotton-20xz5](https://dgreports.deci.ai/detection/RF100_cotton-20xz5/Report.pdf)
+
+- [cotton-plant-disease](https://dgreports.deci.ai/detection/RF100_cotton-plant-disease/Report.pdf)
+
+- [csgo-videogame](https://dgreports.deci.ai/detection/RF100_csgo-videogame/Report.pdf)
+
+- [currency-v4f8j](https://dgreports.deci.ai/detection/RF100_currency-v4f8j/Report.pdf)
+
+- [digits-t2eg6](https://dgreports.deci.ai/detection/RF100_digits-t2eg6/Report.pdf)
+
+- [document-parts](https://dgreports.deci.ai/detection/RF100_document-parts/Report.pdf)
+
+- [excavators-czvg9](https://dgreports.deci.ai/detection/RF100_excavators-czvg9/Report.pdf)
+
+- [farcry6-videogame](https://dgreports.deci.ai/detection/RF100_farcry6-videogame/Report.pdf)
+
+- [fish-market-ggjso](https://dgreports.deci.ai/detection/RF100_fish-market-ggjso/Report.pdf)
+
+- [flir-camera-objects](https://dgreports.deci.ai/detection/RF100_flir-camera-objects/Report.pdf)
+
+- [furniture-ngpea](https://dgreports.deci.ai/detection/RF100_furniture-ngpea/Report.pdf)
+
+- [gauge-u2lwv](https://dgreports.deci.ai/detection/RF100_gauge-u2lwv/Report.pdf)
+
+- [grass-weeds](https://dgreports.deci.ai/detection/RF100_grass-weeds/Report.pdf)
+
+- [gynecology-mri](https://dgreports.deci.ai/detection/RF100_gynecology-mri/Report.pdf)
+
+- [halo-infinite-angel-videogame](https://dgreports.deci.ai/detection/RF100_halo-infinite-angel-videogame/Report.pdf)
+
+- [hand-gestures-jps7z](https://dgreports.deci.ai/detection/RF100_hand-gestures-jps7z/Report.pdf)
+
+- [insects-mytwu](https://dgreports.deci.ai/detection/RF100_insects-mytwu/Report.pdf)
+
+- [leaf-disease-nsdsr](https://dgreports.deci.ai/detection/RF100_leaf-disease-nsdsr/Report.pdf)
+
+- [lettuce-pallets](https://dgreports.deci.ai/detection/RF100_lettuce-pallets/Report.pdf)
+
+- [liver-disease](https://dgreports.deci.ai/detection/RF100_liver-disease/Report.pdf)
+
+- [marbles](https://dgreports.deci.ai/detection/RF100_marbles/Report.pdf)
+
+- [mask-wearing-608pr](https://dgreports.deci.ai/detection/RF100_mask-wearing-608pr/Report.pdf)
+
+- [mitosis-gjs3g](https://dgreports.deci.ai/detection/RF100_mitosis-gjs3g/Report.pdf)
+
+- [number-ops](https://dgreports.deci.ai/detection/RF100_number-ops/Report.pdf)
+
+- [paper-parts](https://dgreports.deci.ai/detection/RF100_paper-parts/Report.pdf)
+
+- [paragraphs-co84b](https://dgreports.deci.ai/detection/RF100_paragraphs-co84b/Report.pdf)
+
+- [parasites-1s07h](https://dgreports.deci.ai/detection/RF100_parasites-1s07h/Report.pdf)
+
+- [peanuts-sd4kf](https://dgreports.deci.ai/detection/RF100_peanuts-sd4kf/Report.pdf)
+
+- [peixos-fish](https://dgreports.deci.ai/detection/RF100_peixos-fish/Report.pdf)
+
+- [people-in-paintings](https://dgreports.deci.ai/detection/RF100_people-in-paintings/Report.pdf)
+
+- [pests-2xlvx](https://dgreports.deci.ai/detection/RF100_pests-2xlvx/Report.pdf)
+
+- [phages](https://dgreports.deci.ai/detection/RF100_phages/Report.pdf)
+
+- [pills-sxdht](https://dgreports.deci.ai/detection/RF100_pills-sxdht/Report.pdf)
+
+- [poker-cards-cxcvz](https://dgreports.deci.ai/detection/RF100_poker-cards-cxcvz/Report.pdf)
+
+- [printed-circuit-board](https://dgreports.deci.ai/detection/RF100_printed-circuit-board/Report.pdf)
+
+- [radio-signal](https://dgreports.deci.ai/detection/RF100_radio-signal/Report.pdf)
+
+- [road-signs-6ih4y](https://dgreports.deci.ai/detection/RF100_road-signs-6ih4y/Report.pdf)
+
+- [road-traffic](https://dgreports.deci.ai/detection/RF100_road-traffic/Report.pdf)
+
+- [robomasters-285km](https://dgreports.deci.ai/detection/RF100_robomasters-285km/Report.pdf)
+
+- [secondary-chains](https://dgreports.deci.ai/detection/RF100_secondary-chains/Report.pdf)
+
+- [sedimentary-features-9eosf](https://dgreports.deci.ai/detection/RF100_sedimentary-features-9eosf/Report.pdf)
+
+- [shark-teeth-5atku](https://dgreports.deci.ai/detection/RF100_shark-teeth-5atku/Report.pdf)
+
+- [sign-language-sokdr](https://dgreports.deci.ai/detection/RF100_sign-language-sokdr/Report.pdf)
+
+- [signatures-xc8up](https://dgreports.deci.ai/detection/RF100_signatures-xc8up/Report.pdf)
+
+- [smoke-uvylj](https://dgreports.deci.ai/detection/RF100_smoke-uvylj/Report.pdf)
+
+- [soccer-players-5fuqs](https://dgreports.deci.ai/detection/RF100_soccer-players-5fuqs/Report.pdf)
+
+- [soda-bottles](https://dgreports.deci.ai/detection/RF100_soda-bottles/Report.pdf)
+
+- [solar-panels-taxvb](https://dgreports.deci.ai/detection/RF100_solar-panels-taxvb/Report.pdf)
+
+- [stomata-cells](https://dgreports.deci.ai/detection/RF100_stomata-cells/Report.pdf)
+
+- [street-work](https://dgreports.deci.ai/detection/RF100_street-work/Report.pdf)
+
+- [tabular-data-wf9uh](https://dgreports.deci.ai/detection/RF100_tabular-data-wf9uh/Report.pdf)
+
+- [team-fight-tactics](https://dgreports.deci.ai/detection/RF100_team-fight-tactics/Report.pdf)
+
+- [thermal-cheetah-my4dp](https://dgreports.deci.ai/detection/RF100_thermal-cheetah-my4dp/Report.pdf)
+
+- [thermal-dogs-and-people-x6ejw](https://dgreports.deci.ai/detection/RF100_thermal-dogs-and-people-x6ejw/Report.pdf)
+
+- [trail-camera](https://dgreports.deci.ai/detection/RF100_trail-camera/Report.pdf)
+
+- [truck-movement](https://dgreports.deci.ai/detection/RF100_truck-movement/Report.pdf)
+
+- [tweeter-posts](https://dgreports.deci.ai/detection/RF100_tweeter-posts/Report.pdf)
+
+- [tweeter-profile](https://dgreports.deci.ai/detection/RF100_tweeter-profile/Report.pdf)
+
+- [underwater-objects-5v7p8](https://dgreports.deci.ai/detection/RF100_underwater-objects-5v7p8/Report.pdf)
+
+- [underwater-pipes-4ng4t](https://dgreports.deci.ai/detection/RF100_underwater-pipes-4ng4t/Report.pdf)
+
+- [uno-deck](https://dgreports.deci.ai/detection/RF100_uno-deck/Report.pdf)
+
+- [valentines-chocolate](https://dgreports.deci.ai/detection/RF100_valentines-chocolate/Report.pdf)
+
+- [vehicles-q0x2v](https://dgreports.deci.ai/detection/RF100_vehicles-q0x2v/Report.pdf)
+
+- [wall-damage](https://dgreports.deci.ai/detection/RF100_wall-damage/Report.pdf)
+
+- [washroom-rf1fa](https://dgreports.deci.ai/detection/RF100_washroom-rf1fa/Report.pdf)
+
+- [weed-crop-aerial](https://dgreports.deci.ai/detection/RF100_weed-crop-aerial/Report.pdf)
+
+- [wine-labels](https://dgreports.deci.ai/detection/RF100_wine-labels/Report.pdf)
+
+- [x-ray-rheumatology](https://dgreports.deci.ai/detection/RF100_x-ray-rheumatology/Report.pdf)
+
+</details>
+
+
+<details>
+
+<summary><h3>Segmentation</h3></summary>
+
+- [COCO](https://dgreports.deci.ai/segmentation/COCO/Report.pdf)
+
+- [Cityspace](https://dgreports.deci.ai/segmentation/Cityspace/Report.pdf)
+
+- [VOC](https://dgreports.deci.ai/segmentation/VOC/Report.pdf)
+
+</details>
+
 ## Community
 <table style="border: 0">
   <tr>
@@ -272,4 +503,4 @@ SegmentationAnalysisManager(
 
 ## License
 
-This project is released under the [Apache 2.0 license](LICENSE.md).
+This project is released under the [Apache 2.0 license](https://dgreports.deci.ai/detection/LICENSE.md).

scripts/generate_reports_detection.py

@@ -0,0 +1,71 @@
+"""
+Script for INTERNAL USE ONLY.
+Generate a list of reports for detection datasets.
+The script requires a clear dataset directory structures and will not work in environments not setup the same way.
+"""
+
+import os
+from data_gradients.managers.detection_manager import DetectionAnalysisManager
+
+from data_gradients.feature_extractors import (
+    SummaryStats,
+    ImagesResolution,
+    ImageColorDistribution,
+    ImagesAverageBrightness,
+    ImageDuplicates,
+    DetectionSampleVisualization,
+    DetectionClassHeatmap,
+    DetectionBoundingBoxArea,
+    DetectionBoundingBoxPerImageCount,
+    DetectionBoundingBoxSize,
+    DetectionClassFrequency,
+    DetectionClassesPerImageCount,
+    DetectionBoundingBoxIoU,
+)
+
+
+def _get_all_report_features(train_image_dir: str, valid_image_dir: str):
+    """Features defined manually in order to dynamically define `ImageDuplicates(train_image_dir=..., valid_image_dir=...)`"""
+    features = [
+        SummaryStats(),
+        ImagesResolution(),
+        ImageColorDistribution(),
+        ImagesAverageBrightness(),
+        ImageDuplicates(train_image_dir=train_image_dir, valid_image_dir=valid_image_dir),
+        DetectionSampleVisualization(n_rows=3, n_cols=4, stack_splits_vertically=True),
+        DetectionClassHeatmap(n_rows=6, n_cols=2, heatmap_shape=(200, 200)),
+        DetectionBoundingBoxArea(topk=30, prioritization_mode="train_val_diff"),
+        DetectionBoundingBoxPerImageCount(),
+        DetectionBoundingBoxSize(),
+        DetectionClassFrequency(topk=30, prioritization_mode="train_val_diff"),
+        DetectionClassesPerImageCount(topk=30, prioritization_mode="train_val_diff"),
+        DetectionBoundingBoxIoU(num_bins=10, class_agnostic=True),
+    ]
+    return features
+
+
+if __name__ == "__main__":
+
+    DetectionAnalysisManager.analyze_coco(
+        root_dir="/data/coco",
+        year=2017,
+        report_title="COCO",
+        feature_extractors=_get_all_report_features(train_image_dir="/data/coco/images/train2017/", valid_image_dir="/data/coco/images/val2017/"),
+    )
+
+    # VOC dataset does not clearly split the train/valid sets so we cannot run duplicate analysis
+    DetectionAnalysisManager.analyze_voc(root_dir="/data/voc/VOCdevkit", year=2012, report_title="VOC")
+
+    # Running on all the Roboflow100 datasets
+    for dataset_name in os.listdir("/data/rf100"):
+        dataset_path = os.path.join("/data/rf100", dataset_name)
+
+        DetectionAnalysisManager.analyze_coco_format(
+            root_dir=dataset_path,
+            feature_extractors=_get_all_report_features(train_image_dir=f"{dataset_path}/train/", valid_image_dir=f"{dataset_path}/valid/"),
+            train_images_subdir="train",
+            train_annotation_file_path="train/_annotations.coco.json",
+            val_images_subdir="valid",
+            val_annotation_file_path="valid/_annotations.coco.json",
+            report_title=f"DET RF100 {dataset_name}",
+        )

scripts/generate_reports_segmentation.py

@@ -0,0 +1,72 @@
+"""
+Script for INTERNAL USE ONLY.
+Generate a list of reports for segmentation datasets.
+The script requires a clear dataset directory structures and will not work in environments not setup the same way.
+"""
+
+from data_gradients.managers.segmentation_manager import SegmentationAnalysisManager
+from super_gradients.training.dataloaders import cityscapes_train, cityscapes_val
+
+from data_gradients.feature_extractors import (
+    SummaryStats,
+    ImagesResolution,
+    ImageColorDistribution,
+    ImagesAverageBrightness,
+    ImageDuplicates,
+    SegmentationBoundingBoxArea,
+    SegmentationBoundingBoxResolution,
+    SegmentationClassFrequency,
+    SegmentationClassHeatmap,
+    SegmentationClassesPerImageCount,
+    SegmentationComponentsConvexity,
+    SegmentationComponentsPerImageCount,
+    SegmentationSampleVisualization,
+)
+
+
+def _get_all_report_features(train_image_dir: str, valid_image_dir: str):
+    """Features defined manually in order to dynamically define `ImageDuplicates(train_image_dir=..., valid_image_dir=...)`"""
+    features = [
+        SummaryStats(),
+        ImagesResolution(),
+        ImageColorDistribution(),
+        ImagesAverageBrightness(),
+        ImageDuplicates(train_image_dir=train_image_dir, valid_image_dir=valid_image_dir),
+        SegmentationSampleVisualization(n_rows=3, n_cols=3, stack_splits_vertically=True, stack_mask_vertically=True),
+        SegmentationClassHeatmap(n_rows=6, n_cols=2, heatmap_shape=(200, 200)),
+        SegmentationClassFrequency(topk=30, prioritization_mode="train_val_diff"),
+        SegmentationClassesPerImageCount(topk=30, prioritization_mode="train_val_diff"),
+        SegmentationComponentsPerImageCount(),
+        SegmentationBoundingBoxResolution(),
+        SegmentationBoundingBoxArea(topk=30, prioritization_mode="train_val_diff"),
+        SegmentationComponentsConvexity(),
+    ]
+    return features
+
+
+if __name__ == "__main__":
+
+    SegmentationAnalysisManager.analyze_coco(
+        root_dir="/data/coco",
+        year=2017,
+        report_title="SEG COCO",
+        feature_extractors=_get_all_report_features(train_image_dir="/data/coco/images/train2017/", valid_image_dir="/data/coco/images/val2017/"),
+    )
+
+    # VOC dataset does not clearly split the train/valid sets so we cannot run duplicate analysis
+    SegmentationAnalysisManager.analyze_voc(
+        root_dir="/data/voc/VOCdevkit",
+        year=2012,
+        report_title="SEG VOC",
+    )
+
+    # Cityscape does not support image duplicate out of the box because it is made of multiple image sets
+    trainset = cityscapes_train()
+    val_set = cityscapes_val()
+    SegmentationAnalysisManager(
+        train_data=trainset,
+        val_data=val_set,
+        report_title="SEG Cityspace",
+        class_names=trainset.dataset.classes + ["Ignore"],
+        feature_extractors=_get_all_report_features(train_image_dir="/data/coco/images/train2017/", valid_image_dir="/data/coco/images/val2017/"),
+    ).run()