dataeval 0.86.8__py3-none-any.whl → 0.87.0__py3-none-any.whl

{dataeval-0.86.8.dist-info → dataeval-0.87.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dataeval
-Version: 0.86.8
+Version: 0.87.0
 Summary: DataEval provides a simple interface to characterize image data and its impact on model performance across classification and object-detection tasks
 Project-URL: Homepage, https://dataeval.ai/
 Project-URL: Repository, https://github.com/aria-ml/dataeval/
@@ -8,7 +8,7 @@ Project-URL: Documentation, https://dataeval.readthedocs.io/
 Author-email: Andrew Weng <andrew.weng@ariacoustics.com>, Bill Peria <bill.peria@ariacoustics.com>, Jon Botts <jonathan.botts@ariacoustics.com>, Jonathan Christian <jonathan.christian@ariacoustics.com>, Justin McMillan <justin.mcmillan@ariacoustics.com>, Ryan Wood <ryan.wood@ariacoustics.com>, Scott Swan <scott.swan@ariacoustics.com>, Shaun Jullens <shaun.jullens@ariacoustics.com>
 Maintainer-email: ARiA <dataeval@ariacoustics.com>
 License-Expression: MIT
-License-File: LICENSE.txt
+License-File: LICENSE
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Science/Research
 Classifier: License :: OSI Approved :: MIT License
@@ -20,15 +20,12 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering
 Requires-Python: <3.13,>=3.9
-Requires-Dist: defusedxml>=0.7.1
 Requires-Dist: fast-hdbscan==0.2.0
 Requires-Dist: lightgbm>=4
 Requires-Dist: numba>=0.59.1
 Requires-Dist: numpy>=1.24.2
 Requires-Dist: pandas>=2.0
-Requires-Dist: pillow>=10.3.0
 Requires-Dist: polars>=1.0.0
-Requires-Dist: requests>=2.32.3
 Requires-Dist: scikit-learn>=1.5.0
 Requires-Dist: scipy>=1.10
 Requires-Dist: torch>=2.2.0
@@ -123,14 +120,8 @@ micromamba create -f environment\environment.yaml -c pytorch
 
 ### **Installing from GitHub**
 
-To install DataEval from source locally on Ubuntu, you will need `git-lfs` to
-download larger, binary source files.
-
-```bash
-sudo apt-get install git-lfs
-```
-
-Pull the source down and change to the DataEval project directory.
+To install DataEval from source locally on Ubuntu, pull the source down and
+change to the DataEval project directory.
 
 ```bash
 git clone https://github.com/aria-ml/dataeval.git
@@ -167,10 +158,7 @@ source .venv/bin/activate
 
 ## Contact Us
 
-If you have any questions, feel free to reach out to the people below:
-
-- **POC**: Scott Swan @scott.swan
-- **DPOC**: Andrew Weng @aweng
+If you have any questions, feel free to reach out to [us](mailto:dataeval@ariacoustics.com)!
 
 ## Acknowledgement
 

{dataeval-0.86.8.dist-info → dataeval-0.87.0.dist-info}/RECORD

@@ -1,23 +1,23 @@
-dataeval/__init__.py,sha256=dEDltdHOnbk4-XAbQwJLOZtCbRLZsDMnptWRwbF2r54,1773
+dataeval/__init__.py,sha256=aFzX3SLx8wgc763RY772P41ZLqeHcUHRKW9XAN0KfHQ,1793
 dataeval/_log.py,sha256=C7AGkIRzymvYJ0LQXtnShiy3i5Xrp8T58JzIHHguk_Q,365
-dataeval/_version.py,sha256=IPUOExUy8nF4kYGtCPV5bg6_IYDRLVOKnFJcNllcO1M,513
-dataeval/config.py,sha256=g3Np0Q3J5Rzij6Gsz7tJh7eOxgwNPf6NsFYmAR8Atfs,4219
+dataeval/_version.py,sha256=17MAD7hlEBqgdl5YlmaM4PJXKdgvw_hAzlX52HDAwlU,513
+dataeval/config.py,sha256=lL73s_xa9pBxHHCnBKi59D_tl4vS7ig1rfWbIYkM_ac,3839
 dataeval/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-dataeval/typing.py,sha256=W8rqFFkAqE5a5ar3MmB-O5gcMJqvoDKXC8Y0ggBqAKo,7216
+dataeval/typing.py,sha256=si4ZosMrHG-eYKSLCErAEI7Oo1giFRvWkaNK7EhRr1w,7513
 dataeval/data/__init__.py,sha256=wzQ6uUFLNB3VJR0a2QnRBYwEmwXT93q0WpHu7FmFW1E,486
 dataeval/data/_embeddings.py,sha256=PFjpdV9bfusCB4taTIYSzx1hP8nJb_KCkZTN8kMw-Hs,12885
 dataeval/data/_images.py,sha256=Rc_59CuU4zfN7Xm7an1XUx8ZghQg6a56VJWMZD9edRw,2654
-dataeval/data/_metadata.py,sha256=3aixstlgcAZXC0qNjwDlxjscC3IX1xjPt_FK0liRqoo,14423
+dataeval/data/_metadata.py,sha256=jr6W0aC_fKMYPwRjSHkXl02QTZ63QgqOnbvVOCoLLsg,15250
 dataeval/data/_selection.py,sha256=r06xeiyK8nTWPLyItkoPQRWZI1i6LATSue_cuEbCdc4,4463
-dataeval/data/_split.py,sha256=nQABR05vxil2Qx7-uX4Fm0_DWpibskBGDJOYj_b1u3I,16737
+dataeval/data/_split.py,sha256=0WOKwOxMBfzimo_VQUU0dbc4zQleA4OQFO4ho9W57hE,16732
 dataeval/data/selections/__init__.py,sha256=2m8ZB53wXzqLcqmc6p5atO6graB6ZyiRSNJFxf11X_g,613
-dataeval/data/selections/_classbalance.py,sha256=7v8ApoL3X8eCZ6fGDNTehE_bZ1loaP3TlhsJLaICVWg,1458
-dataeval/data/selections/_classfilter.py,sha256=bXfoYnWnAfUGsAQSlLufJeF2PfgRKekFHfBx8hv1r3w,4351
-dataeval/data/selections/_indices.py,sha256=RFsR9z10aM3N0gJSfKrukFpi-LkiQGXoOwXhmOQ5cpg,630
+dataeval/data/selections/_classbalance.py,sha256=AqExg-QnYBcfBNzS1Ygsz3Cgb2cqcgGXE0-cseD8_vA,1580
+dataeval/data/selections/_classfilter.py,sha256=oYTsqxwOV_mos4_BoNqhHOAKUWFMAXczjrJfEkusLIY,4422
+dataeval/data/selections/_indices.py,sha256=5TqKyMJmFRoNfJT5T9yIMx-p5VeJmSmCl2Qxzwi0pPE,628
 dataeval/data/selections/_limit.py,sha256=JG4GmEiNKt3sk4PbOUbBnGGzNlyz72H-kQrt8COMm4Y,512
-dataeval/data/selections/_prioritize.py,sha256=4dGUvgR7m6NGzzPU0N_bw0Xhujo8b72Wo8L4PGHbvBo,11233
-dataeval/data/selections/_reverse.py,sha256=b67kNC43A5KpQOic5gifjo9HpJ7FMh4LFCrfovPiJ-M,368
-dataeval/data/selections/_shuffle.py,sha256=TSCIZBgLAn09iMI_WIw0aqwSU4NZLAhHG7t8H_CuDUY,1195
+dataeval/data/selections/_prioritize.py,sha256=ss_GZ5MB2ohdNuB55C69TYNwV3PUSmk715gDJI6qfYA,20140
+dataeval/data/selections/_reverse.py,sha256=FqYlpPg-0Vz75kbEhGFrJlzIGELSmDZxPlBMY18a57I,365
+dataeval/data/selections/_shuffle.py,sha256=nZG1kxc7TfiznaPnDYqWTWnFBf2gWb8koCmEWnf8TWE,1242
 dataeval/detectors/__init__.py,sha256=3Sg-XWlwr75zEEH3hZKA4nWMtGvaRlnfzTWvZG_Ak6U,189
 dataeval/detectors/drift/__init__.py,sha256=Jqv98oOVeC2tvHlNGxQ8RJ6De2q4SyS5lTpaYlb4ocM,756
 dataeval/detectors/drift/_base.py,sha256=6aNF1LzG3w1sNUrmSBbsvuN5IkQnoRikRacqobYge84,7592
@@ -36,9 +36,10 @@ dataeval/detectors/drift/_nml/_thresholds.py,sha256=WGdkLei9w_EvvsRHQzWdDyFVoZHI
 dataeval/detectors/linters/__init__.py,sha256=xn2zPwUcmsuf-Jd9uw6AVI11C9z1b1Y9fYtuFnXenZ0,404
 dataeval/detectors/linters/duplicates.py,sha256=X5WSEvI_BHkLoXjkaHK6wTnSkx4IjpO_exMRjSlhc70,4963
 dataeval/detectors/linters/outliers.py,sha256=GaM9n8yPgBPzVOL_bxJCj0eCwobEEP4JHKHD9liRdlw,10130
-dataeval/detectors/ood/__init__.py,sha256=juCYBDs7CQEAtMhnEpPqF6uTrOIH9kTBSuQ_GRw6a8o,283
+dataeval/detectors/ood/__init__.py,sha256=qDoDdQetJY1xZB43dNzcOIO_8NiEuEU0z1QNU4QkEXs,341
 dataeval/detectors/ood/ae.py,sha256=cJ7nq4iwTvW8uihHCUhGfTlKsAlthJ2tOhgSsB27cOY,2941
-dataeval/detectors/ood/base.py,sha256=hx-TPJnUTZ7KcBkm8SbN1RGhtJyQN0XLajDyNqiZrJo,3042
+dataeval/detectors/ood/base.py,sha256=fsjQ7wHRNJNPLGFw_6jvygkFFbv2G1ydwp8Zh1ncVlA,4374
+dataeval/detectors/ood/knn.py,sha256=Fu77geQFHPYNOn81VIXUJ3yC3t5Ylv0ZgvwMeA2JX6I,3782
 dataeval/detectors/ood/mixin.py,sha256=0_o-1HPvgf3-Lf1MSOIfjj5UB8LTLEBGYtJJfyCCzwc,5431
 dataeval/metadata/__init__.py,sha256=XDDmJbOZBNM6pL0r6Nbu6oMRoyAh22IDkPYGndNlkZU,316
 dataeval/metadata/_distance.py,sha256=MbXM9idsooNWnGLaTKg8j4ZqavUeJUjuW7EPW3-UQyg,4234
@@ -46,11 +47,11 @@ dataeval/metadata/_ood.py,sha256=lNPHouj_9WfM_uTtsaiRaPn46RcVy3YebD1c32vDj-c,898
 dataeval/metadata/_utils.py,sha256=BcGoYVfA4AkAWpInY5txOc3QBpsGf6cnnUAsHOQTJAE,1210
 dataeval/metrics/__init__.py,sha256=8VC8q3HuJN3o_WN51Ae2_wXznl3RMXIvA5GYVcy7vr8,225
 dataeval/metrics/bias/__init__.py,sha256=329S1_3WnWqeU4-qVcbe0fMy4lDrj9uKslWHIQf93yg,839
-dataeval/metrics/bias/_balance.py,sha256=fREtoMLUZPOf_ivqNKwij6oPiKMTk02ECO5rWURf3KY,5541
+dataeval/metrics/bias/_balance.py,sha256=Yf0WNw9DxluFPNP-_wA1BcRRs-PRwocnHp0HScXS6t4,5719
 dataeval/metrics/bias/_completeness.py,sha256=2cvOXe7fhtxZGH_4QBuiCafIeamxFBarMiUBuEP7QGI,4596
 dataeval/metrics/bias/_coverage.py,sha256=v2x2hbOf2za9jFcSVSJUAoJ2BJfzzlCzt0mFIGtBL0A,3639
-dataeval/metrics/bias/_diversity.py,sha256=25udDKmel9IjeVT5nM4dOa1apda66QdRxBc922yuUvI,5830
-dataeval/metrics/bias/_parity.py,sha256=MKpqL4aoqEHkRl0vtGvVq9V3KBOtDFTtAo5I2GfIG4A,11443
+dataeval/metrics/bias/_diversity.py,sha256=Z7UQzKp9bsmB-hC3_sY6HIJUJRkLHb5cVEoU79cNDzc,5800
+dataeval/metrics/bias/_parity.py,sha256=ZIKc5OK6wQ4moleBJzGDfOPvyNzj03-KoHAGBZnO4pk,11433
 dataeval/metrics/estimators/__init__.py,sha256=Pnds8uIyAovt2fKqZjiHCIP_kVoBWlVllekYuK5UmmU,568
 dataeval/metrics/estimators/_ber.py,sha256=7noeRyOJJYqrJ_jt90nRHtR2t2u5MIvTCmWt0_rd4EU,5370
 dataeval/metrics/estimators/_clusterer.py,sha256=1HrpihGTJ63IkNSOy4Ibw633Gllkm1RxKmoKT5MOgt0,1434
@@ -60,7 +61,7 @@ dataeval/metrics/stats/__init__.py,sha256=6tA_9nbbM5ObJ6cds8Y1VBtTQiTOxrpGQSFLu_
 dataeval/metrics/stats/_base.py,sha256=R-hxoEPLreZcxYxBfyjbKfdoGMMTPiqJ5g2zSO-1UYM,12541
 dataeval/metrics/stats/_boxratiostats.py,sha256=ROZrlqgbowkGfCR5PJ5TL7Og40iMOdUqJnsCtaz_Xek,6450
 dataeval/metrics/stats/_dimensionstats.py,sha256=s2Juca8GG501nZd2SWL_YtXWkTfxUrUIAl53PO3_VeA,2876
-dataeval/metrics/stats/_hashstats.py,sha256=qa1CYRgOebkxqkALfffaPM-kJ074ZbyfpWbfOfuObSs,4758
+dataeval/metrics/stats/_hashstats.py,sha256=8C4EgzmBd3HMNsSATTriLVcvaWfoSasTLYizONqUDf4,5388
 dataeval/metrics/stats/_imagestats.py,sha256=gUPNgN5Zwzdr7WnSwbve1NXNsyxd5dy3cSnlR_7guCg,3007
 dataeval/metrics/stats/_labelstats.py,sha256=_dXt3p8_-SHEtHvJWbL0rnQvO2g30zxX42mG2LGJepU,3195
 dataeval/metrics/stats/_pixelstats.py,sha256=N9e7RXuzSHtlJtWU7l5IcTTIXe2kOmWiuj6lnJpZWq0,3312
@@ -75,31 +76,21 @@ dataeval/outputs/_metadata.py,sha256=ffZgpX8KWURPHXpOWjbvJ2KRqWQkS2nWuIjKUzoHhMI
 dataeval/outputs/_ood.py,sha256=suLKVXULGtXH0rq9eXHI1d3d2jhGmItJtz4QiQd47A4,1718
 dataeval/outputs/_stats.py,sha256=_ItGjs9YaMHqjivkR1YBcSErD5ICfa_-iV9nq0l8bTM,17451
 dataeval/outputs/_utils.py,sha256=NfhYaGT2PZlhIs8ICKUsPWHZXjhWYDkEJqBDdqMeaOM,929
-dataeval/outputs/_workflows.py,sha256=K786mOgegxVi81diUA-qpbwGEkwa8YA7Fk4ttgjJeaY,10831
-dataeval/utils/__init__.py,sha256=hRvyUK7b3d6JBEV5u47rFcOHEcmDYqAvZQw_T5pDAWw,264
+dataeval/outputs/_workflows.py,sha256=_0U9VzCvqLIOlxqpngPhmPcUZMk57bF9qnnrkLUMoGY,11450
+dataeval/utils/__init__.py,sha256=sjelzMPaTImF6isiRcp8UGDE3tppEpWS5GoR8WKPZ1k,242
 dataeval/utils/_array.py,sha256=bIDbnv15_hNzFn2Uc4WV1qRyFzubQj2nNYsFUDIdwT0,6335
-dataeval/utils/_bin.py,sha256=w3eJ2Szw5eapqQ0cGv731rhNgLFGW0cCz2pXo9I6CuY,7296
+dataeval/utils/_bin.py,sha256=KpAnhzLBgh6PxMlM9dPPvuic0S1KNKwlcM1Vg-d4dGI,7364
 dataeval/utils/_clusterer.py,sha256=rUvEdyMwp95lffmt6xKMEwsjRXNoBS0n5mAS_HNOnck,5656
 dataeval/utils/_fast_mst.py,sha256=pv42flr1Uf5RBa9qDG0YLDXWH7Mr7a9zpauO1HqZXaY,8061
 dataeval/utils/_image.py,sha256=4uxTIOYZZlRJOfNmdA3ek3no3FrLWCK5un48kStMDt8,3578
 dataeval/utils/_method.py,sha256=9B9JQbgqWJBRhQJb7glajUtWaQzUTIUuvrZ9_bisxsM,394
 dataeval/utils/_mst.py,sha256=bLmJmu_1Dtj3hC5gQp3oAiJ_7TKtEjahTqusVRRU4eI,2168
 dataeval/utils/_plot.py,sha256=1rnMkBRvTFLoTAHqXwF7c7GJ5_5iqlgarZKAzmYciLk,7225
-dataeval/utils/data/__init__.py,sha256=xGzrjrOxOP2DP1tU84AWMKPnSxFvSjM81CTlDg4rNM8,331
-dataeval/utils/data/_dataset.py,sha256=tC_vqgWnmojAoAANo5BUVfEUYXl7GzOBSeYjR9olbDk,9506
+dataeval/utils/data/__init__.py,sha256=AD7o2rllEdq4BVvlxljYKRXrXNer39XdGNuaRMbvH4Y,414
+dataeval/utils/data/_dataset.py,sha256=901qUUcLg_HPg07N5uNabAZ00MGFCdOr7o6VbIEk2_I,9870
+dataeval/utils/data/_validate.py,sha256=sea8B7DLbbxTqTjAQ5Vhs5XNRZWE5wBBqDgcKNVQBRA,6923
 dataeval/utils/data/collate.py,sha256=5egEEKhNNCGeNLChO1p6dZ4Wg6x51VEaMNHz7hEZUxI,3936
 dataeval/utils/data/metadata.py,sha256=L1c2bCiMj0aR0QCoKkjwBujIftJDEMgW_3ZbgeS8WHo,14703
-dataeval/utils/datasets/__init__.py,sha256=pAXqHX76yAoBI8XB3m6zGuW-u3s3PCoIXG5GDzxH7Zs,572
-dataeval/utils/datasets/_antiuav.py,sha256=kA_ia1fYNcJiz9SpCvh-Z8iSc7iJrdogjBI3soyaa7A,8304
-dataeval/utils/datasets/_base.py,sha256=pyfpJda3ku469M3TFRsJn9S2oAiQODOGTlLcdcoEW9U,9031
-dataeval/utils/datasets/_cifar10.py,sha256=hZc_A30yKYBbv2kvVdEkZ9egyEe6XBUnmksoIAoJ-5Y,8265
-dataeval/utils/datasets/_fileio.py,sha256=LEoFVNdryRdi7mKpWw-9D8lA6XMa-Jaszd85bv93POo,5454
-dataeval/utils/datasets/_milco.py,sha256=iXf4C1I3Eg_3gHKUe4XPi21yFMBO51zxTIqAkGf9bYg,7869
-dataeval/utils/datasets/_mixin.py,sha256=S8iii-SoYUsFFYNXjw2thlZkpBvRLnZ4XI8wTqOKXgU,1729
-dataeval/utils/datasets/_mnist.py,sha256=uz46sE1Go3TgGjG6x2cXckSVQ0mSg2mhgk8BUvLWjb0,8149
-dataeval/utils/datasets/_ships.py,sha256=6U04HAoM3jgLl1qv-NnxjZeSsBipcqWJBMhBMn5iIUY,5115
-dataeval/utils/datasets/_types.py,sha256=iSKyHXRlGuomXs0FHK6md8lXLQrQQ4fxgVOwr4o81bo,1089
-dataeval/utils/datasets/_voc.py,sha256=pafY112O80isYkrdy7Quie9SBm_TmYhREuyl8SxtsR0,24586
 dataeval/utils/torch/__init__.py,sha256=dn5mjCrFp0b1aL_UEURhONU0Ag0cmXoTOBSGagpkTiA,325
 dataeval/utils/torch/_blocks.py,sha256=HVhBTMMD5NA4qheMUgyol1KWiKZDIuc8k5j4RcMKmhk,1466
 dataeval/utils/torch/_gmm.py,sha256=XM68GNEP97EjaB1U49-ZXRb81d0CEFnPS910alrcB3g,3740
@@ -107,8 +98,8 @@ dataeval/utils/torch/_internal.py,sha256=9rzlMeM8i3p-ctulh9WDQATMXtlp-Jk2pBX7NGC
 dataeval/utils/torch/models.py,sha256=1idpXyjrYcCBSsbxxRUOto8xr4MJNjDEqQHiIXVU5Zc,9700
 dataeval/utils/torch/trainer.py,sha256=DRyPScGdE4o5Xo3BmD9p2PGOApzi1E-QfsBRNZ5IXW8,5544
 dataeval/workflows/__init__.py,sha256=ou8y0KO-d6W5lgmcyLjKlf-J_ckP3vilW7wHkgiDlZ4,255
-dataeval/workflows/sufficiency.py,sha256=j-R8dg4XE6a66p_oTXG2GNzgg3vGk85CTblxhFXaxog,8513
-dataeval-0.86.8.dist-info/METADATA,sha256=rCf58-uzgjsTNZkY3LOBMSi5fhQ2cdAtnrrDI_eYR_I,5925
-dataeval-0.86.8.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-dataeval-0.86.8.dist-info/licenses/LICENSE.txt,sha256=uAooygKWvX6NbU9Ran9oG2msttoG8aeTeHSTe5JeCnY,1061
-dataeval-0.86.8.dist-info/RECORD,,
+dataeval/workflows/sufficiency.py,sha256=UAPjowFrmM6IJJaOk9GkH3nfQTyDy2_zOY55o2g3G1M,10072
+dataeval-0.87.0.dist-info/METADATA,sha256=xhp28LbYD7FWbfhFfDgVzS_pi-E2TFgl-X33seCD2cE,5674
+dataeval-0.87.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+dataeval-0.87.0.dist-info/licenses/LICENSE,sha256=uAooygKWvX6NbU9Ran9oG2msttoG8aeTeHSTe5JeCnY,1061
+dataeval-0.87.0.dist-info/RECORD,,

dataeval/utils/datasets/__init__.py

@@ -1,19 +0,0 @@
-"""Provides access to common Computer Vision datasets."""
-
-from dataeval.utils.datasets._antiuav import AntiUAVDetection
-from dataeval.utils.datasets._cifar10 import CIFAR10
-from dataeval.utils.datasets._milco import MILCO
-from dataeval.utils.datasets._mnist import MNIST
-from dataeval.utils.datasets._ships import Ships
-from dataeval.utils.datasets._voc import VOCDetection, VOCDetectionTorch, VOCSegmentation
-
-__all__ = [
-    "MNIST",
-    "Ships",
-    "CIFAR10",
-    "AntiUAVDetection",
-    "MILCO",
-    "VOCDetection",
-    "VOCDetectionTorch",
-    "VOCSegmentation",
-]

dataeval/utils/datasets/_antiuav.py

@@ -1,189 +0,0 @@
-from __future__ import annotations
-
-__all__ = []
-
-from pathlib import Path
-from typing import TYPE_CHECKING, Any, Literal, Sequence
-
-from defusedxml.ElementTree import parse
-from numpy.typing import NDArray
-
-from dataeval.utils.datasets._base import BaseODDataset, DataLocation
-from dataeval.utils.datasets._mixin import BaseDatasetNumpyMixin
-
-if TYPE_CHECKING:
-    from dataeval.typing import Transform
-
-
-class AntiUAVDetection(BaseODDataset[NDArray[Any]], BaseDatasetNumpyMixin):
-    """
-    A UAV detection dataset focused on detecting UAVs in natural images against large variation in backgrounds.
-
-    The dataset comes from the paper
-    `Vision-based Anti-UAV Detection and Tracking <https://ieeexplore.ieee.org/document/9785379>`_
-    by Jie Zhao et. al. (2022).
-
-    The dataset is approximately 1.3 GB and can be found `here <https://github.com/wangdongdut/DUT-Anti-UAV>`_.
-    Images are collected against a variety of different backgrounds with a variety in the number and type of UAV.
-    Ground truth labels are provided for the train, validation and test set.
-    There are 35 different types of drones along with a variety in lighting conditions and weather conditions.
-
-    There are 10,000 images: 5200 images in the training set, 2200 images in the validation set,
-    and 2600 images in the test set.
-    The dataset only has a single UAV class with the focus being on identifying object location in the image.
-    Ground-truth bounding boxes are provided in (x0, y0, x1, y1) format.
-    The images come in a variety of sizes from 3744 x 5616 to 160 x 240.
-
-    Parameters
-    ----------
-    root : str or pathlib.Path
-        Root directory where the data should be downloaded to or
-        the ``antiuavdetection`` folder of the already downloaded data.
-    image_set: "train", "val", "test", or "base", default "train"
-        If "base", then the full dataset is selected (train, val and test).
-    transforms : Transform, Sequence[Transform] or None, default None
-        Transform(s) to apply to the data.
-    download : bool, default False
-        If True, downloads the dataset from the internet and puts it in root directory.
-        Class checks to see if data is already downloaded to ensure it does not create a duplicate download.
-    verbose : bool, default False
-        If True, outputs print statements.
-
-    Attributes
-    ----------
-    path : pathlib.Path
-        Location of the folder containing the data.
-    image_set : "train", "val", "test", or "base"
-        The selected image set from the dataset.
-    index2label : dict[int, str]
-        Dictionary which translates from class integers to the associated class strings.
-    label2index : dict[str, int]
-        Dictionary which translates from class strings to the associated class integers.
-    metadata : DatasetMetadata
-        Typed dictionary containing dataset metadata, such as `id` which returns the dataset class name.
-    transforms : Sequence[Transform]
-        The transforms to be applied to the data.
-    size : int
-        The size of the dataset.
-
-    Note
-    ----
-    Data License: `Apache 2.0 <https://www.apache.org/licenses/LICENSE-2.0.txt>`_
-    """
-
-    # Need to run the sha256 on the files and then store that
-    _resources = [
-        DataLocation(
-            url="https://drive.usercontent.google.com/download?id=1RVsSGPUKTdmoyoPTBTWwroyulLek1eTj&export=download&authuser=0&confirm=t&uuid=6bca4f94-a242-4bc2-9663-fb03cd94ef2c&at=APcmpox0--NroQ_3bqeTFaJxP7Pw%3A1746552902927",
-            filename="train.zip",
-            md5=False,
-            checksum="14f927290556df60e23cedfa80dffc10dc21e4a3b6843e150cfc49644376eece",
-        ),
-        DataLocation(
-            url="https://drive.usercontent.google.com/download?id=1333uEQfGuqTKslRkkeLSCxylh6AQ0X6n&export=download&authuser=0&confirm=t&uuid=c2ad2f01-aca8-4a85-96bb-b8ef6e40feea&at=APcmpozY-8bhk3nZSFaYbE8rq1Fi%3A1746551543297",
-            filename="val.zip",
-            md5=False,
-            checksum="238be0ceb3e7c5be6711ee3247e49df2750d52f91f54f5366c68bebac112ebf8",
-        ),
-        DataLocation(
-            url="https://drive.usercontent.google.com/download?id=1L1zeW1EMDLlXHClSDcCjl3rs_A6sVai0&export=download&authuser=0&confirm=t&uuid=5a1d7650-d8cd-4461-8354-7daf7292f06c&at=APcmpozLQC1CuP-n5_UX2JnP53Zo%3A1746551676177",
-            filename="test.zip",
-            md5=False,
-            checksum="a671989a01cff98c684aeb084e59b86f4152c50499d86152eb970a9fc7fb1cbe",
-        ),
-    ]
-
-    index2label: dict[int, str] = {
-        0: "unknown",
-        1: "UAV",
-    }
-
-    def __init__(
-        self,
-        root: str | Path,
-        image_set: Literal["train", "val", "test", "base"] = "train",
-        transforms: Transform[NDArray[Any]] | Sequence[Transform[NDArray[Any]]] | None = None,
-        download: bool = False,
-        verbose: bool = False,
-    ) -> None:
-        super().__init__(
-            root,
-            image_set,
-            transforms,
-            download,
-            verbose,
-        )
-
-    def _load_data(self) -> tuple[list[str], list[str], dict[str, list[Any]]]:
-        filepaths: list[str] = []
-        targets: list[str] = []
-        datum_metadata: dict[str, list[Any]] = {}
-
-        # If base, load all resources
-        if self.image_set == "base":
-            metadata_list: list[dict[str, Any]] = []
-
-            for resource in self._resources:
-                self._resource = resource
-                resource_filepaths, resource_targets, resource_metadata = super()._load_data()
-                filepaths.extend(resource_filepaths)
-                targets.extend(resource_targets)
-                metadata_list.append(resource_metadata)
-
-            # Combine metadata
-            for data_dict in metadata_list:
-                for key, val in data_dict.items():
-                    str_key = str(key)  # Ensure key is string
-                    if str_key not in datum_metadata:
-                        datum_metadata[str_key] = []
-                    datum_metadata[str_key].extend(val)
-
-        else:
-            # Grab only the desired data
-            for resource in self._resources:
-                if self.image_set in resource.filename:
-                    self._resource = resource
-                    resource_filepaths, resource_targets, resource_metadata = super()._load_data()
-                    filepaths.extend(resource_filepaths)
-                    targets.extend(resource_targets)
-                    datum_metadata.update(resource_metadata)
-
-        return filepaths, targets, datum_metadata
-
-    def _load_data_inner(self) -> tuple[list[str], list[str], dict[str, Any]]:
-        resource_name = self._resource.filename[:-4]
-        base_dir = self.path / resource_name
-        data_folder = sorted((base_dir / "img").glob("*.jpg"))
-        if not data_folder:
-            raise FileNotFoundError
-
-        file_data = {"image_id": [f"{resource_name}_{entry.name}" for entry in data_folder]}
-        data = [str(entry) for entry in data_folder]
-        annotations = sorted(str(entry) for entry in (base_dir / "xml").glob("*.xml"))
-
-        return data, annotations, file_data
-
-    def _read_annotations(self, annotation: str) -> tuple[list[list[float]], list[int], dict[str, Any]]:
-        """Function for extracting the info for the label and boxes"""
-        boxes: list[list[float]] = []
-        labels = []
-        root = parse(annotation).getroot()
-        if root is None:
-            raise ValueError(f"Unable to parse {annotation}")
-        additional_meta: dict[str, Any] = {
-            "image_width": int(root.findtext("size/width", default="-1")),
-            "image_height": int(root.findtext("size/height", default="-1")),
-            "image_depth": int(root.findtext("size/depth", default="-1")),
-        }
-        for obj in root.findall("object"):
-            labels.append(1 if obj.findtext("name", default="") == "UAV" else 0)
-            boxes.append(
-                [
-                    float(obj.findtext("bndbox/xmin", default="0")),
-                    float(obj.findtext("bndbox/ymin", default="0")),
-                    float(obj.findtext("bndbox/xmax", default="0")),
-                    float(obj.findtext("bndbox/ymax", default="0")),
-                ]
-            )
-
-        return boxes, labels, additional_meta

dataeval/utils/datasets/_base.py

@@ -1,262 +0,0 @@
-from __future__ import annotations
-
-__all__ = []
-
-from abc import abstractmethod
-from pathlib import Path
-from typing import TYPE_CHECKING, Any, Generic, Iterator, Literal, NamedTuple, Sequence, TypeVar
-
-import numpy as np
-
-from dataeval.utils.datasets._fileio import _ensure_exists
-from dataeval.utils.datasets._mixin import BaseDatasetMixin
-from dataeval.utils.datasets._types import (
-    AnnotatedDataset,
-    DatasetMetadata,
-    ImageClassificationDataset,
-    ObjectDetectionDataset,
-    ObjectDetectionTarget,
-    SegmentationDataset,
-    SegmentationTarget,
-)
-
-if TYPE_CHECKING:
-    from dataeval.typing import Array, Transform
-
-    _TArray = TypeVar("_TArray", bound=Array)
-else:
-    _TArray = TypeVar("_TArray")
-
-_TTarget = TypeVar("_TTarget")
-_TRawTarget = TypeVar("_TRawTarget", list[int], list[str])
-
-
-class DataLocation(NamedTuple):
-    url: str
-    filename: str
-    md5: bool
-    checksum: str
-
-
-class BaseDataset(AnnotatedDataset[tuple[_TArray, _TTarget, dict[str, Any]]], Generic[_TArray, _TTarget, _TRawTarget]):
-    """
-    Base class for internet downloaded datasets.
-    """
-
-    # Each subclass should override the attributes below.
-    # Each resource tuple must contain:
-    #    'url': str, the URL to download from
-    #    'filename': str, the name of the file once downloaded
-    #    'md5': boolean, True if it's the checksum value is md5
-    #    'checksum': str, the associated checksum for the downloaded file
-    _resources: list[DataLocation]
-    _resource_index: int = 0
-    index2label: dict[int, str]
-
-    def __init__(
-        self,
-        root: str | Path,
-        image_set: Literal["train", "val", "test", "operational", "base"] = "train",
-        transforms: Transform[_TArray] | Sequence[Transform[_TArray]] | None = None,
-        download: bool = False,
-        verbose: bool = False,
-    ) -> None:
-        self._root: Path = root.absolute() if isinstance(root, Path) else Path(root).absolute()
-        transforms = transforms if transforms is not None else []
-        self.transforms: Sequence[Transform[_TArray]] = transforms if isinstance(transforms, Sequence) else [transforms]
-        self.image_set = image_set
-        self._verbose = verbose
-
-        # Internal Attributes
-        self._download = download
-        self._filepaths: list[str]
-        self._targets: _TRawTarget
-        self._datum_metadata: dict[str, list[Any]]
-        self._resource: DataLocation = self._resources[self._resource_index]
-        self._label2index = {v: k for k, v in self.index2label.items()}
-
-        self.metadata: DatasetMetadata = DatasetMetadata(
-            id=self._unique_id(),
-            index2label=self.index2label,
-            split=self.image_set,
-        )
-
-        # Load the data
-        self.path: Path = self._get_dataset_dir()
-        self._filepaths, self._targets, self._datum_metadata = self._load_data()
-        self.size: int = len(self._filepaths)
-
-    def __str__(self) -> str:
-        nt = "\n    "
-        title = f"{self.__class__.__name__} Dataset"
-        sep = "-" * len(title)
-        attrs = [f"{k.capitalize()}: {v}" for k, v in self.__dict__.items() if not k.startswith("_")]
-        return f"{title}\n{sep}{nt}{nt.join(attrs)}"
-
-    @property
-    def label2index(self) -> dict[str, int]:
-        return self._label2index
-
-    def __iter__(self) -> Iterator[tuple[_TArray, _TTarget, dict[str, Any]]]:
-        for i in range(len(self)):
-            yield self[i]
-
-    def _get_dataset_dir(self) -> Path:
-        # Create a designated folder for this dataset (named after the class)
-        if self._root.stem.lower() == self.__class__.__name__.lower():
-            dataset_dir: Path = self._root
-        else:
-            dataset_dir: Path = self._root / self.__class__.__name__.lower()
-        if not dataset_dir.exists():
-            dataset_dir.mkdir(parents=True, exist_ok=True)
-        return dataset_dir
-
-    def _unique_id(self) -> str:
-        return f"{self.__class__.__name__}_{self.image_set}"
-
-    def _load_data(self) -> tuple[list[str], _TRawTarget, dict[str, Any]]:
-        """
-        Function to determine if data can be accessed or if it needs to be downloaded and/or extracted.
-        """
-        if self._verbose:
-            print(f"Determining if {self._resource.filename} needs to be downloaded.")
-
-        try:
-            result = self._load_data_inner()
-            if self._verbose:
-                print("No download needed, loaded data successfully.")
-        except FileNotFoundError:
-            _ensure_exists(*self._resource, self.path, self._root, self._download, self._verbose)
-            result = self._load_data_inner()
-        return result
-
-    @abstractmethod
-    def _load_data_inner(self) -> tuple[list[str], _TRawTarget, dict[str, Any]]: ...
-
-    def _transform(self, image: _TArray) -> _TArray:
-        """Function to transform the image prior to returning based on parameters passed in."""
-        for transform in self.transforms:
-            image = transform(image)
-        return image
-
-    def __len__(self) -> int:
-        return self.size
-
-
-class BaseICDataset(
-    BaseDataset[_TArray, _TArray, list[int]],
-    BaseDatasetMixin[_TArray],
-    ImageClassificationDataset[_TArray],
-):
-    """
-    Base class for image classification datasets.
-    """
-
-    def __getitem__(self, index: int) -> tuple[_TArray, _TArray, dict[str, Any]]:
-        """
-        Args
-        ----
-        index : int
-            Value of the desired data point
-
-        Returns
-        -------
-        tuple[TArray, TArray, dict[str, Any]]
-            Image, target, datum_metadata - where target is one-hot encoding of class.
-        """
-        # Get the associated label and score
-        label = self._targets[index]
-        score = self._one_hot_encode(label)
-        # Get the image
-        img = self._read_file(self._filepaths[index])
-        img = self._transform(img)
-
-        img_metadata = {key: val[index] for key, val in self._datum_metadata.items()}
-
-        return img, score, img_metadata
-
-
-class BaseODDataset(
-    BaseDataset[_TArray, ObjectDetectionTarget[_TArray], list[str]],
-    BaseDatasetMixin[_TArray],
-    ObjectDetectionDataset[_TArray],
-):
-    """
-    Base class for object detection datasets.
-    """
-
-    _bboxes_per_size: bool = False
-
-    def __getitem__(self, index: int) -> tuple[_TArray, ObjectDetectionTarget[_TArray], dict[str, Any]]:
-        """
-        Args
-        ----
-        index : int
-            Value of the desired data point
-
-        Returns
-        -------
-        tuple[TArray, ObjectDetectionTarget[TArray], dict[str, Any]]
-            Image, target, datum_metadata - target.boxes returns boxes in x0, y0, x1, y1 format
-        """
-        # Grab the bounding boxes and labels from the annotations
-        boxes, labels, additional_metadata = self._read_annotations(self._targets[index])
-        # Get the image
-        img = self._read_file(self._filepaths[index])
-        img_size = img.shape
-        img = self._transform(img)
-        # Adjust labels if necessary
-        if self._bboxes_per_size and boxes:
-            boxes = boxes * np.array([[img_size[1], img_size[2], img_size[1], img_size[2]]])
-        # Create the Object Detection Target
-        target = ObjectDetectionTarget(self._as_array(boxes), self._as_array(labels), self._one_hot_encode(labels))
-
-        img_metadata = {key: val[index] for key, val in self._datum_metadata.items()}
-        img_metadata = img_metadata | additional_metadata
-
-        return img, target, img_metadata
-
-    @abstractmethod
-    def _read_annotations(self, annotation: str) -> tuple[list[list[float]], list[int], dict[str, Any]]: ...
-
-
-class BaseSegDataset(
-    BaseDataset[_TArray, SegmentationTarget[_TArray], list[str]],
-    BaseDatasetMixin[_TArray],
-    SegmentationDataset[_TArray],
-):
-    """
-    Base class for segmentation datasets.
-    """
-
-    _masks: Sequence[str]
-
-    def __getitem__(self, index: int) -> tuple[_TArray, SegmentationTarget[_TArray], dict[str, Any]]:
-        """
-        Args
-        ----
-        index : int
-            Value of the desired data point
-
-        Returns
-        -------
-        tuple[TArray, SegmentationTarget[TArray], dict[str, Any]]
-            Image, target, datum_metadata - target.mask returns the ground truth mask
-        """
-        # Grab the labels from the annotations
-        _, labels, additional_metadata = self._read_annotations(self._targets[index])
-        # Grab the ground truth masks
-        mask = self._read_file(self._masks[index])
-        # Get the image
-        img = self._read_file(self._filepaths[index])
-        img = self._transform(img)
-
-        target = SegmentationTarget(mask, self._as_array(labels), self._one_hot_encode(labels))
-
-        img_metadata = {key: val[index] for key, val in self._datum_metadata.items()}
-        img_metadata = img_metadata | additional_metadata
-
-        return img, target, img_metadata
-
-    @abstractmethod
-    def _read_annotations(self, annotation: str) -> tuple[list[list[float]], list[int], dict[str, Any]]: ...