ultralytics 8.2.0__tar.gz → 8.2.1__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.

This version of ultralytics might be problematic. Click here for more details.

Files changed (217) hide show
  1. {ultralytics-8.2.0/ultralytics.egg-info → ultralytics-8.2.1}/PKG-INFO +34 -34
  2. {ultralytics-8.2.0 → ultralytics-8.2.1}/README.md +33 -33
  3. {ultralytics-8.2.0 → ultralytics-8.2.1}/tests/test_integrations.py +1 -1
  4. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/__init__.py +1 -1
  5. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/engine/exporter.py +2 -0
  6. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/engine/trainer.py +3 -0
  7. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/classify/val.py +2 -2
  8. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/downloads.py +2 -2
  9. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/torch_utils.py +2 -0
  10. {ultralytics-8.2.0 → ultralytics-8.2.1/ultralytics.egg-info}/PKG-INFO +34 -34
  11. {ultralytics-8.2.0 → ultralytics-8.2.1}/LICENSE +0 -0
  12. {ultralytics-8.2.0 → ultralytics-8.2.1}/pyproject.toml +0 -0
  13. {ultralytics-8.2.0 → ultralytics-8.2.1}/setup.cfg +0 -0
  14. {ultralytics-8.2.0 → ultralytics-8.2.1}/tests/test_cli.py +0 -0
  15. {ultralytics-8.2.0 → ultralytics-8.2.1}/tests/test_cuda.py +0 -0
  16. {ultralytics-8.2.0 → ultralytics-8.2.1}/tests/test_engine.py +0 -0
  17. {ultralytics-8.2.0 → ultralytics-8.2.1}/tests/test_explorer.py +0 -0
  18. {ultralytics-8.2.0 → ultralytics-8.2.1}/tests/test_python.py +0 -0
  19. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/assets/bus.jpg +0 -0
  20. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/assets/zidane.jpg +0 -0
  21. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/__init__.py +0 -0
  22. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/Argoverse.yaml +0 -0
  23. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/DOTAv1.5.yaml +0 -0
  24. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/DOTAv1.yaml +0 -0
  25. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/GlobalWheat2020.yaml +0 -0
  26. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/ImageNet.yaml +0 -0
  27. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/Objects365.yaml +0 -0
  28. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/SKU-110K.yaml +0 -0
  29. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/VOC.yaml +0 -0
  30. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/VisDrone.yaml +0 -0
  31. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/african-wildlife.yaml +0 -0
  32. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/brain-tumor.yaml +0 -0
  33. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/carparts-seg.yaml +0 -0
  34. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/coco-pose.yaml +0 -0
  35. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/coco.yaml +0 -0
  36. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/coco128-seg.yaml +0 -0
  37. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/coco128.yaml +0 -0
  38. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/coco8-pose.yaml +0 -0
  39. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/coco8-seg.yaml +0 -0
  40. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/coco8.yaml +0 -0
  41. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/crack-seg.yaml +0 -0
  42. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/dota8.yaml +0 -0
  43. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/lvis.yaml +0 -0
  44. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/open-images-v7.yaml +0 -0
  45. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/package-seg.yaml +0 -0
  46. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/tiger-pose.yaml +0 -0
  47. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/datasets/xView.yaml +0 -0
  48. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/default.yaml +0 -0
  49. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/rt-detr/rtdetr-l.yaml +0 -0
  50. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/rt-detr/rtdetr-resnet101.yaml +0 -0
  51. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/rt-detr/rtdetr-resnet50.yaml +0 -0
  52. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/rt-detr/rtdetr-x.yaml +0 -0
  53. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v3/yolov3-spp.yaml +0 -0
  54. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v3/yolov3-tiny.yaml +0 -0
  55. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v3/yolov3.yaml +0 -0
  56. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v5/yolov5-p6.yaml +0 -0
  57. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v5/yolov5.yaml +0 -0
  58. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v6/yolov6.yaml +0 -0
  59. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v8/yolov8-cls-resnet101.yaml +0 -0
  60. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v8/yolov8-cls-resnet50.yaml +0 -0
  61. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v8/yolov8-cls.yaml +0 -0
  62. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v8/yolov8-ghost-p2.yaml +0 -0
  63. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v8/yolov8-ghost-p6.yaml +0 -0
  64. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v8/yolov8-ghost.yaml +0 -0
  65. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v8/yolov8-obb.yaml +0 -0
  66. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v8/yolov8-p2.yaml +0 -0
  67. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v8/yolov8-p6.yaml +0 -0
  68. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v8/yolov8-pose-p6.yaml +0 -0
  69. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v8/yolov8-pose.yaml +0 -0
  70. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v8/yolov8-rtdetr.yaml +0 -0
  71. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v8/yolov8-seg-p6.yaml +0 -0
  72. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v8/yolov8-seg.yaml +0 -0
  73. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v8/yolov8-world.yaml +0 -0
  74. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v8/yolov8-worldv2.yaml +0 -0
  75. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v8/yolov8.yaml +0 -0
  76. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v9/yolov9c-seg.yaml +0 -0
  77. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v9/yolov9c.yaml +0 -0
  78. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v9/yolov9e-seg.yaml +0 -0
  79. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/models/v9/yolov9e.yaml +0 -0
  80. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/trackers/botsort.yaml +0 -0
  81. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/cfg/trackers/bytetrack.yaml +0 -0
  82. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/data/__init__.py +0 -0
  83. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/data/annotator.py +0 -0
  84. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/data/augment.py +0 -0
  85. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/data/base.py +0 -0
  86. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/data/build.py +0 -0
  87. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/data/converter.py +0 -0
  88. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/data/dataset.py +0 -0
  89. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/data/explorer/__init__.py +0 -0
  90. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/data/explorer/explorer.py +0 -0
  91. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/data/explorer/gui/__init__.py +0 -0
  92. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/data/explorer/gui/dash.py +0 -0
  93. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/data/explorer/utils.py +0 -0
  94. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/data/loaders.py +0 -0
  95. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/data/split_dota.py +0 -0
  96. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/data/utils.py +0 -0
  97. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/engine/__init__.py +0 -0
  98. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/engine/model.py +0 -0
  99. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/engine/predictor.py +0 -0
  100. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/engine/results.py +0 -0
  101. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/engine/tuner.py +0 -0
  102. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/engine/validator.py +0 -0
  103. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/hub/__init__.py +0 -0
  104. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/hub/auth.py +0 -0
  105. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/hub/session.py +0 -0
  106. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/hub/utils.py +0 -0
  107. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/__init__.py +0 -0
  108. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/fastsam/__init__.py +0 -0
  109. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/fastsam/model.py +0 -0
  110. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/fastsam/predict.py +0 -0
  111. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/fastsam/prompt.py +0 -0
  112. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/fastsam/utils.py +0 -0
  113. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/fastsam/val.py +0 -0
  114. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/nas/__init__.py +0 -0
  115. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/nas/model.py +0 -0
  116. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/nas/predict.py +0 -0
  117. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/nas/val.py +0 -0
  118. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/rtdetr/__init__.py +0 -0
  119. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/rtdetr/model.py +0 -0
  120. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/rtdetr/predict.py +0 -0
  121. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/rtdetr/train.py +0 -0
  122. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/rtdetr/val.py +0 -0
  123. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/sam/__init__.py +0 -0
  124. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/sam/amg.py +0 -0
  125. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/sam/build.py +0 -0
  126. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/sam/model.py +0 -0
  127. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/sam/modules/__init__.py +0 -0
  128. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/sam/modules/decoders.py +0 -0
  129. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/sam/modules/encoders.py +0 -0
  130. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/sam/modules/sam.py +0 -0
  131. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/sam/modules/tiny_encoder.py +0 -0
  132. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/sam/modules/transformer.py +0 -0
  133. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/sam/predict.py +0 -0
  134. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/utils/__init__.py +0 -0
  135. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/utils/loss.py +0 -0
  136. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/utils/ops.py +0 -0
  137. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/__init__.py +0 -0
  138. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/classify/__init__.py +0 -0
  139. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/classify/predict.py +0 -0
  140. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/classify/train.py +0 -0
  141. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/detect/__init__.py +0 -0
  142. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/detect/predict.py +0 -0
  143. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/detect/train.py +0 -0
  144. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/detect/val.py +0 -0
  145. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/model.py +0 -0
  146. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/obb/__init__.py +0 -0
  147. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/obb/predict.py +0 -0
  148. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/obb/train.py +0 -0
  149. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/obb/val.py +0 -0
  150. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/pose/__init__.py +0 -0
  151. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/pose/predict.py +0 -0
  152. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/pose/train.py +0 -0
  153. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/pose/val.py +0 -0
  154. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/segment/__init__.py +0 -0
  155. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/segment/predict.py +0 -0
  156. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/segment/train.py +0 -0
  157. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/segment/val.py +0 -0
  158. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/world/__init__.py +0 -0
  159. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/world/train.py +0 -0
  160. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/world/train_world.py +0 -0
  161. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/nn/__init__.py +0 -0
  162. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/nn/autobackend.py +0 -0
  163. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/nn/modules/__init__.py +0 -0
  164. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/nn/modules/block.py +0 -0
  165. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/nn/modules/conv.py +0 -0
  166. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/nn/modules/head.py +0 -0
  167. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/nn/modules/transformer.py +0 -0
  168. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/nn/modules/utils.py +0 -0
  169. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/nn/tasks.py +0 -0
  170. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/solutions/__init__.py +0 -0
  171. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/solutions/ai_gym.py +0 -0
  172. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/solutions/distance_calculation.py +0 -0
  173. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/solutions/heatmap.py +0 -0
  174. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/solutions/object_counter.py +0 -0
  175. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/solutions/queue_management.py +0 -0
  176. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/solutions/speed_estimation.py +0 -0
  177. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/trackers/__init__.py +0 -0
  178. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/trackers/basetrack.py +0 -0
  179. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/trackers/bot_sort.py +0 -0
  180. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/trackers/byte_tracker.py +0 -0
  181. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/trackers/track.py +0 -0
  182. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/trackers/utils/__init__.py +0 -0
  183. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/trackers/utils/gmc.py +0 -0
  184. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/trackers/utils/kalman_filter.py +0 -0
  185. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/trackers/utils/matching.py +0 -0
  186. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/__init__.py +0 -0
  187. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/autobatch.py +0 -0
  188. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/benchmarks.py +0 -0
  189. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/callbacks/__init__.py +0 -0
  190. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/callbacks/base.py +0 -0
  191. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/callbacks/clearml.py +0 -0
  192. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/callbacks/comet.py +0 -0
  193. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/callbacks/dvc.py +0 -0
  194. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/callbacks/hub.py +0 -0
  195. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/callbacks/mlflow.py +0 -0
  196. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/callbacks/neptune.py +0 -0
  197. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/callbacks/raytune.py +0 -0
  198. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/callbacks/tensorboard.py +0 -0
  199. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/callbacks/wb.py +0 -0
  200. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/checks.py +0 -0
  201. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/dist.py +0 -0
  202. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/errors.py +0 -0
  203. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/files.py +0 -0
  204. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/instance.py +0 -0
  205. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/loss.py +0 -0
  206. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/metrics.py +0 -0
  207. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/ops.py +0 -0
  208. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/patches.py +0 -0
  209. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/plotting.py +0 -0
  210. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/tal.py +0 -0
  211. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/triton.py +0 -0
  212. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/tuner.py +0 -0
  213. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics.egg-info/SOURCES.txt +0 -0
  214. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics.egg-info/dependency_links.txt +0 -0
  215. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics.egg-info/entry_points.txt +0 -0
  216. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics.egg-info/requires.txt +0 -0
  217. {ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics.egg-info/top_level.txt +0 -0
{ultralytics-8.2.0/ultralytics.egg-info → ultralytics-8.2.1}/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: ultralytics
3
- Version: 8.2.0
3
+ Version: 8.2.1
4
4
  Summary: Ultralytics YOLOv8 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
5
5
  Author: Glenn Jocher, Ayush Chaurasia, Jing Qiu
6
6
  Maintainer: Glenn Jocher, Ayush Chaurasia, Jing Qiu
@@ -80,8 +80,8 @@ Requires-Dist: pycocotools>=2.0.7; extra == "extra"
80
80
 
81
81
  <div align="center">
82
82
  <p>
83
- <a href="https://www.ultralytics.com/blog/ultralytics-yolov8-turns-one-a-year-of-breakthroughs-and-innovations" target="_blank">
84
- <img width="100%" src="https://raw.githubusercontent.com/ultralytics/assets/main/im/banner-yolo-vision-2023.png" alt="YOLO Vision banner"></a>
83
+ <a href="https://github.com/ultralytics/assets/releases/tag/v8.2.0" target="_blank">
84
+ <img width="100%" src="https://raw.githubusercontent.com/ultralytics/assets/main/yolov8/banner-yolov8.png" alt="YOLO Vision banner"></a>
85
85
  </p>
86
86
 
87
87
  [中文](https://docs.ultralytics.com/zh/) | [한국어](https://docs.ultralytics.com/ko/) | [日本語](https://docs.ultralytics.com/ja/) | [Русский](https://docs.ultralytics.com/ru/) | [Deutsch](https://docs.ultralytics.com/de/) | [Français](https://docs.ultralytics.com/fr/) | [Español](https://docs.ultralytics.com/es/) | [Português](https://docs.ultralytics.com/pt/) | [हिन्दी](https://docs.ultralytics.com/hi/) | [العربية](https://docs.ultralytics.com/ar/) <br>
@@ -205,11 +205,11 @@ See [Detection Docs](https://docs.ultralytics.com/tasks/detect/) for usage examp
205
205
 
206
206
  | Model | size<br><sup>(pixels) | mAP<sup>val<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
207
207
  | ------------------------------------------------------------------------------------ | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
208
- | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
209
- | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
210
- | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
211
- | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
212
- | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
208
+ | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
209
+ | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
210
+ | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
211
+ | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
212
+ | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
213
213
 
214
214
  - **mAP<sup>val</sup>** values are for single-model single-scale on [COCO val2017](https://cocodataset.org) dataset. <br>Reproduce by `yolo val detect data=coco.yaml device=0`
215
215
  - **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val detect data=coco.yaml batch=1 device=0|cpu`
@@ -222,11 +222,11 @@ See [Detection Docs](https://docs.ultralytics.com/tasks/detect/) for usage examp
222
222
 
223
223
  | Model | size<br><sup>(pixels) | mAP<sup>val<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
224
224
  | ----------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
225
- | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 |
226
- | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 |
227
- | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 |
228
- | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 |
229
- | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 |
225
+ | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 |
226
+ | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 |
227
+ | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 |
228
+ | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 |
229
+ | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 |
230
230
 
231
231
  - **mAP<sup>val</sup>** values are for single-model single-scale on [Open Image V7](https://docs.ultralytics.com/datasets/detect/open-images-v7/) dataset. <br>Reproduce by `yolo val detect data=open-images-v7.yaml device=0`
232
232
  - **Speed** averaged over Open Image V7 val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val detect data=open-images-v7.yaml batch=1 device=0|cpu`
@@ -239,11 +239,11 @@ See [Segmentation Docs](https://docs.ultralytics.com/tasks/segment/) for usage e
239
239
 
240
240
  | Model | size<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
241
241
  | -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
242
- | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
243
- | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
244
- | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
245
- | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
246
- | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
242
+ | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
243
+ | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
244
+ | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
245
+ | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
246
+ | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
247
247
 
248
248
  - **mAP<sup>val</sup>** values are for single-model single-scale on [COCO val2017](https://cocodataset.org) dataset. <br>Reproduce by `yolo val segment data=coco-seg.yaml device=0`
249
249
  - **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val segment data=coco-seg.yaml batch=1 device=0|cpu`
@@ -256,12 +256,12 @@ See [Pose Docs](https://docs.ultralytics.com/tasks/pose/) for usage examples wit
256
256
 
257
257
  | Model | size<br><sup>(pixels) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
258
258
  | ---------------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
259
- | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
260
- | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
261
- | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
262
- | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
263
- | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
264
- | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
259
+ | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
260
+ | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
261
+ | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
262
+ | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
263
+ | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
264
+ | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
265
265
 
266
266
  - **mAP<sup>val</sup>** values are for single-model single-scale on [COCO Keypoints val2017](https://cocodataset.org) dataset. <br>Reproduce by `yolo val pose data=coco-pose.yaml device=0`
267
267
  - **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val pose data=coco-pose.yaml batch=1 device=0|cpu`
@@ -274,11 +274,11 @@ See [OBB Docs](https://docs.ultralytics.com/tasks/obb/) for usage examples with
274
274
 
275
275
  | Model | size<br><sup>(pixels) | mAP<sup>test<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
276
276
  | -------------------------------------------------------------------------------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
277
- | [YOLOv8n-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-obb.pt) | 1024 | 78.0 | 204.77 | 3.57 | 3.1 | 23.3 |
278
- | [YOLOv8s-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-obb.pt) | 1024 | 79.5 | 424.88 | 4.07 | 11.4 | 76.3 |
279
- | [YOLOv8m-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-obb.pt) | 1024 | 80.5 | 763.48 | 7.61 | 26.4 | 208.6 |
280
- | [YOLOv8l-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-obb.pt) | 1024 | 80.7 | 1278.42 | 11.83 | 44.5 | 433.8 |
281
- | [YOLOv8x-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-obb.pt) | 1024 | 81.36 | 1759.10 | 13.23 | 69.5 | 676.7 |
277
+ | [YOLOv8n-obb](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n-obb.pt) | 1024 | 78.0 | 204.77 | 3.57 | 3.1 | 23.3 |
278
+ | [YOLOv8s-obb](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8s-obb.pt) | 1024 | 79.5 | 424.88 | 4.07 | 11.4 | 76.3 |
279
+ | [YOLOv8m-obb](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8m-obb.pt) | 1024 | 80.5 | 763.48 | 7.61 | 26.4 | 208.6 |
280
+ | [YOLOv8l-obb](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8l-obb.pt) | 1024 | 80.7 | 1278.42 | 11.83 | 44.5 | 433.8 |
281
+ | [YOLOv8x-obb](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8x-obb.pt) | 1024 | 81.36 | 1759.10 | 13.23 | 69.5 | 676.7 |
282
282
 
283
283
  - **mAP<sup>test</sup>** values are for single-model multiscale on [DOTAv1](https://captain-whu.github.io/DOTA/index.html) dataset. <br>Reproduce by `yolo val obb data=DOTAv1.yaml device=0 split=test` and submit merged results to [DOTA evaluation](https://captain-whu.github.io/DOTA/evaluation.html).
284
284
  - **Speed** averaged over DOTAv1 val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val obb data=DOTAv1.yaml batch=1 device=0|cpu`
@@ -291,11 +291,11 @@ See [Classification Docs](https://docs.ultralytics.com/tasks/classify/) for usag
291
291
 
292
292
  | Model | size<br><sup>(pixels) | acc<br><sup>top1 | acc<br><sup>top5 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) at 640 |
293
293
  | -------------------------------------------------------------------------------------------- | --------------------- | ---------------- | ---------------- | ------------------------------ | ----------------------------------- | ------------------ | ------------------------ |
294
- | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 69.0 | 88.3 | 12.9 | 0.31 | 2.7 | 4.3 |
295
- | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 73.8 | 91.7 | 23.4 | 0.35 | 6.4 | 13.5 |
296
- | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.8 | 93.5 | 85.4 | 0.62 | 17.0 | 42.7 |
297
- | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 76.8 | 93.5 | 163.0 | 0.87 | 37.5 | 99.7 |
298
- | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 79.0 | 94.6 | 232.0 | 1.01 | 57.4 | 154.8 |
294
+ | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n-cls.pt) | 224 | 69.0 | 88.3 | 12.9 | 0.31 | 2.7 | 4.3 |
295
+ | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8s-cls.pt) | 224 | 73.8 | 91.7 | 23.4 | 0.35 | 6.4 | 13.5 |
296
+ | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8m-cls.pt) | 224 | 76.8 | 93.5 | 85.4 | 0.62 | 17.0 | 42.7 |
297
+ | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8l-cls.pt) | 224 | 76.8 | 93.5 | 163.0 | 0.87 | 37.5 | 99.7 |
298
+ | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8x-cls.pt) | 224 | 79.0 | 94.6 | 232.0 | 1.01 | 57.4 | 154.8 |
299
299
 
300
300
  - **acc** values are model accuracies on the [ImageNet](https://www.image-net.org/) dataset validation set. <br>Reproduce by `yolo val classify data=path/to/ImageNet device=0`
301
301
  - **Speed** averaged over ImageNet val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val classify data=path/to/ImageNet batch=1 device=0|cpu`
{ultralytics-8.2.0 → ultralytics-8.2.1}/README.md RENAMED
@@ -1,7 +1,7 @@
1
1
  <div align="center">
2
2
  <p>
3
- <a href="https://www.ultralytics.com/blog/ultralytics-yolov8-turns-one-a-year-of-breakthroughs-and-innovations" target="_blank">
4
- <img width="100%" src="https://raw.githubusercontent.com/ultralytics/assets/main/im/banner-yolo-vision-2023.png" alt="YOLO Vision banner"></a>
3
+ <a href="https://github.com/ultralytics/assets/releases/tag/v8.2.0" target="_blank">
4
+ <img width="100%" src="https://raw.githubusercontent.com/ultralytics/assets/main/yolov8/banner-yolov8.png" alt="YOLO Vision banner"></a>
5
5
  </p>
6
6
 
7
7
  [中文](https://docs.ultralytics.com/zh/) | [한국어](https://docs.ultralytics.com/ko/) | [日本語](https://docs.ultralytics.com/ja/) | [Русский](https://docs.ultralytics.com/ru/) | [Deutsch](https://docs.ultralytics.com/de/) | [Français](https://docs.ultralytics.com/fr/) | [Español](https://docs.ultralytics.com/es/) | [Português](https://docs.ultralytics.com/pt/) | [हिन्दी](https://docs.ultralytics.com/hi/) | [العربية](https://docs.ultralytics.com/ar/) <br>
@@ -125,11 +125,11 @@ See [Detection Docs](https://docs.ultralytics.com/tasks/detect/) for usage examp
125
125
 
126
126
  | Model | size<br><sup>(pixels) | mAP<sup>val<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
127
127
  | ------------------------------------------------------------------------------------ | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
128
- | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
129
- | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
130
- | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
131
- | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
132
- | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
128
+ | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
129
+ | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
130
+ | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
131
+ | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
132
+ | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
133
133
 
134
134
  - **mAP<sup>val</sup>** values are for single-model single-scale on [COCO val2017](https://cocodataset.org) dataset. <br>Reproduce by `yolo val detect data=coco.yaml device=0`
135
135
  - **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val detect data=coco.yaml batch=1 device=0|cpu`
@@ -142,11 +142,11 @@ See [Detection Docs](https://docs.ultralytics.com/tasks/detect/) for usage examp
142
142
 
143
143
  | Model | size<br><sup>(pixels) | mAP<sup>val<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
144
144
  | ----------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
145
- | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 |
146
- | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 |
147
- | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 |
148
- | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 |
149
- | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 |
145
+ | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 |
146
+ | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 |
147
+ | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 |
148
+ | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 |
149
+ | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 |
150
150
 
151
151
  - **mAP<sup>val</sup>** values are for single-model single-scale on [Open Image V7](https://docs.ultralytics.com/datasets/detect/open-images-v7/) dataset. <br>Reproduce by `yolo val detect data=open-images-v7.yaml device=0`
152
152
  - **Speed** averaged over Open Image V7 val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val detect data=open-images-v7.yaml batch=1 device=0|cpu`
@@ -159,11 +159,11 @@ See [Segmentation Docs](https://docs.ultralytics.com/tasks/segment/) for usage e
159
159
 
160
160
  | Model | size<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
161
161
  | -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
162
- | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
163
- | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
164
- | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
165
- | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
166
- | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
162
+ | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
163
+ | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
164
+ | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
165
+ | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
166
+ | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
167
167
 
168
168
  - **mAP<sup>val</sup>** values are for single-model single-scale on [COCO val2017](https://cocodataset.org) dataset. <br>Reproduce by `yolo val segment data=coco-seg.yaml device=0`
169
169
  - **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val segment data=coco-seg.yaml batch=1 device=0|cpu`
@@ -176,12 +176,12 @@ See [Pose Docs](https://docs.ultralytics.com/tasks/pose/) for usage examples wit
176
176
 
177
177
  | Model | size<br><sup>(pixels) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
178
178
  | ---------------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
179
- | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
180
- | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
181
- | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
182
- | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
183
- | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
184
- | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
179
+ | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
180
+ | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
181
+ | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
182
+ | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
183
+ | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
184
+ | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
185
185
 
186
186
  - **mAP<sup>val</sup>** values are for single-model single-scale on [COCO Keypoints val2017](https://cocodataset.org) dataset. <br>Reproduce by `yolo val pose data=coco-pose.yaml device=0`
187
187
  - **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val pose data=coco-pose.yaml batch=1 device=0|cpu`
@@ -194,11 +194,11 @@ See [OBB Docs](https://docs.ultralytics.com/tasks/obb/) for usage examples with
194
194
 
195
195
  | Model | size<br><sup>(pixels) | mAP<sup>test<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
196
196
  | -------------------------------------------------------------------------------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
197
- | [YOLOv8n-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-obb.pt) | 1024 | 78.0 | 204.77 | 3.57 | 3.1 | 23.3 |
198
- | [YOLOv8s-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-obb.pt) | 1024 | 79.5 | 424.88 | 4.07 | 11.4 | 76.3 |
199
- | [YOLOv8m-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-obb.pt) | 1024 | 80.5 | 763.48 | 7.61 | 26.4 | 208.6 |
200
- | [YOLOv8l-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-obb.pt) | 1024 | 80.7 | 1278.42 | 11.83 | 44.5 | 433.8 |
201
- | [YOLOv8x-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-obb.pt) | 1024 | 81.36 | 1759.10 | 13.23 | 69.5 | 676.7 |
197
+ | [YOLOv8n-obb](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n-obb.pt) | 1024 | 78.0 | 204.77 | 3.57 | 3.1 | 23.3 |
198
+ | [YOLOv8s-obb](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8s-obb.pt) | 1024 | 79.5 | 424.88 | 4.07 | 11.4 | 76.3 |
199
+ | [YOLOv8m-obb](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8m-obb.pt) | 1024 | 80.5 | 763.48 | 7.61 | 26.4 | 208.6 |
200
+ | [YOLOv8l-obb](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8l-obb.pt) | 1024 | 80.7 | 1278.42 | 11.83 | 44.5 | 433.8 |
201
+ | [YOLOv8x-obb](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8x-obb.pt) | 1024 | 81.36 | 1759.10 | 13.23 | 69.5 | 676.7 |
202
202
 
203
203
  - **mAP<sup>test</sup>** values are for single-model multiscale on [DOTAv1](https://captain-whu.github.io/DOTA/index.html) dataset. <br>Reproduce by `yolo val obb data=DOTAv1.yaml device=0 split=test` and submit merged results to [DOTA evaluation](https://captain-whu.github.io/DOTA/evaluation.html).
204
204
  - **Speed** averaged over DOTAv1 val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val obb data=DOTAv1.yaml batch=1 device=0|cpu`
@@ -211,11 +211,11 @@ See [Classification Docs](https://docs.ultralytics.com/tasks/classify/) for usag
211
211
 
212
212
  | Model | size<br><sup>(pixels) | acc<br><sup>top1 | acc<br><sup>top5 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) at 640 |
213
213
  | -------------------------------------------------------------------------------------------- | --------------------- | ---------------- | ---------------- | ------------------------------ | ----------------------------------- | ------------------ | ------------------------ |
214
- | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 69.0 | 88.3 | 12.9 | 0.31 | 2.7 | 4.3 |
215
- | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 73.8 | 91.7 | 23.4 | 0.35 | 6.4 | 13.5 |
216
- | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.8 | 93.5 | 85.4 | 0.62 | 17.0 | 42.7 |
217
- | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 76.8 | 93.5 | 163.0 | 0.87 | 37.5 | 99.7 |
218
- | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 79.0 | 94.6 | 232.0 | 1.01 | 57.4 | 154.8 |
214
+ | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n-cls.pt) | 224 | 69.0 | 88.3 | 12.9 | 0.31 | 2.7 | 4.3 |
215
+ | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8s-cls.pt) | 224 | 73.8 | 91.7 | 23.4 | 0.35 | 6.4 | 13.5 |
216
+ | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8m-cls.pt) | 224 | 76.8 | 93.5 | 85.4 | 0.62 | 17.0 | 42.7 |
217
+ | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8l-cls.pt) | 224 | 76.8 | 93.5 | 163.0 | 0.87 | 37.5 | 99.7 |
218
+ | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8x-cls.pt) | 224 | 79.0 | 94.6 | 232.0 | 1.01 | 57.4 | 154.8 |
219
219
 
220
220
  - **acc** values are model accuracies on the [ImageNet](https://www.image-net.org/) dataset validation set. <br>Reproduce by `yolo val classify data=path/to/ImageNet device=0`
221
221
  - **Speed** averaged over ImageNet val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val classify data=path/to/ImageNet batch=1 device=0|cpu`
{ultralytics-8.2.0 → ultralytics-8.2.1}/tests/test_integrations.py RENAMED
@@ -126,7 +126,7 @@ def test_pycocotools():
126
126
  from ultralytics.models.yolo.segment import SegmentationValidator
127
127
 
128
128
  # Download annotations after each dataset downloads first
129
- url = "https://github.com/ultralytics/assets/releases/download/v8.1.0/"
129
+ url = "https://github.com/ultralytics/assets/releases/download/v8.2.0/"
130
130
 
131
131
  args = {"model": "yolov8n.pt", "data": "coco8.yaml", "save_json": True, "imgsz": 64}
132
132
  validator = DetectionValidator(args=args)
{ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/__init__.py RENAMED
@@ -1,6 +1,6 @@
1
1
  # Ultralytics YOLO 🚀, AGPL-3.0 license
2
2
 
3
- __version__ = "8.2.0"
3
+ __version__ = "8.2.1"
4
4
 
5
5
  from ultralytics.data.explorer.explorer import Explorer
6
6
  from ultralytics.models import RTDETR, SAM, YOLO, YOLOWorld
{ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/engine/exporter.py RENAMED
@@ -50,6 +50,7 @@ TensorFlow.js:
50
50
  $ npm start
51
51
  """
52
52
 
53
+ import gc
53
54
  import json
54
55
  import os
55
56
  import shutil
@@ -713,6 +714,7 @@ class Exporter:
713
714
 
714
715
  # Free CUDA memory
715
716
  del self.model
717
+ gc.collect()
716
718
  torch.cuda.empty_cache()
717
719
 
718
720
  # Write file
{ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/engine/trainer.py RENAMED
@@ -6,6 +6,7 @@ Usage:
6
6
  $ yolo mode=train model=yolov8n.pt data=coco128.yaml imgsz=640 epochs=100 batch=16
7
7
  """
8
8
 
9
+ import gc
9
10
  import math
10
11
  import os
11
12
  import subprocess
@@ -437,6 +438,7 @@ class BaseTrainer:
437
438
  self.scheduler.last_epoch = self.epoch # do not move
438
439
  self.stop |= epoch >= self.epochs # stop if exceeded epochs
439
440
  self.run_callbacks("on_fit_epoch_end")
441
+ gc.collect()
440
442
  torch.cuda.empty_cache() # clear GPU memory at end of epoch, may help reduce CUDA out of memory errors
441
443
 
442
444
  # Early Stopping
@@ -458,6 +460,7 @@ class BaseTrainer:
458
460
  if self.args.plots:
459
461
  self.plot_metrics()
460
462
  self.run_callbacks("on_train_end")
463
+ gc.collect()
461
464
  torch.cuda.empty_cache()
462
465
  self.run_callbacks("teardown")
463
466
 
{ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/models/yolo/classify/val.py RENAMED
@@ -56,8 +56,8 @@ class ClassificationValidator(BaseValidator):
56
56
  def update_metrics(self, preds, batch):
57
57
  """Updates running metrics with model predictions and batch targets."""
58
58
  n5 = min(len(self.names), 5)
59
- self.pred.append(preds.argsort(1, descending=True)[:, :n5])
60
- self.targets.append(batch["cls"])
59
+ self.pred.append(preds.argsort(1, descending=True)[:, :n5].type(torch.int32).cpu())
60
+ self.targets.append(batch["cls"].type(torch.int32).cpu())
61
61
 
62
62
  def finalize_metrics(self, *args, **kwargs):
63
63
  """Finalizes metrics of the model such as confusion_matrix and speed."""
{ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/downloads.py RENAMED
@@ -402,7 +402,7 @@ def get_github_assets(repo="ultralytics/assets", version="latest", retry=False):
402
402
  return data["tag_name"], [x["name"] for x in data["assets"]] # tag, assets i.e. ['yolov8n.pt', 'yolov8s.pt', ...]
403
403
 
404
404
 
405
- def attempt_download_asset(file, repo="ultralytics/assets", release="v8.1.0", **kwargs):
405
+ def attempt_download_asset(file, repo="ultralytics/assets", release="v8.2.0", **kwargs):
406
406
  """
407
407
  Attempt to download a file from GitHub release assets if it is not found locally. The function checks for the file
408
408
  locally first, then tries to download it from the specified GitHub repository release.
@@ -410,7 +410,7 @@ def attempt_download_asset(file, repo="ultralytics/assets", release="v8.1.0", **
410
410
  Args:
411
411
  file (str | Path): The filename or file path to be downloaded.
412
412
  repo (str, optional): The GitHub repository in the format 'owner/repo'. Defaults to 'ultralytics/assets'.
413
- release (str, optional): The specific release version to be downloaded. Defaults to 'v8.1.0'.
413
+ release (str, optional): The specific release version to be downloaded. Defaults to 'v8.2.0'.
414
414
  **kwargs (any): Additional keyword arguments for the download process.
415
415
 
416
416
  Returns:
{ultralytics-8.2.0 → ultralytics-8.2.1}/ultralytics/utils/torch_utils.py RENAMED
@@ -1,5 +1,6 @@
1
1
  # Ultralytics YOLO 🚀, AGPL-3.0 license
2
2
 
3
+ import gc
3
4
  import math
4
5
  import os
5
6
  import random
@@ -581,6 +582,7 @@ def profile(input, ops, n=10, device=None):
581
582
  except Exception as e:
582
583
  LOGGER.info(e)
583
584
  results.append(None)
585
+ gc.collect() # attempt to free unused memory
584
586
  torch.cuda.empty_cache()
585
587
  return results
586
588
 
{ultralytics-8.2.0 → ultralytics-8.2.1/ultralytics.egg-info}/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: ultralytics
3
- Version: 8.2.0
3
+ Version: 8.2.1
4
4
  Summary: Ultralytics YOLOv8 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
5
5
  Author: Glenn Jocher, Ayush Chaurasia, Jing Qiu
6
6
  Maintainer: Glenn Jocher, Ayush Chaurasia, Jing Qiu
@@ -80,8 +80,8 @@ Requires-Dist: pycocotools>=2.0.7; extra == "extra"
80
80
 
81
81
  <div align="center">
82
82
  <p>
83
- <a href="https://www.ultralytics.com/blog/ultralytics-yolov8-turns-one-a-year-of-breakthroughs-and-innovations" target="_blank">
84
- <img width="100%" src="https://raw.githubusercontent.com/ultralytics/assets/main/im/banner-yolo-vision-2023.png" alt="YOLO Vision banner"></a>
83
+ <a href="https://github.com/ultralytics/assets/releases/tag/v8.2.0" target="_blank">
84
+ <img width="100%" src="https://raw.githubusercontent.com/ultralytics/assets/main/yolov8/banner-yolov8.png" alt="YOLO Vision banner"></a>
85
85
  </p>
86
86
 
87
87
  [中文](https://docs.ultralytics.com/zh/) | [한국어](https://docs.ultralytics.com/ko/) | [日本語](https://docs.ultralytics.com/ja/) | [Русский](https://docs.ultralytics.com/ru/) | [Deutsch](https://docs.ultralytics.com/de/) | [Français](https://docs.ultralytics.com/fr/) | [Español](https://docs.ultralytics.com/es/) | [Português](https://docs.ultralytics.com/pt/) | [हिन्दी](https://docs.ultralytics.com/hi/) | [العربية](https://docs.ultralytics.com/ar/) <br>
@@ -205,11 +205,11 @@ See [Detection Docs](https://docs.ultralytics.com/tasks/detect/) for usage examp
205
205
 
206
206
  | Model | size<br><sup>(pixels) | mAP<sup>val<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
207
207
  | ------------------------------------------------------------------------------------ | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
208
- | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
209
- | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
210
- | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
211
- | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
212
- | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
208
+ | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 |
209
+ | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 |
210
+ | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 |
211
+ | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 |
212
+ | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 |
213
213
 
214
214
  - **mAP<sup>val</sup>** values are for single-model single-scale on [COCO val2017](https://cocodataset.org) dataset. <br>Reproduce by `yolo val detect data=coco.yaml device=0`
215
215
  - **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val detect data=coco.yaml batch=1 device=0|cpu`
@@ -222,11 +222,11 @@ See [Detection Docs](https://docs.ultralytics.com/tasks/detect/) for usage examp
222
222
 
223
223
  | Model | size<br><sup>(pixels) | mAP<sup>val<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
224
224
  | ----------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
225
- | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 |
226
- | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 |
227
- | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 |
228
- | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 |
229
- | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 |
225
+ | [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n-oiv7.pt) | 640 | 18.4 | 142.4 | 1.21 | 3.5 | 10.5 |
226
+ | [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8s-oiv7.pt) | 640 | 27.7 | 183.1 | 1.40 | 11.4 | 29.7 |
227
+ | [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8m-oiv7.pt) | 640 | 33.6 | 408.5 | 2.26 | 26.2 | 80.6 |
228
+ | [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8l-oiv7.pt) | 640 | 34.9 | 596.9 | 2.43 | 44.1 | 167.4 |
229
+ | [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8x-oiv7.pt) | 640 | 36.3 | 860.6 | 3.56 | 68.7 | 260.6 |
230
230
 
231
231
  - **mAP<sup>val</sup>** values are for single-model single-scale on [Open Image V7](https://docs.ultralytics.com/datasets/detect/open-images-v7/) dataset. <br>Reproduce by `yolo val detect data=open-images-v7.yaml device=0`
232
232
  - **Speed** averaged over Open Image V7 val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val detect data=open-images-v7.yaml batch=1 device=0|cpu`
@@ -239,11 +239,11 @@ See [Segmentation Docs](https://docs.ultralytics.com/tasks/segment/) for usage e
239
239
 
240
240
  | Model | size<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
241
241
  | -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
242
- | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
243
- | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
244
- | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
245
- | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
246
- | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
242
+ | [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 |
243
+ | [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 |
244
+ | [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 |
245
+ | [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 |
246
+ | [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 |
247
247
 
248
248
  - **mAP<sup>val</sup>** values are for single-model single-scale on [COCO val2017](https://cocodataset.org) dataset. <br>Reproduce by `yolo val segment data=coco-seg.yaml device=0`
249
249
  - **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val segment data=coco-seg.yaml batch=1 device=0|cpu`
@@ -256,12 +256,12 @@ See [Pose Docs](https://docs.ultralytics.com/tasks/pose/) for usage examples wit
256
256
 
257
257
  | Model | size<br><sup>(pixels) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
258
258
  | ---------------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
259
- | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
260
- | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
261
- | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
262
- | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
263
- | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
264
- | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
259
+ | [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
260
+ | [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
261
+ | [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
262
+ | [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
263
+ | [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
264
+ | [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
265
265
 
266
266
  - **mAP<sup>val</sup>** values are for single-model single-scale on [COCO Keypoints val2017](https://cocodataset.org) dataset. <br>Reproduce by `yolo val pose data=coco-pose.yaml device=0`
267
267
  - **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val pose data=coco-pose.yaml batch=1 device=0|cpu`
@@ -274,11 +274,11 @@ See [OBB Docs](https://docs.ultralytics.com/tasks/obb/) for usage examples with
274
274
 
275
275
  | Model | size<br><sup>(pixels) | mAP<sup>test<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
276
276
  | -------------------------------------------------------------------------------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
277
- | [YOLOv8n-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-obb.pt) | 1024 | 78.0 | 204.77 | 3.57 | 3.1 | 23.3 |
278
- | [YOLOv8s-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-obb.pt) | 1024 | 79.5 | 424.88 | 4.07 | 11.4 | 76.3 |
279
- | [YOLOv8m-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-obb.pt) | 1024 | 80.5 | 763.48 | 7.61 | 26.4 | 208.6 |
280
- | [YOLOv8l-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-obb.pt) | 1024 | 80.7 | 1278.42 | 11.83 | 44.5 | 433.8 |
281
- | [YOLOv8x-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-obb.pt) | 1024 | 81.36 | 1759.10 | 13.23 | 69.5 | 676.7 |
277
+ | [YOLOv8n-obb](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n-obb.pt) | 1024 | 78.0 | 204.77 | 3.57 | 3.1 | 23.3 |
278
+ | [YOLOv8s-obb](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8s-obb.pt) | 1024 | 79.5 | 424.88 | 4.07 | 11.4 | 76.3 |
279
+ | [YOLOv8m-obb](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8m-obb.pt) | 1024 | 80.5 | 763.48 | 7.61 | 26.4 | 208.6 |
280
+ | [YOLOv8l-obb](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8l-obb.pt) | 1024 | 80.7 | 1278.42 | 11.83 | 44.5 | 433.8 |
281
+ | [YOLOv8x-obb](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8x-obb.pt) | 1024 | 81.36 | 1759.10 | 13.23 | 69.5 | 676.7 |
282
282
 
283
283
  - **mAP<sup>test</sup>** values are for single-model multiscale on [DOTAv1](https://captain-whu.github.io/DOTA/index.html) dataset. <br>Reproduce by `yolo val obb data=DOTAv1.yaml device=0 split=test` and submit merged results to [DOTA evaluation](https://captain-whu.github.io/DOTA/evaluation.html).
284
284
  - **Speed** averaged over DOTAv1 val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val obb data=DOTAv1.yaml batch=1 device=0|cpu`
@@ -291,11 +291,11 @@ See [Classification Docs](https://docs.ultralytics.com/tasks/classify/) for usag
291
291
 
292
292
  | Model | size<br><sup>(pixels) | acc<br><sup>top1 | acc<br><sup>top5 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) at 640 |
293
293
  | -------------------------------------------------------------------------------------------- | --------------------- | ---------------- | ---------------- | ------------------------------ | ----------------------------------- | ------------------ | ------------------------ |
294
- | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8n-cls.pt) | 224 | 69.0 | 88.3 | 12.9 | 0.31 | 2.7 | 4.3 |
295
- | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-cls.pt) | 224 | 73.8 | 91.7 | 23.4 | 0.35 | 6.4 | 13.5 |
296
- | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8m-cls.pt) | 224 | 76.8 | 93.5 | 85.4 | 0.62 | 17.0 | 42.7 |
297
- | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-cls.pt) | 224 | 76.8 | 93.5 | 163.0 | 0.87 | 37.5 | 99.7 |
298
- | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-cls.pt) | 224 | 79.0 | 94.6 | 232.0 | 1.01 | 57.4 | 154.8 |
294
+ | [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n-cls.pt) | 224 | 69.0 | 88.3 | 12.9 | 0.31 | 2.7 | 4.3 |
295
+ | [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8s-cls.pt) | 224 | 73.8 | 91.7 | 23.4 | 0.35 | 6.4 | 13.5 |
296
+ | [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8m-cls.pt) | 224 | 76.8 | 93.5 | 85.4 | 0.62 | 17.0 | 42.7 |
297
+ | [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8l-cls.pt) | 224 | 76.8 | 93.5 | 163.0 | 0.87 | 37.5 | 99.7 |
298
+ | [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8x-cls.pt) | 224 | 79.0 | 94.6 | 232.0 | 1.01 | 57.4 | 154.8 |
299
299
 
300
300
  - **acc** values are model accuracies on the [ImageNet](https://www.image-net.org/) dataset validation set. <br>Reproduce by `yolo val classify data=path/to/ImageNet device=0`
301
301
  - **Speed** averaged over ImageNet val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val classify data=path/to/ImageNet batch=1 device=0|cpu`
{ultralytics-8.2.0 → ultralytics-8.2.1}/LICENSE RENAMED
File without changes
{ultralytics-8.2.0 → ultralytics-8.2.1}/pyproject.toml RENAMED
File without changes
{ultralytics-8.2.0 → ultralytics-8.2.1}/setup.cfg RENAMED
File without changes