You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.

metafile.yml 3.2 kB

2 years ago
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293
  1. Collections:
  2. - Name: GRoIE
  3. Metadata:
  4. Training Data: COCO
  5. Training Techniques:
  6. - SGD with Momentum
  7. - Weight Decay
  8. Training Resources: 8x V100 GPUs
  9. Architecture:
  10. - Generic RoI Extractor
  11. - FPN
  12. - RPN
  13. - ResNet
  14. - RoIAlign
  15. Paper:
  16. URL: https://arxiv.org/abs/2004.13665
  17. Title: 'A novel Region of Interest Extraction Layer for Instance Segmentation'
  18. README: configs/groie/README.md
  19. Code:
  20. URL: https://github.com/open-mmlab/mmdetection/blob/v2.1.0/mmdet/models/roi_heads/roi_extractors/groie.py#L15
  21. Version: v2.1.0
  22. Models:
  23. - Name: faster_rcnn_r50_fpn_groie_1x_coco
  24. In Collection: GRoIE
  25. Config: configs/groie/faster_rcnn_r50_fpn_groie_1x_coco.py
  26. Metadata:
  27. Epochs: 12
  28. Results:
  29. - Task: Object Detection
  30. Dataset: COCO
  31. Metrics:
  32. box AP: 38.3
  33. Weights: https://download.openmmlab.com/mmdetection/v2.0/groie/faster_rcnn_r50_fpn_groie_1x_coco/faster_rcnn_r50_fpn_groie_1x_coco_20200604_211715-66ee9516.pth
  34. - Name: grid_rcnn_r50_fpn_gn-head_groie_1x_coco
  35. In Collection: GRoIE
  36. Config: configs/groie/grid_rcnn_r50_fpn_gn-head_groie_1x_coco.py
  37. Metadata:
  38. Epochs: 12
  39. Results:
  40. - Task: Object Detection
  41. Dataset: COCO
  42. Metrics:
  43. box AP: 39.1
  44. - Name: mask_rcnn_r50_fpn_groie_1x_coco
  45. In Collection: GRoIE
  46. Config: configs/groie/mask_rcnn_r50_fpn_groie_1x_coco.py
  47. Metadata:
  48. Epochs: 12
  49. Results:
  50. - Task: Object Detection
  51. Dataset: COCO
  52. Metrics:
  53. box AP: 39.0
  54. - Task: Instance Segmentation
  55. Dataset: COCO
  56. Metrics:
  57. mask AP: 36.0
  58. Weights: https://download.openmmlab.com/mmdetection/v2.0/groie/mask_rcnn_r50_fpn_groie_1x_coco/mask_rcnn_r50_fpn_groie_1x_coco_20200604_211715-50d90c74.pth
  59. - Name: mask_rcnn_r50_fpn_syncbn-backbone_r4_gcb_c3-c5_groie_1x_coco
  60. In Collection: GRoIE
  61. Config: configs/groie/mask_rcnn_r50_fpn_syncbn-backbone_r4_gcb_c3-c5_groie_1x_coco.py
  62. Metadata:
  63. Epochs: 12
  64. Results:
  65. - Task: Object Detection
  66. Dataset: COCO
  67. Metrics:
  68. box AP: 41.0
  69. - Task: Instance Segmentation
  70. Dataset: COCO
  71. Metrics:
  72. mask AP: 37.8
  73. Weights: https://download.openmmlab.com/mmdetection/v2.0/groie/mask_rcnn_r50_fpn_syncbn-backbone_r4_gcb_c3-c5_groie_1x_coco/mask_rcnn_r50_fpn_syncbn-backbone_r4_gcb_c3-c5_groie_1x_coco_20200604_211715-42eb79e1.pth
  74. - Name: mask_rcnn_r101_fpn_syncbn-backbone_r4_gcb_c3-c5_groie_1x_coco
  75. In Collection: GRoIE
  76. Config: configs/groie/mask_rcnn_r101_fpn_syncbn-backbone_r4_gcb_c3-c5_groie_1x_coco.py
  77. Metadata:
  78. Epochs: 12
  79. Results:
  80. - Task: Object Detection
  81. Dataset: COCO
  82. Metrics:
  83. box AP: 42.6
  84. - Task: Instance Segmentation
  85. Dataset: COCO
  86. Metrics:
  87. mask AP: 38.7
  88. Weights: https://download.openmmlab.com/mmdetection/v2.0/groie/mask_rcnn_r101_fpn_syncbn-backbone_r4_gcb_c3-c5_groie_1x_coco/mask_rcnn_r101_fpn_syncbn-backbone_r4_gcb_c3-c5_groie_1x_coco_20200607_224507-8daae01c.pth

No Description

Contributors (2)