fix model zoo doc (#2629)

* fix model zoo doc

configs/faster_rcnn_se154_vd_1x.yml

-architecture: FasterRCNN
-train_feed: FasterRCNNTrainFeed
-eval_feed: FasterRCNNEvalFeed
-test_feed: FasterRCNNTestFeed
-max_iters: 180000
-snapshot_iter: 10000
-use_gpu: true
-log_smooth_window: 20
-save_dir: output
-pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/SE154_vd_pretrained.tar
-weights: output/faster_rcnn_se154_1x/model_final
-metric: COCO
-
-FasterRCNN:
-  backbone: SENet
-  rpn_head: RPNHead
-  roi_extractor: RoIAlign
-  bbox_head: BBoxHead
-  bbox_assigner: BBoxAssigner
-
-SENet:
-  depth: 152
-  feature_maps: 4
-  freeze_at: 2
-  group_width: 4
-  groups: 64
-  norm_type: affine_channel
-  variant: d
-
-SENetC5:
-  depth: 152
-  freeze_at: 2
-  group_width: 4
-  groups: 64
-  norm_type: affine_channel
-  variant: d
-
-RPNHead:
-  anchor_generator:
-    anchor_sizes: [32, 64, 128, 256, 512]
-    aspect_ratios: [0.5, 1.0, 2.0]
-    stride: [16.0, 16.0]
-    variance: [1.0, 1.0, 1.0, 1.0]
-  rpn_target_assign:
-    rpn_batch_size_per_im: 256
-    rpn_fg_fraction: 0.5
-    rpn_negative_overlap: 0.3
-    rpn_positive_overlap: 0.7
-    rpn_straddle_thresh: 0.0
-  train_proposal:
-    min_size: 0.0
-    nms_thresh: 0.7
-    post_nms_top_n: 2000
-    pre_nms_top_n: 12000
-  test_proposal:
-    min_size: 0.0
-    nms_thresh: 0.7
-    post_nms_top_n: 1000
-    pre_nms_top_n: 6000
-
-RoIAlign:
-  resolution: 7
-  sampling_ratio: 0
-  spatial_scale: 0.0625
-
-BBoxAssigner:
-  batch_size_per_im: 512
-  bbox_reg_weights: [0.1, 0.1, 0.2, 0.2]
-  bg_thresh_hi: 0.5
-  bg_thresh_lo: 0.0
-  fg_fraction: 0.25
-  fg_thresh: 0.5
-  num_classes: 81
-
-BBoxHead:
-  head: SENetC5
-  nms:
-    keep_top_k: 100
-    nms_threshold: 0.5
-    score_threshold: 0.05
-  num_classes: 81
-
-LearningRate:
-  base_lr: 0.01
-  schedulers:
-  - !PiecewiseDecay
-    gamma: 0.1
-    milestones: [120000, 160000]
-  - !LinearWarmup
-    start_factor: 0.1
-    steps: 1000
-
-OptimizerBuilder:
-  optimizer:
-    momentum: 0.9
-    type: Momentum
-  regularizer:
-    factor: 0.0001
-    type: L2
-
-FasterRCNNTrainFeed:
-  # batch size per device
-  batch_size: 1
-  dataset:
-    dataset_dir: dataset/coco
-    annotation: annotations/instances_val2017.json
-    image_dir: val2017
-  num_workers: 2
-
-FasterRCNNEvalFeed:
-  batch_size: 1
-  dataset:
-    dataset_dir: dataset/coco
-    annotation: annotations/instances_val2017.json
-    image_dir: val2017
-  num_workers: 2
-
-FasterRCNNTestFeed:
-  batch_size: 1
-  dataset:
-    annotation: annotations/instances_val2017.json
-  num_workers: 2

configs/faster_rcnn_se154_vd_fpn_1x.yml

-architecture: FasterRCNN
-train_feed: FasterRCNNTrainFeed
-eval_feed: FasterRCNNEvalFeed
-test_feed: FasterRCNNTestFeed
-max_iters: 180000
-snapshot_iter: 10000
-use_gpu: true
-log_smooth_window: 20
-save_dir: output
-pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/SE154_vd_pretrained.tar
-weights: output/faster_rcnn_se154_fpn_1x/model_final
-metric: COCO
-
-FasterRCNN:
-  backbone: SENet
-  fpn: FPN
-  rpn_head: FPNRPNHead
-  roi_extractor: FPNRoIAlign
-  bbox_head: BBoxHead
-  bbox_assigner: BBoxAssigner
-
-SENet:
-  depth: 152
-  feature_maps: [2, 3, 4, 5]
-  freeze_at: 2
-  group_width: 4
-  groups: 64
-  norm_type: affine_channel
-  variant: d
-
-FPN:
-  max_level: 6
-  min_level: 2
-  num_chan: 256
-  spatial_scale: [0.03125, 0.0625, 0.125, 0.25]
-
-FPNRPNHead:
-  anchor_generator:
-    anchor_sizes: [32, 64, 128, 256, 512]
-    aspect_ratios: [0.5, 1.0, 2.0]
-    stride: [16.0, 16.0]
-    variance: [1.0, 1.0, 1.0, 1.0]
-  anchor_start_size: 32
-  max_level: 6
-  min_level: 2
-  num_chan: 256
-  rpn_target_assign:
-    rpn_batch_size_per_im: 256
-    rpn_fg_fraction: 0.5
-    rpn_negative_overlap: 0.3
-    rpn_positive_overlap: 0.7
-    rpn_straddle_thresh: 0.0
-  train_proposal:
-    min_size: 0.0
-    nms_thresh: 0.7
-    post_nms_top_n: 2000
-    pre_nms_top_n: 2000
-  test_proposal:
-    min_size: 0.0
-    nms_thresh: 0.7
-    post_nms_top_n: 1000
-    pre_nms_top_n: 1000
-
-FPNRoIAlign:
-  canconical_level: 4
-  canonical_size: 224
-  max_level: 5
-  min_level: 2
-  box_resolution: 7
-  sampling_ratio: 2
-
-BBoxAssigner:
-  batch_size_per_im: 512
-  bbox_reg_weights: [0.1, 0.1, 0.2, 0.2]
-  bg_thresh_hi: 0.5
-  bg_thresh_lo: 0.0
-  fg_fraction: 0.25
-  fg_thresh: 0.5
-  num_classes: 81
-
-BBoxHead:
-  head: TwoFCHead
-  nms:
-    keep_top_k: 100
-    nms_threshold: 0.5
-    score_threshold: 0.05
-  num_classes: 81
-
-TwoFCHead:
-  num_chan: 1024
-
-LearningRate:
-  base_lr: 0.01
-  schedulers:
-  - !PiecewiseDecay
-    gamma: 0.1
-    milestones: [120000, 160000]
-  - !LinearWarmup
-    start_factor: 0.1
-    steps: 1000
-
-OptimizerBuilder:
-  optimizer:
-    momentum: 0.9
-    type: Momentum
-  regularizer:
-    factor: 0.0001
-    type: L2
-
-FasterRCNNTrainFeed:
-  # batch size per device
-  batch_size: 1
-  dataset:
-    dataset_dir: dataset/coco
-    image_dir: train2017
-    annotation: annotations/instances_train2017.json
-  batch_transforms:
-  - !PadBatch
-    pad_to_stride: 32
-  num_workers: 2
-
-FasterRCNNEvalFeed:
-  batch_size: 1
-  dataset:
-    dataset_dir: dataset/coco
-    annotation: annotations/instances_val2017.json
-    image_dir: val2017
-  batch_transforms:
-  - !PadBatch
-    pad_to_stride: 32
-  num_workers: 2
-
-FasterRCNNTestFeed:
-  batch_size: 1
-  dataset:
-    annotation: annotations/instances_val2017.json
-  batch_transforms:
-  - !PadBatch
-    pad_to_stride: 32
-  num_workers: 2

configs/faster_rcnn_se154_vd_fpn_s1x.yml

@@ -8,7 +8,7 @@ use_gpu: true
 log_smooth_window: 20
 save_dir: output
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/SE154_vd_pretrained.tar
-weights: output/faster_rcnn_se154_fpn_s1x/model_final
+weights: output/faster_rcnn_se154_vd_fpn_s1x/model_final
 metric: COCO
 
 FasterRCNN:

configs/faster_rcnn_x101_64x4d_fpn_1x.yml

-architecture: FasterRCNN
-train_feed: FasterRCNNTrainFeed
-eval_feed: FasterRCNNEvalFeed
-test_feed: FasterRCNNTestFeed
-max_iters: 180000
-snapshot_iter: 10000
-use_gpu: true
-log_smooth_window: 20
-save_dir: output
-pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_64x4d_pretrained.tar
-weights: output/faster_rcnn_x101_64x4d_fpn_1x/model_final
-metric: COCO
-
-FasterRCNN:
-  backbone: ResNeXt
-  fpn: FPN
-  rpn_head: FPNRPNHead
-  roi_extractor: FPNRoIAlign
-  bbox_head: BBoxHead
-  bbox_assigner: BBoxAssigner
-
-ResNeXt:
-  depth: 101
-  feature_maps: [2, 3, 4, 5]
-  freeze_at: 2
-  group_width: 4
-  groups: 64
-  norm_type: affine_channel
-
-FPN:
-  max_level: 6
-  min_level: 2
-  num_chan: 256
-  spatial_scale: [0.03125, 0.0625, 0.125, 0.25]
-
-FPNRPNHead:
-  anchor_generator:
-    anchor_sizes: [32, 64, 128, 256, 512]
-    aspect_ratios: [0.5, 1.0, 2.0]
-    stride: [16.0, 16.0]
-    variance: [1.0, 1.0, 1.0, 1.0]
-  anchor_start_size: 32
-  max_level: 6
-  min_level: 2
-  num_chan: 256
-  rpn_target_assign:
-    rpn_batch_size_per_im: 256
-    rpn_fg_fraction: 0.5
-    rpn_negative_overlap: 0.3
-    rpn_positive_overlap: 0.7
-    rpn_straddle_thresh: 0.0
-  train_proposal:
-    min_size: 0.0
-    nms_thresh: 0.7
-    post_nms_top_n: 2000
-    pre_nms_top_n: 2000
-  test_proposal:
-    min_size: 0.0
-    nms_thresh: 0.7
-    post_nms_top_n: 1000
-    pre_nms_top_n: 1000
-
-FPNRoIAlign:
-  canconical_level: 4
-  canonical_size: 224
-  max_level: 5
-  min_level: 2
-  box_resolution: 7
-  sampling_ratio: 2
-
-BBoxAssigner:
-  batch_size_per_im: 512
-  bbox_reg_weights: [0.1, 0.1, 0.2, 0.2]
-  bg_thresh_hi: 0.5
-  bg_thresh_lo: 0.0
-  fg_fraction: 0.25
-  fg_thresh: 0.5
-  num_classes: 81
-
-BBoxHead:
-  head: TwoFCHead
-  nms:
-    keep_top_k: 100
-    nms_threshold: 0.5
-    score_threshold: 0.05
-  num_classes: 81
-
-TwoFCHead:
-  num_chan: 1024
-
-LearningRate:
-  base_lr: 0.01
-  schedulers:
-  - !PiecewiseDecay
-    gamma: 0.1
-    milestones: [120000, 160000]
-  - !LinearWarmup
-    start_factor: 0.3333333333333333
-    steps: 500
-
-OptimizerBuilder:
-  optimizer:
-    momentum: 0.9
-    type: Momentum
-  regularizer:
-    factor: 0.0001
-    type: L2
-
-FasterRCNNTrainFeed:
-  # batch size per device
-  batch_size: 1
-  dataset:
-    dataset_dir: dataset/coco
-    image_dir: train2017
-    annotation: annotations/instances_train2017.json
-  batch_transforms:
-  - !PadBatch
-    pad_to_stride: 32
-  num_workers: 2
-
-FasterRCNNEvalFeed:
-  batch_size: 1
-  dataset:
-    dataset_dir: dataset/coco
-    annotation: annotations/instances_val2017.json
-    image_dir: val2017
-  batch_transforms:
-  - !PadBatch
-    pad_to_stride: 32
-  num_workers: 2
-
-FasterRCNNTestFeed:
-  batch_size: 1
-  dataset:
-    annotation: annotations/instances_val2017.json
-  batch_transforms:
-  - !PadBatch
-    pad_to_stride: 32
-  num_workers: 2

configs/faster_rcnn_x101_64x4d_fpn_2x.yml

-architecture: FasterRCNN
-train_feed: FasterRCNNTrainFeed
-eval_feed: FasterRCNNEvalFeed
-test_feed: FasterRCNNTestFeed
-max_iters: 180000
-snapshot_iter: 10000
-use_gpu: true
-log_smooth_window: 20
-save_dir: output
-pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_64x4d_pretrained.tar
-weights: output/faster_rcnn_x101_64x4d_fpn_2x/model_final
-metric: COCO
-
-FasterRCNN:
-  backbone: ResNeXt
-  fpn: FPN
-  rpn_head: FPNRPNHead
-  roi_extractor: FPNRoIAlign
-  bbox_head: BBoxHead
-  bbox_assigner: BBoxAssigner
-
-ResNeXt:
-  depth: 101
-  feature_maps: [2, 3, 4, 5]
-  freeze_at: 2
-  group_width: 4
-  groups: 64
-  norm_type: affine_channel
-
-FPN:
-  max_level: 6
-  min_level: 2
-  num_chan: 256
-  spatial_scale: [0.03125, 0.0625, 0.125, 0.25]
-
-FPNRPNHead:
-  anchor_generator:
-    anchor_sizes: [32, 64, 128, 256, 512]
-    aspect_ratios: [0.5, 1.0, 2.0]
-    stride: [16.0, 16.0]
-    variance: [1.0, 1.0, 1.0, 1.0]
-  anchor_start_size: 32
-  max_level: 6
-  min_level: 2
-  num_chan: 256
-  rpn_target_assign:
-    rpn_batch_size_per_im: 256
-    rpn_fg_fraction: 0.5
-    rpn_negative_overlap: 0.3
-    rpn_positive_overlap: 0.7
-    rpn_straddle_thresh: 0.0
-  train_proposal:
-    min_size: 0.0
-    nms_thresh: 0.7
-    post_nms_top_n: 2000
-    pre_nms_top_n: 2000
-  test_proposal:
-    min_size: 0.0
-    nms_thresh: 0.7
-    post_nms_top_n: 1000
-    pre_nms_top_n: 1000
-
-FPNRoIAlign:
-  canconical_level: 4
-  canonical_size: 224
-  max_level: 5
-  min_level: 2
-  box_resolution: 7
-  sampling_ratio: 2
-
-BBoxAssigner:
-  batch_size_per_im: 512
-  bbox_reg_weights: [0.1, 0.1, 0.2, 0.2]
-  bg_thresh_hi: 0.5
-  bg_thresh_lo: 0.0
-  fg_fraction: 0.25
-  fg_thresh: 0.5
-  num_classes: 81
-
-BBoxHead:
-  head: TwoFCHead
-  nms:
-    keep_top_k: 100
-    nms_threshold: 0.5
-    score_threshold: 0.05
-  num_classes: 81
-
-TwoFCHead:
-  num_chan: 1024
-
-LearningRate:
-  base_lr: 0.01
-  schedulers:
-  - !PiecewiseDecay
-    gamma: 0.1
-    milestones: [240000, 320000]
-  - !LinearWarmup
-    start_factor: 0.3333333333333333
-    steps: 500
-
-OptimizerBuilder:
-  optimizer:
-    momentum: 0.9
-    type: Momentum
-  regularizer:
-    factor: 0.0001
-    type: L2
-
-FasterRCNNTrainFeed:
-  # batch size per device
-  batch_size: 1
-  dataset:
-    dataset_dir: dataset/coco
-    image_dir: train2017
-    annotation: annotations/instances_train2017.json
-  batch_transforms:
-  - !PadBatch
-    pad_to_stride: 32
-  num_workers: 2
-
-FasterRCNNEvalFeed:
-  batch_size: 1
-  dataset:
-    dataset_dir: dataset/coco
-    annotation: annotations/instances_val2017.json
-    image_dir: val2017
-  batch_transforms:
-  - !PadBatch
-    pad_to_stride: 32
-  num_workers: 2
-
-FasterRCNNTestFeed:
-  batch_size: 1
-  dataset:
-    annotation: annotations/instances_val2017.json
-  batch_transforms:
-  - !PadBatch
-    pad_to_stride: 32
-  num_workers: 2

docs/MODEL_ZOO.md

@@ -30,57 +30,58 @@ The backbone models pretrained on ImageNet are available. All backbone models ar
 
 ### Faster & Mask R-CNN
 
-| Backbone             | Type           | Img/gpu | Lr schd | Box AP | Mask AP |                           Download                           |
+| Backbone             | Type           | Image/gpu | Lr schd | Box AP | Mask AP |                           Download                           |
 | :------------------- | :------------- | :-----: | :-----: | :----: | :-----: | :----------------------------------------------------------: |
 | ResNet50             | Faster         |    1    |   1x    |  35.2  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_1x.tar) |
 | ResNet50             | Faster         |    1    |   2x    |  37.1  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_2x.tar) |
 | ResNet50             | Mask           |    1    |   1x    |  36.5  |  32.2   | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_1x.tar) |
-| ResNet50             | Mask           |    1    |   2x    |        |         |                          [model]()                           |
-| ResNet50-D           | Faster         |    1    |   1x    |  36.4  |    -    | [model](ttps://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_1x.tar) |
+| ResNet50-vd          | Faster         |    1    |   1x    |  36.4  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_1x.tar) |
 | ResNet50-FPN         | Faster         |    2    |   1x    |  37.2  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_fpn_1x.tar) |
 | ResNet50-FPN         | Faster         |    2    |   2x    |  37.7  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_fpn_2x.tar) |
 | ResNet50-FPN         | Mask           |    2    |   1x    |  37.9  |  34.2   | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_fpn_1x.tar) |
 | ResNet50-FPN         | Cascade Faster |    2    |   1x    |  40.9  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_r50_fpn_1x.tar) |
-| ResNet50-D-FPN       | Faster         |    2    |   2x    |  38.9  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_2x.tar) |
-| ResNet50-D-FPN       | Mask           |    2    |   2x    |  39.8  |  35.4   | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_vd_fpn_2x.tar) |
+| ResNet50-vd-FPN      | Faster         |    2    |   2x    |  38.9  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_fpn_2x.tar) |
+| ResNet50-vd-FPN      | Mask           |    2    |   2x    |  39.8  |  35.4   | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_vd_fpn_2x.tar) |
 | ResNet101            | Faster         |    1    |   1x    |  38.3  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_1x.tar) |
 | ResNet101-FPN        | Faster         |    1    |   1x    |  38.7  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_1x.tar) |
 | ResNet101-FPN        | Faster         |    1    |   2x    |  39.1  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_2x.tar) |
 | ResNet101-FPN        | Mask           |    1    |   1x    |  39.5  |  35.2   | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r101_fpn_1x.tar) |
-| ResNet101-D-FPN      | Faster         |    1    |   1x    |  40.0  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_1x.tar) |
-| ResNet101-D-FPN      | Faster         |    1    |   2x    |  40.6  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_2x.tar) |
-| SENet154-D-FPN       | Faster         |    1    |  1.44x  |  43.5  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_se154_fpn_s1x.tar) |
-| SENet154-D-FPN       | Mask           |    1    |  1.44x  |  44.0  |  38.7   | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_se154_vd_fpn_s1x.tar) |
+| ResNet101-vd-FPN     | Faster         |    1    |   1x    |  40.0  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_1x.tar) |
+| ResNet101-vd-FPN     | Faster         |    1    |   2x    |  40.6  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_fpn_2x.tar) |
+| SENet154-vd-FPN      | Faster         |    1    |  1.44x  |  42.9  |    -    | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_se154_vd_fpn_s1x.tar) |
+| SENet154-vd-FPN      | Mask           |    1    |  1.44x  |  44.0  |  38.7   | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_se154_vd_fpn_s1x.tar) |
 
 ### Yolo v3
 
-| Backbone     | Size | Img/gpu | Lr schd | Box AP | Download  |
+| Backbone     | Size | Image/gpu | Lr schd | Box AP | Download  |
 | :----------- | :--: | :-----: | :-----: | :----: | :-------: |
-| DarkNet53    | 608  |    8    |   120e  |  38.9  | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) |
-| DarkNet53    | 416  |    8    |   120e  |  37.5  | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) |
-| DarkNet53    | 320  |    8    |   120e  |  34.8  | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) |
-| MobileNet-V1 | 608  |    8    |   120e  |  29.3  | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) |
-| MobileNet-V1 | 416  |    8    |   120e  |  29.3  | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) |
-| MobileNet-V1 | 320  |    8    |   120e  |  27.1  | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) |
-| ResNet34     | 608  |    8    |   120e  |  36.2  | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) |
-| ResNet34     | 416  |    8    |   120e  |  34.3  | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) |
-| ResNet34     | 320  |    8    |   120e  |  31.4  | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) |
-
-**NOTE**: Yolo v3 trained in 8 GPU with total batch size as 64. Yolo v3 training data augmentations: mixup image, 
-random distort image, random crop image, random expand image, random interpolate, random flip image.
+| DarkNet53    | 608  |    8    |   270e  |  38.9  | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) |
+| DarkNet53    | 416  |    8    |   270e  |  37.5  | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) |
+| DarkNet53    | 320  |    8    |   270e  |  34.8  | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar) |
+| MobileNet-V1 | 608  |    8    |   270e  |  29.3  | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) |
+| MobileNet-V1 | 416  |    8    |   270e  |  29.3  | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) |
+| MobileNet-V1 | 320  |    8    |   270e  |  27.1  | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) |
+| ResNet34     | 608  |    8    |   270e  |  36.2  | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) |
+| ResNet34     | 416  |    8    |   270e  |  34.3  | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) |
+| ResNet34     | 320  |    8    |   270e  |  31.4  | [model](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) |
+
+**NOTE**: Yolo v3 trained in 8 GPU with total batch size as 64 and trained 270 epoches. Yolo v3 training data augmentations: mixup,
+randomly color distortion, randomly cropping, randomly expansion, randomly interpolation method, randomly flippling.
 
 ### RetinaNet
 
-| Backbone     | Size | Lr schd | Box AP | Download  |
-| :----------- | :--: | :-----: | :----: | :-------: |
-| ResNet50-FPN | 300  |  120e   |  36.0  | [model](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_r50_fpn_1x.tar) |
-| ResNet101-FPN | 300  |  120e   |  37.3  | [model](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_r101_fpn_1x.tar) |
+| Backbone      | Image/gpu | Lr schd | Box AP | Download  |
+| :-----------  | :-----: | :-----: | :----: | :-------: |
+| ResNet50-FPN  |    2    |   1x    |  36.0  | [model](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_r50_fpn_1x.tar)  |
+| ResNet101-FPN |    2    |   1x    |  37.3  | [model](https://paddlemodels.bj.bcebos.com/object_detection/retinanet_r101_fpn_1x.tar) |
+
+**Notes:** In RetinaNet, the base LR is changed to 0.01 for minibatch size 16.
 
 ### SSD on PascalVOC
 
-| Backbone     | Size | Img/gpu | Lr schd | Box AP | Download  |
+| Backbone     | Size | Image/gpu | Lr schd | Box AP | Download  |
 | :----------- | :--: | :-----: | :-----: | :----: | :-------: |
 | MobileNet v1 | 300  |    32   |   120e  |  73.2  | [model](https://paddlemodels.bj.bcebos.com/object_detection/ssd_mobilenet_v1_voc.tar) |
 
-**NOTE**: SSD trained in 2 GPU with totoal batch size as 64. SSD training data augmentations: random distort image, 
-random crop image, random expand image, random flip image.
+**NOTE**: SSD trained in 2 GPU with totoal batch size as 64 and trained 120 epoches. SSD training data augmentations: randomly color distortion,
+randomly cropping, randomly expansion, randomly flipping.