Add solov2_mobilenetv3 (#1642)

* add solov2_mobilenetv3

configs/solov2/README.md

@@ -14,6 +14,7 @@ SOLOv2 (Segmenting Objects by Locations) is a fast instance segmentation framewo
 
 | Backbone                | Multi-scale training  | Lr schd | Inf time (V100) | Mask AP |         Download                  | Configs |
 | :---------------------: | :-------------------: | :-----: | :------------: | :-----: | :---------: | :------------------------: |
+| Mobilenetv3-FPN                 |  True                |   3x    |     20.0ms          |  30.0   | [model](https://paddlemodels.bj.bcebos.com/object_detection/solov2_mobilenetv3_fpn_448_3x.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/solov2/solov2_mobilenetv3_fpn_448_3x.yml) |
 | R50-FPN                 |  False                |   1x    |     45.7ms          |  35.6   | [model](https://paddlemodels.bj.bcebos.com/object_detection/solov2_r50_fpn_1x.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/solov2/solov2_r50_fpn_1x.yml) |
 | R50-FPN                 |  True                |   3x    |     45.7ms          |  37.9   | [model](https://paddlemodels.bj.bcebos.com/object_detection/solov2_r50_fpn_3x.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/solov2/solov2_r50_fpn_3x.yml) |
 | R101-VD-FPN                 |  True               |   3x    |     82.6ms       |  42.6   | [model](https://paddlemodels.bj.bcebos.com/object_detection/solov2_r101_vd_fpn_3x.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/solov2/solov2_r101_vd_fpn_3x.yml) |

configs/solov2/solov2_light_448_reader.yml

+TrainReader:
+  batch_size: 4
+  worker_num: 2
+  inputs_def:
+    fields: ['image', 'im_id', 'gt_segm']
+  dataset:
+    !COCODataSet
+    dataset_dir: dataset/coco
+    anno_path: annotations/instances_train2017.json
+    image_dir: train2017
+  sample_transforms:
+  - !DecodeImage
+    to_rgb: true
+  - !Poly2Mask {}
+  - !ColorDistort {}
+  - !RandomCrop
+    is_mask_crop: True
+  - !ResizeImage
+    target_size: [352, 384, 416, 448, 480, 512]
+    max_size: 768
+    interp: 1
+    use_cv2: true
+    resize_box: true
+  - !RandomFlipImage
+    prob: 0.5
+  - !NormalizeImage
+    is_channel_first: false
+    is_scale: true
+    mean: [0.485,0.456,0.406]
+    std: [0.229, 0.224,0.225]
+  - !Permute
+    to_bgr: false
+    channel_first: true
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+  - !Gt2Solov2Target
+    num_grids: [40, 36, 24, 16, 12]
+    scale_ranges: [[1, 56], [28, 112], [56, 224], [112, 448], [224, 896]]
+    coord_sigma: 0.2
+  shuffle: True
+
+EvalReader:
+  inputs_def:
+    fields: ['image', 'im_info', 'im_id']
+  dataset:
+    !COCODataSet
+    image_dir: val2017
+    anno_path: annotations/instances_val2017.json
+    dataset_dir: dataset/coco
+  sample_transforms:
+  - !DecodeImage
+    to_rgb: true
+  - !ResizeImage
+    interp: 1
+    max_size: 768
+    target_size: 448
+    use_cv2: true
+  - !NormalizeImage
+    is_channel_first: false
+    is_scale: true
+    mean: [0.485,0.456,0.406]
+    std: [0.229, 0.224,0.225]
+  - !Permute
+    channel_first: true
+    to_bgr: false
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+    use_padded_im_info: false
+  # only support batch_size=1 when evaluation
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+  drop_empty: false
+  worker_num: 2
+
+TestReader:
+  inputs_def:
+    fields: ['image', 'im_info', 'im_id', 'im_shape']
+  dataset:
+    !ImageFolder
+    anno_path: dataset/coco/annotations/instances_val2017.json
+  sample_transforms:
+  - !DecodeImage
+    to_rgb: true
+  - !ResizeImage
+    interp: 1
+    max_size: 768
+    target_size: 448
+    use_cv2: true
+  - !NormalizeImage
+    is_channel_first: false
+    is_scale: true
+    mean: [0.485,0.456,0.406]
+    std: [0.229, 0.224,0.225]
+  - !Permute
+    channel_first: true
+    to_bgr: false
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+    use_padded_im_info: false

configs/solov2/solov2_mobilenetv3_fpn_448_3x.yml

+architecture: SOLOv2
+use_gpu: true
+max_iters: 135000
+snapshot_iter: 20000
+log_smooth_window: 20
+save_dir: output
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x1_0_ssld_pretrained.tar
+metric: COCO
+weights: output/solov2/solov2_mobilenetv3_fpn_448_3x/model_final
+num_classes: 81
+use_ema: true
+ema_decay: 0.9998
+
+SOLOv2:
+  backbone: MobileNetV3RCNN
+  fpn: FPN
+  bbox_head: SOLOv2Head
+  mask_head: SOLOv2MaskHead
+
+MobileNetV3RCNN:
+  norm_type: bn
+  freeze_norm: true
+  norm_decay: 0.0
+  feature_maps: [2, 3, 4, 6]
+  conv_decay: 0.00001
+  lr_mult_list: [0.25, 0.25, 0.5, 0.5, 0.75]
+  scale: 1.0
+  model_name: large
+
+FPN:
+  max_level: 6
+  min_level: 2
+  num_chan: 256
+  spatial_scale: [0.03125, 0.0625, 0.125, 0.25]
+  reverse_out: True
+
+SOLOv2Head:
+  seg_feat_channels: 256
+  stacked_convs: 2
+  num_grids: [40, 36, 24, 16, 12]
+  kernel_out_channels: 128
+  solov2_loss: SOLOv2Loss
+  mask_nms: MaskMatrixNMS
+  drop_block: True
+
+SOLOv2MaskHead:
+  in_channels: 128
+  out_channels: 128
+  start_level: 0
+  end_level: 3
+
+SOLOv2Loss:
+  ins_loss_weight: 3.0
+  focal_loss_gamma: 2.0
+  focal_loss_alpha: 0.25
+
+MaskMatrixNMS:
+  pre_nms_top_n: 500
+  post_nms_top_n: 100
+
+LearningRate:
+  base_lr: 0.02
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [90000, 120000]
+  - !LinearWarmup
+    start_factor: 0.
+    steps: 1000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0001
+    type: L2
+
+_READER_: 'solov2_light_448_reader.yml'