add Mobilenet_v3-SSDLite configs (#462)

* add mobilenet v3 configs

* fix some comment

* fix memsize

configs/ssd/ssdlite_mobilenet_v3_large.yml

+architecture: SSD
+use_gpu: true
+max_iters: 400000
+snapshot_iter: 20000
+log_smooth_window: 20
+log_iter: 20
+metric: COCO
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x1_0_ssld_pretrained.tar
+save_dir: output
+weights: output/ssdlite_mobilenet_v3_large/model_final
+# 80(label_class) + 1(background)
+num_classes: 81
+
+SSD:
+  backbone: MobileNetV3
+  multi_box_head: SSDLiteMultiBoxHead
+  output_decoder:
+    background_label: 0
+    keep_top_k: 200
+    nms_eta: 1.0
+    nms_threshold: 0.45
+    nms_top_k: 400
+    score_threshold: 0.01
+
+MobileNetV3:
+  scale: 1.0
+  model_name: large
+  extra_block_filters: [[256, 512], [128, 256], [128, 256], [64, 128]]
+  with_extra_blocks: true
+  conv_decay: 0.00004
+
+SSDLiteMultiBoxHead:
+  aspect_ratios: [[2.], [2., 3.], [2., 3.], [2., 3.], [2., 3.], [2., 3.]]
+  base_size: 320
+  steps: [16, 32, 64, 107, 160, 320]
+  flip: true
+  clip: true
+  max_ratio: 95
+  min_ratio: 20
+  offset: 0.5
+  conv_decay: 0.00004
+
+LearningRate:
+  base_lr: 0.4
+  schedulers:
+  - !CosineDecay
+    max_iters: 400000
+  - !LinearWarmup
+    start_factor: 0.33333
+    steps: 2000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2
+
+TrainReader:
+  inputs_def:
+    image_shape: [3, 320, 320]
+    fields: ['image', 'gt_bbox', 'gt_class']
+  dataset:
+    !COCODataSet
+    dataset_dir: dataset/coco
+    anno_path: annotations/instances_train2017.json
+    image_dir: train2017
+  sample_transforms:
+  - !DecodeImage
+    to_rgb: true
+  - !RandomDistort
+    brightness_lower: 0.875
+    brightness_upper: 1.125
+    is_order: true
+  - !RandomExpand
+    fill_value: [123.675, 116.28, 103.53]
+  - !RandomCrop
+    allow_no_crop: false
+  - !NormalizeBox {}
+  - !ResizeImage
+    interp: 1
+    target_size: 320
+    use_cv2: false
+  - !RandomFlipImage
+    is_normalized: false
+  - !NormalizeImage
+    mean: [0.485, 0.456, 0.406]
+    std: [0.229, 0.224, 0.225]
+    is_scale: true
+    is_channel_first: false
+  - !Permute
+    to_bgr: false
+    channel_first: true
+  batch_size: 64
+  shuffle: true
+  drop_last: true
+  # Number of working threads/processes. To speed up, can be set to 16 or 32 etc.
+  worker_num: 8
+  # Size of shared memory used in result queue. After increasing `worker_num`, need expand `memsize`.
+  memsize: 8G
+  # Buffer size for multi threads/processes.one instance in buffer is one batch data.
+  # To speed up, can be set to 64 or 128 etc.
+  bufsize: 32
+  use_process: true
+
+
+EvalReader:
+  inputs_def:
+    image_shape: [3, 320, 320]
+    fields: ['image', 'gt_bbox', 'gt_class', 'im_shape', 'im_id']
+  dataset:
+    !COCODataSet
+    dataset_dir: dataset/coco
+    anno_path: annotations/instances_val2017.json
+    image_dir: val2017
+  sample_transforms:
+  - !DecodeImage
+    to_rgb: true
+  - !NormalizeBox {}
+  - !ResizeImage
+    interp: 1
+    target_size: 320
+    use_cv2: false
+  - !NormalizeImage
+    mean: [0.485, 0.456, 0.406]
+    std: [0.229, 0.224, 0.225]
+    is_scale: true
+    is_channel_first: false
+  - !Permute
+    to_bgr: false
+    channel_first: True
+  batch_size: 8
+  worker_num: 8
+  bufsize: 32
+  use_process: false
+
+TestReader:
+  inputs_def:
+    image_shape: [3,320,320]
+    fields: ['image', 'im_id', 'im_shape']
+  dataset:
+    !ImageFolder
+    anno_path: annotations/instances_val2017.json
+  sample_transforms:
+  - !DecodeImage
+    to_rgb: true
+  - !ResizeImage
+    interp: 1
+    max_size: 0
+    target_size: 320
+    use_cv2: false
+  - !NormalizeImage
+    mean: [0.485, 0.456, 0.406]
+    std: [0.229, 0.224, 0.225]
+    is_scale: true
+    is_channel_first: false
+  - !Permute
+    to_bgr: false
+    channel_first: True
+  batch_size: 1

configs/ssd/ssdlite_mobilenet_v3_small.yml

+architecture: SSD
+use_gpu: true
+max_iters: 400000
+snapshot_iter: 20000
+log_smooth_window: 20
+log_iter: 20
+metric: COCO
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_small_x1_0_pretrained.tar
+save_dir: output
+weights: output/ssd_mobilenet_v3_small/model_final
+# 80(label_class) + 1(background)
+num_classes: 81
+
+SSD:
+  backbone: MobileNetV3
+  multi_box_head: SSDLiteMultiBoxHead
+  output_decoder:
+    background_label: 0
+    keep_top_k: 200
+    nms_eta: 1.0
+    nms_threshold: 0.45
+    nms_top_k: 400
+    score_threshold: 0.01
+
+MobileNetV3:
+  scale: 1.0
+  model_name: small
+  extra_block_filters: [[256, 512], [128, 256], [128, 256], [64, 128]]
+  with_extra_blocks: true
+  conv_decay: 0.00004
+
+SSDLiteMultiBoxHead:
+  aspect_ratios: [[2.], [2., 3.], [2., 3.], [2., 3.], [2., 3.], [2., 3.]]
+  base_size: 320
+  steps: [16, 32, 64, 107, 160, 320]
+  flip: true
+  clip: true
+  max_ratio: 95
+  min_ratio: 20
+  offset: 0.5
+  conv_decay: 0.00004
+
+LearningRate:
+  base_lr: 0.4
+  schedulers:
+  - !CosineDecay
+    max_iters: 400000
+  - !LinearWarmup
+    start_factor: 0.33333
+    steps: 2000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2
+
+TrainReader:
+  inputs_def:
+    image_shape: [3, 320, 320]
+    fields: ['image', 'gt_bbox', 'gt_class']
+  dataset:
+    !COCODataSet
+    dataset_dir: dataset/coco
+    anno_path: annotations/instances_train2017.json
+    image_dir: train2017
+  sample_transforms:
+  - !DecodeImage
+    to_rgb: true
+  - !RandomDistort
+    brightness_lower: 0.875
+    brightness_upper: 1.125
+    is_order: true
+  - !RandomExpand
+    fill_value: [123.675, 116.28, 103.53]
+  - !RandomCrop
+    allow_no_crop: false
+  - !NormalizeBox {}
+  - !ResizeImage
+    interp: 1
+    target_size: 320
+    use_cv2: false
+  - !RandomFlipImage
+    is_normalized: false
+  - !NormalizeImage
+    mean: [0.485, 0.456, 0.406]
+    std: [0.229, 0.224, 0.225]
+    is_scale: true
+    is_channel_first: false
+  - !Permute
+    to_bgr: false
+    channel_first: true
+  batch_size: 64
+  shuffle: true
+  drop_last: true
+  # Number of working threads/processes. To speed up, can be set to 16 or 32 etc.
+  worker_num: 8
+  # Size of shared memory used in result queue. After increasing `worker_num`, need expand `memsize`.
+  memsize: 8G
+  # Buffer size for multi threads/processes.one instance in buffer is one batch data.
+  # To speed up, can be set to 64 or 128 etc.
+  bufsize: 32
+  use_process: true
+
+
+EvalReader:
+  inputs_def:
+    image_shape: [3, 320, 320]
+    fields: ['image', 'gt_bbox', 'gt_class', 'im_shape', 'im_id']
+  dataset:
+    !COCODataSet
+    dataset_dir: dataset/coco
+    anno_path: annotations/instances_val2017.json
+    image_dir: val2017
+  sample_transforms:
+  - !DecodeImage
+    to_rgb: true
+  - !NormalizeBox {}
+  - !ResizeImage
+    interp: 1
+    target_size: 320
+    use_cv2: false
+  - !NormalizeImage
+    mean: [0.485, 0.456, 0.406]
+    std: [0.229, 0.224, 0.225]
+    is_scale: true
+    is_channel_first: false
+  - !Permute
+    to_bgr: false
+    channel_first: True
+  batch_size: 8
+  worker_num: 8
+  bufsize: 32
+  use_process: false
+
+TestReader:
+  inputs_def:
+    image_shape: [3,320,320]
+    fields: ['image', 'im_id', 'im_shape']
+  dataset:
+    !ImageFolder
+    anno_path: annotations/instances_val2017.json
+  sample_transforms:
+  - !DecodeImage
+    to_rgb: true
+  - !ResizeImage
+    interp: 1
+    max_size: 0
+    target_size: 320
+    use_cv2: false
+  - !NormalizeImage
+    mean: [0.485, 0.456, 0.406]
+    std: [0.229, 0.224, 0.225]
+    is_scale: true
+    is_channel_first: false
+  - !Permute
+    to_bgr: false
+    channel_first: True
+  batch_size: 1

docs/MODEL_ZOO.md

@@ -176,6 +176,15 @@ results of image size 608/416/320 above. Deformable conv is added on stage 5 of
 
 **Notes:** In RetinaNet, the base LR is changed to 0.01 for minibatch size 16.
 
+### SSDLite
+
+| Backbone | Size | Image/gpu | Lr schd | Inf time (fps) | Box AP |                           Download                           |
+| :------: | :--: | :-------: | :-----: | :------------: | :----: | :----------------------------------------------------------: |
+| MobileNet_v3 small | 320 | 64 | 40w | - | 16.6 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mobilenet_v3_ssdlite_small.tar) |
+| MobileNet_v3 large | 320 | 64 | 40w | - | 22.8 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mobilenet_v3_ssdlite_large.tar) |
+
+**Notes:** MobileNet_v3-SSDLite is trained in 8 GPU with total batch size as 512 and uses cosine decay strategy to train.
+
 ### SSD
 
 | Backbone | Size | Image/gpu | Lr schd | Inf time (fps) | Box AP |                           Download                           |

docs/MODEL_ZOO_cn.md

@@ -129,9 +129,9 @@ Paddle提供基于ImageNet的骨架网络预训练模型。所有预训练模型
 | MobileNet-V1        | ImageNet | 608  |  否    |    8    |   270e  |    78.302     |  29.3  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) |
 | MobileNet-V1        | ImageNet | 416  |  否    |    8    |   270e  |      -        |  29.3  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) |
 | MobileNet-V1        | ImageNet | 320  |  否    |    8    |   270e  |      -        |  27.1  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar) |
-| MobileNet-V1        | ImageNet | 608  |  否    |    8    |   270e  |      -        |  31.6  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3.pdparams) |
-| MobileNet-V1        | ImageNet | 416  |  否    |    8    |   270e  |      -        |  29.9  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3.pdparams) |
-| MobileNet-V1        | ImageNet | 320  |  否    |    8    |   270e  |      -        |  27.1  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3.pdparams) |
+| MobileNet-V3        | ImageNet | 608  |  否    |    8    |   270e  |      -        |  31.6  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3.pdparams) |
+| MobileNet-V3        | ImageNet | 416  |  否    |    8    |   270e  |      -        |  29.9  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3.pdparams) |
+| MobileNet-V3        | ImageNet | 320  |  否    |    8    |   270e  |      -        |  27.1  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3.pdparams) |
 | ResNet34            | ImageNet | 608  |  否    |    8    |   270e  |    63.356     |  36.2  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) |
 | ResNet34            | ImageNet | 416  |  否    |    8    |   270e  |      -        |  34.3  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) |
 | ResNet34            | ImageNet | 320  |  否    |    8    |   270e  |      -        |  31.4  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar) |
@@ -168,6 +168,15 @@ Paddle提供基于ImageNet的骨架网络预训练模型。所有预训练模型
 
 **注意事项:** RetinaNet系列模型中，在总batch size为16下情况下，初始学习率改为0.01。
 
+### SSDLite
+
+|  骨架网络     | 输入尺寸 | 每张GPU图片个数 | 学习率策略|推理时间(fps) | Box AP | 下载 |
+| :----------: | :--: | :-----: | :-----: |:------------: |:----: | :-------: |
+| MobileNet_v3 small | 320 | 64 | 40w | - | 16.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mobilenet_v3_ssdlite_small.tar) |
+| MobileNet_v3 large | 320 | 64 | 40w | - | 22.8 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/mobilenet_v3_ssdlite_large.tar) |
+
+**注意事项:** MobileNet_v3-SSDLite 使用学习率余弦衰减策略在8卡GPU下总batch size为512。
+
 ### SSD
 
 |  骨架网络     | 输入尺寸 | 每张GPU图片个数 | 学习率策略|推理时间(fps) | Box AP | 下载 |

ppdet/modeling/backbones/mobilenet_v3.py

+# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
 import paddle.fluid as fluid
 from paddle.fluid.param_attr import ParamAttr
 from paddle.fluid.regularizer import L2Decay
@@ -10,6 +24,19 @@ __all__ = ['MobileNetV3']
 
 @register
 class MobileNetV3():
+    """
+    MobileNet v3, see https://arxiv.org/abs/1905.02244
+    Args:
+	scale (float): scaling factor for convolution groups proportion of mobilenet_v3.
+        model_name (str): There are two modes, small and large.
+        norm_type (str): normalization type, 'bn' and 'sync_bn' are supported.
+        norm_decay (float): weight decay for normalization layer weights.
+        conv_decay (float): weight decay for convolution layer weights.
+        with_extra_blocks (bool): if extra blocks should be added.
+        extra_block_filters (list): number of filter for each extra block.
+    """
+    __shared__ = ['norm_type']
+
     def __init__(self,
                  scale=1.0,
                  model_name='small',