add blazeface nas1 result based on latency (#235)

* add blazeface_nas1

configs/face_detection/blazeface_nas_v2.yml

+architecture: BlazeFace
+max_iters: 320000
+pretrain_weights:
+use_gpu: true
+snapshot_iter: 10000
+log_smooth_window: 20
+log_iter: 20
+metric: WIDERFACE
+save_dir: output
+weights: output/blazeface_nas/model_final/
+# 1(label_class) + 1(background)
+num_classes: 2
+
+BlazeFace:
+  backbone: BlazeNet
+  output_decoder:
+    keep_top_k: 750
+    nms_threshold: 0.3
+    nms_top_k: 5000
+    score_threshold: 0.01
+  min_sizes: [[16.,24.], [32., 48., 64., 80., 96., 128.]]
+  use_density_prior_box: false
+
+BlazeNet:
+  blaze_filters: [[12, 12], [12, 12, 2], [12, 12]]
+  double_blaze_filters: [[12, 16, 32, 2], [32, 32, 32], [32, 16, 72, 2], [72, 24, 72]]
+  with_extra_blocks: true
+  lite_edition: false
+
+LearningRate:
+  base_lr: 0.001
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [240000, 300000]
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.0
+    type: RMSPropOptimizer
+  regularizer:
+    factor: 0.0005
+    type: L2
+
+TrainReader:
+  inputs_def:
+    image_shape: [3, 640, 640]
+    fields: ['image', 'gt_bbox', 'gt_class']
+  dataset:
+    !WIDERFaceDataSet
+    dataset_dir: dataset/wider_face
+    anno_path: wider_face_split/wider_face_train_bbx_gt.txt
+    image_dir: WIDER_train/images
+  sample_transforms:
+  - !DecodeImage
+    to_rgb: true
+  - !NormalizeBox {}
+  - !RandomDistort
+    brightness_lower: 0.875
+    brightness_upper: 1.125
+    is_order: true
+  - !ExpandImage
+    max_ratio: 4
+    prob: 0.5
+  - !CropImageWithDataAchorSampling
+    anchor_sampler:
+    - [1, 10, 1.0, 1.0, 1.0, 1.0, 0.0, 0.0, 0.2, 0.0]
+    batch_sampler:
+    - [1, 50, 1.0, 1.0, 1.0, 1.0, 0.0, 0.0, 1.0, 0.0]
+    - [1, 50, 0.3, 1.0, 1.0, 1.0, 0.0, 0.0, 1.0, 0.0]
+    - [1, 50, 0.3, 1.0, 1.0, 1.0, 0.0, 0.0, 1.0, 0.0]
+    - [1, 50, 0.3, 1.0, 1.0, 1.0, 0.0, 0.0, 1.0, 0.0]
+    - [1, 50, 0.3, 1.0, 1.0, 1.0, 0.0, 0.0, 1.0, 0.0]
+    target_size: 640
+  - !RandomInterpImage
+    target_size: 640
+  - !RandomFlipImage
+    is_normalized: true
+  - !Permute {}
+  - !NormalizeImage
+    is_scale: false
+    mean: [104, 117, 123]
+    std: [127.502231, 127.502231, 127.502231]
+  batch_size: 8
+  use_process: true
+  worker_num: 8
+  shuffle: true
+
+EvalReader:
+  inputs_def:
+    fields: ['image', 'im_id']
+  dataset:
+    !WIDERFaceDataSet
+    dataset_dir: dataset/wider_face
+    anno_path: wider_face_split/wider_face_val_bbx_gt.txt
+    image_dir: WIDER_val/images
+  sample_transforms:
+  - !DecodeImage
+    to_rgb: true
+  - !NormalizeBox {}
+  - !ResizeImage
+    interp: 1
+    target_size: 640
+    use_cv2: false
+  - !Permute {}
+  - !NormalizeImage
+    is_scale: false
+    mean: [104, 117, 123]
+    std: [127.502231, 127.502231, 127.502231]
+  batch_size: 1
+
+TestReader:
+  inputs_def:
+    image_shape: [3,640,640]
+    fields: ['image', 'im_id', 'im_shape']
+  dataset:
+    !ImageFolder
+    use_default_label: true
+  sample_transforms:
+  - !DecodeImage
+    to_rgb: true
+  - !ResizeImage
+    interp: 1
+    target_size: 640
+    use_cv2: false
+  - !Permute {}
+  - !NormalizeImage
+    is_scale: false
+    mean: [104, 117, 123]
+    std: [127.502231, 127.502231, 127.502231]
+  batch_size: 1

docs/featured_model/FACE_DETECTION.md

@@ -36,6 +36,7 @@ FaceDetection的目标是提供高效、高速的人脸检测解决方案，包
 | BlazeFace    | 原始版本 | 640  |    8    | 32w     | **0.915** | **0.892**  | **0.797** | [模型](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_original.tar) |
 | BlazeFace    | Lite版本    | 640  |    8    | 32w     | 0.909     | 0.885      | 0.781     | [模型](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_lite.tar) |
 | BlazeFace    | NAS版本    | 640  |    8    | 32w     | 0.837     | 0.807      | 0.658     | [模型](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_nas.tar) |
+| BlazeFace    | NAS_V2版本 | 640  |    8    | 32W     | 0.870     | 0.837      | 0.685     | [模型](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_nas2.tar)
 | FaceBoxes    | 原始版本 | 640  |    8    | 32w     | 0.878     | 0.851      | 0.576     | [模型](https://paddlemodels.bj.bcebos.com/object_detection/faceboxes_original.tar) |
 | FaceBoxes    | Lite版本   | 640  |    8    | 32w     | 0.901     | 0.875      | 0.760     | [模型](https://paddlemodels.bj.bcebos.com/object_detection/faceboxes_lite.tar) |
 
@@ -254,6 +255,7 @@ cd dataset/fddb/evaluation
 - 原始版本: 参考原始论文复现；
 - Lite版本: 使用3x3卷积替换5x5卷积，更少的网络层数和通道数；
 - NAS版本: 使用神经网络搜索算法构建网络结构，相比于`Lite`版本，NAS版本需要更少的网络层数和通道数。
+- NAS_V2版本1: 基于PaddleSlim中SANAS算法在blazeface-NAS的基础上搜索出来的结构，相比`NAS`版本，NAS_V2版本的精度平均高出3个点，在855芯片上的硬件延时相对`NAS`版本仅增加5%。
 
 ### FaceBoxes
 **简介:**  

docs/featured_model/FACE_DETECTION_en.md

@@ -40,6 +40,7 @@ optimized network structure.
 | BlazeFace    | Original | 640  |    8    | 32w     | **0.915** | **0.892**  | **0.797** | [model](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_original.tar) |
 | BlazeFace    | Lite     | 640  |    8    | 32w     | 0.909     | 0.885      | 0.781     | [model](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_lite.tar) |
 | BlazeFace    | NAS      | 640  |    8    | 32w     | 0.837     | 0.807      | 0.658     | [model](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_nas.tar) |
+| BlazeFace    | NAS_V2   | 640  |    8    | 32W     | 0.870     | 0.837      | 0.685     | [model](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_nas2.tar)
 | FaceBoxes    | Original | 640  |    8    | 32w     | 0.878     | 0.851      | 0.576     | [model](https://paddlemodels.bj.bcebos.com/object_detection/faceboxes_original.tar) |
 | FaceBoxes    | Lite     | 640  |    8    | 32w     | 0.901     | 0.875      | 0.760     | [model](https://paddlemodels.bj.bcebos.com/object_detection/faceboxes_lite.tar) |
 
@@ -275,6 +276,7 @@ regression parameters of a bounding box as a weighted mean between the overlappi
 - Lite: Replace 5x5 conv with 3x3 conv, fewer network layers and conv channels.
 - NAS: use `Neural Architecture Search` algorithm to optimized network structure,
 less network layer and conv channel number than `Lite`.
+- NAS_V2: this version of model architecture searched based on blazeface-NAS by the SANAS in PaddleSlim, the average precision is 3% higher than blazeface-NAS, the latency is only 5% higher than blazeface-NAS on chip 855.
 
 ### FaceBoxes
 **Introduction:**