From 2ebb6e42836f347166bd7e9151c5403f7b2130df Mon Sep 17 00:00:00 2001
From: Guanghua Yu <742925032@qq.com>
Date: Thu, 4 Jul 2019 21:33:29 +0800
Subject: [PATCH] dudate config and modelzoo (#2723)
* Add faster_rcnn_x101_vd_64x4d_fpn_1x.yml
* Release faster_rcnn_r101_vd_fpn_1x.tar, faster_rcnn_x101_vd_64x4d_fpn_1x.tar, mask_rcnn_r50_2x.tar
---
README.md | 20 +--
configs/faster_rcnn_x101_vd_64x4d_fpn_1x.yml | 143 +++++++++++++++++++
docs/MODEL_ZOO.md | 4 +-
3 files changed, 156 insertions(+), 11 deletions(-)
create mode 100644 configs/faster_rcnn_x101_vd_64x4d_fpn_1x.yml
diff --git a/README.md b/README.md
index 508c08a24..306f47456 100644
--- a/README.md
+++ b/README.md
@@ -36,16 +36,16 @@ multi-GPU training.
Supported Architectures:
-| | ResNet | ResNet-vd [1](#vd) | SENet | MobileNet | DarkNet |
-|--------------------|:------:|------------------------------:|:-----:|:---------:|:-------:|
-| Faster R-CNN | ✓ | ✓ | ✓ | ✗ | ✗ |
-| Faster R-CNN + FPN | ✓ | ✓ | ✓ | ✗ | ✗ |
-| Mask R-CNN | ✓ | ✓ | ✓ | ✗ | ✗ |
-| Mask R-CNN + FPN | ✓ | ✓ | ✓ | ✗ | ✗ |
-| Cascade R-CNN | ✓ | ✗ | ✗ | ✗ | ✗ |
-| RetinaNet | ✓ | ✗ | ✗ | ✗ | ✗ |
-| Yolov3 | ✓ | ✗ | ✗ | ✓ | ✓ |
-| SSD | ✗ | ✗ | ✗ | ✓ | ✗ |
+| | ResNet | ResNet-vd [1](#vd) | ResNeXt-vd | SENet | MobileNet | DarkNet |
+|--------------------|:------:|------------------------------:|:----------:|:-----:|:---------:|:-------:|
+| Faster R-CNN | ✓ | ✓ | x | ✓ | ✗ | ✗ |
+| Faster R-CNN + FPN | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ |
+| Mask R-CNN | ✓ | ✓ | x | ✓ | ✗ | ✗ |
+| Mask R-CNN + FPN | ✓ | ✓ | x | ✓ | ✗ | ✗ |
+| Cascade R-CNN | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ |
+| RetinaNet | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ |
+| Yolov3 | ✓ | ✗ | ✗ | ✗ | ✓ | ✓ |
+| SSD | ✗ | ✗ | ✗ | ✗ | ✓ | ✗ |
[1] [ResNet-vd](https://arxiv.org/pdf/1812.01187) models offer much improved accuracy with negligible performance cost.
diff --git a/configs/faster_rcnn_x101_vd_64x4d_fpn_1x.yml b/configs/faster_rcnn_x101_vd_64x4d_fpn_1x.yml
new file mode 100644
index 000000000..60c243b2d
--- /dev/null
+++ b/configs/faster_rcnn_x101_vd_64x4d_fpn_1x.yml
@@ -0,0 +1,143 @@
+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_vd_64x4d_pretrained.tar
+weights: output/faster_rcnn_x101_vd_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
+ 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]
+ values: null
+ - !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
+ shuffle: True
+
+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
+ shuffle: False
diff --git a/docs/MODEL_ZOO.md b/docs/MODEL_ZOO.md
index 114c5749f..fdd8f40e6 100644
--- a/docs/MODEL_ZOO.md
+++ b/docs/MODEL_ZOO.md
@@ -35,6 +35,7 @@ The backbone models pretrained on ImageNet are available. All backbone models ar
| 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 | 38.2 | 33.4 | [model](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_2x.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) |
@@ -46,8 +47,9 @@ The backbone models pretrained on ImageNet are available. All backbone models ar
| 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-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 | 1x | 40.5 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_vd_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) |
+| ResNeXt101-vd-FPN | Faster | 1 | 1x | 42.2 | - | [model](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_x101_vd_64x4d_fpn_1x.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) |
--
GitLab