更换文档检测模型

2024-08-27 14:42:45 +08:00
parent aea6f19951
commit 1514e09c40
2072 changed files with 254336 additions and 4967 deletions
--- a/paddle_detection/configs/cascade_rcnn/README.md
+++ b/paddle_detection/configs/cascade_rcnn/README.md
@@ -0,0 +1,28 @@
+# Cascade R-CNN: High Quality Object Detection and Instance Segmentation
+
+## Model Zoo
+
+| 骨架网络             | 网络类型       | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | Mask AP |                           下载                          | 配置文件 |
+| :------------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----: | :-----------------------------------------------------: | :-----: |
+| ResNet50-FPN         | Cascade Faster         |    1    |   1x    |     ----     |  41.1  |    -    | [下载链接](https://paddledet.bj.bcebos.com/models/cascade_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/cascade_rcnn/cascade_rcnn_r50_fpn_1x_coco.yml) |
+| ResNet50-FPN         | Cascade Mask         |    1    |   1x    |     ----     |  41.8  |    36.3    | [下载链接](https://paddledet.bj.bcebos.com/models/cascade_mask_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco.yml) |
+| ResNet50-vd-SSLDv2-FPN | Cascade Faster         |    1    |   1x    |     ----     |  44.4  |    -    | [下载链接](https://paddledet.bj.bcebos.com/models/cascade_rcnn_r50_vd_fpn_ssld_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/cascade_rcnn/cascade_rcnn_r50_vd_fpn_ssld_1x_coco.yml) |
+| ResNet50-vd-SSLDv2-FPN | Cascade Faster         |    1    |   2x    |     ----     |  45.0  |    -    | [下载链接](https://paddledet.bj.bcebos.com/models/cascade_rcnn_r50_vd_fpn_ssld_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/cascade_rcnn/cascade_rcnn_r50_vd_fpn_ssld_2x_coco.yml) |
+| ResNet50-vd-SSLDv2-FPN | Cascade Mask         |    1    |   1x    |     ----     |  44.9  |    39.1    | [下载链接](https://paddledet.bj.bcebos.com/models/cascade_mask_rcnn_r50_vd_fpn_ssld_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/cascade_rcnn/cascade_mask_rcnn_r50_vd_fpn_ssld_1x_coco.yml) |
+| ResNet50-vd-SSLDv2-FPN | Cascade Mask         |    1    |   2x    |     ----     |  45.7  |    39.7    | [下载链接](https://paddledet.bj.bcebos.com/models/cascade_mask_rcnn_r50_vd_fpn_ssld_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/cascade_rcnn/cascade_mask_rcnn_r50_vd_fpn_ssld_2x_coco.yml) |
+
+
+## Citations
+```
+@article{Cai_2019,
+   title={Cascade R-CNN: High Quality Object Detection and Instance Segmentation},
+   ISSN={1939-3539},
+   url={http://dx.doi.org/10.1109/tpami.2019.2956516},
+   DOI={10.1109/tpami.2019.2956516},
+   journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
+   publisher={Institute of Electrical and Electronics Engineers (IEEE)},
+   author={Cai, Zhaowei and Vasconcelos, Nuno},
+   year={2019},
+   pages={1–1}
+}
+```
--- a/paddle_detection/configs/cascade_rcnn/_base_/cascade_fpn_reader.yml
+++ b/paddle_detection/configs/cascade_rcnn/_base_/cascade_fpn_reader.yml
@@ -0,0 +1,40 @@
+worker_num: 2
+TrainReader:
+  sample_transforms:
+  - Decode: {}
+  - RandomResize: {target_size: [[640, 1333], [672, 1333], [704, 1333], [736, 1333], [768, 1333], [800, 1333]], interp: 2, keep_ratio: True}
+  - RandomFlip: {prob: 0.5}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: true
+  drop_last: true
+  collate_batch: false
+
+
+EvalReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+
+TestReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
--- a/paddle_detection/configs/cascade_rcnn/_base_/cascade_mask_fpn_reader.yml
+++ b/paddle_detection/configs/cascade_rcnn/_base_/cascade_mask_fpn_reader.yml
@@ -0,0 +1,40 @@
+worker_num: 2
+TrainReader:
+  sample_transforms:
+  - Decode: {}
+  - RandomResize: {target_size: [[640, 1333], [672, 1333], [704, 1333], [736, 1333], [768, 1333], [800, 1333]], interp: 2, keep_ratio: True}
+  - RandomFlip: {prob: 0.5}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: true
+  drop_last: true
+  collate_batch: false
+
+
+EvalReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+
+TestReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
--- a/paddle_detection/configs/cascade_rcnn/_base_/cascade_mask_rcnn_r50_fpn.yml
+++ b/paddle_detection/configs/cascade_rcnn/_base_/cascade_mask_rcnn_r50_fpn.yml
@@ -0,0 +1,97 @@
+architecture: CascadeRCNN
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_cos_pretrained.pdparams
+
+
+CascadeRCNN:
+  backbone: ResNet
+  neck: FPN
+  rpn_head: RPNHead
+  bbox_head: CascadeHead
+  mask_head: MaskHead
+  # post process
+  bbox_post_process: BBoxPostProcess
+  mask_post_process: MaskPostProcess
+
+ResNet:
+  # index 0 stands for res2
+  depth: 50
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+
+FPN:
+  out_channel: 256
+
+RPNHead:
+  anchor_generator:
+    aspect_ratios: [0.5, 1.0, 2.0]
+    anchor_sizes: [[32], [64], [128], [256], [512]]
+    strides: [4, 8, 16, 32, 64]
+  rpn_target_assign:
+    batch_size_per_im: 256
+    fg_fraction: 0.5
+    negative_overlap: 0.3
+    positive_overlap: 0.7
+    use_random: True
+  train_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 2000
+    post_nms_top_n: 2000
+    topk_after_collect: True
+  test_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 1000
+    post_nms_top_n: 1000
+
+
+CascadeHead:
+  head: CascadeTwoFCHead
+  roi_extractor:
+    resolution: 7
+    sampling_ratio: 0
+    aligned: True
+  bbox_assigner: BBoxAssigner
+
+BBoxAssigner:
+  batch_size_per_im: 512
+  bg_thresh: 0.5
+  fg_thresh: 0.5
+  fg_fraction: 0.25
+  cascade_iou: [0.5, 0.6, 0.7]
+  use_random: True
+
+CascadeTwoFCHead:
+  out_channel: 1024
+
+BBoxPostProcess:
+  decode:
+    name: RCNNBox
+    prior_box_var: [30.0, 30.0, 15.0, 15.0]
+  nms:
+    name: MultiClassNMS
+    keep_top_k: 100
+    score_threshold: 0.05
+    nms_threshold: 0.5
+
+
+MaskHead:
+  head: MaskFeat
+  roi_extractor:
+    resolution: 14
+    sampling_ratio: 0
+    aligned: True
+  mask_assigner: MaskAssigner
+  share_bbox_feat: False
+
+MaskFeat:
+  num_convs: 4
+  out_channel: 256
+
+MaskAssigner:
+  mask_resolution: 28
+
+MaskPostProcess:
+  binary_thresh: 0.5
--- a/paddle_detection/configs/cascade_rcnn/_base_/cascade_rcnn_r50_fpn.yml
+++ b/paddle_detection/configs/cascade_rcnn/_base_/cascade_rcnn_r50_fpn.yml
@@ -0,0 +1,75 @@
+architecture: CascadeRCNN
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_cos_pretrained.pdparams
+
+
+CascadeRCNN:
+  backbone: ResNet
+  neck: FPN
+  rpn_head: RPNHead
+  bbox_head: CascadeHead
+  # post process
+  bbox_post_process: BBoxPostProcess
+
+ResNet:
+  # index 0 stands for res2
+  depth: 50
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+
+FPN:
+  out_channel: 256
+
+RPNHead:
+  anchor_generator:
+    aspect_ratios: [0.5, 1.0, 2.0]
+    anchor_sizes: [[32], [64], [128], [256], [512]]
+    strides: [4, 8, 16, 32, 64]
+  rpn_target_assign:
+    batch_size_per_im: 256
+    fg_fraction: 0.5
+    negative_overlap: 0.3
+    positive_overlap: 0.7
+    use_random: True
+  train_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 2000
+    post_nms_top_n: 2000
+    topk_after_collect: True
+  test_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 1000
+    post_nms_top_n: 1000
+
+
+CascadeHead:
+  head: CascadeTwoFCHead
+  roi_extractor:
+    resolution: 7
+    sampling_ratio: 0
+    aligned: True
+  bbox_assigner: BBoxAssigner
+
+BBoxAssigner:
+  batch_size_per_im: 512
+  bg_thresh: 0.5
+  fg_thresh: 0.5
+  fg_fraction: 0.25
+  cascade_iou: [0.5, 0.6, 0.7]
+  use_random: True
+
+CascadeTwoFCHead:
+  out_channel: 1024
+
+BBoxPostProcess:
+  decode:
+    name: RCNNBox
+    prior_box_var: [30.0, 30.0, 15.0, 15.0]
+  nms:
+    name: MultiClassNMS
+    keep_top_k: 100
+    score_threshold: 0.05
+    nms_threshold: 0.5
--- a/paddle_detection/configs/cascade_rcnn/_base_/optimizer_1x.yml
+++ b/paddle_detection/configs/cascade_rcnn/_base_/optimizer_1x.yml
@@ -0,0 +1,19 @@
+epoch: 12
+
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [8, 11]
+  - !LinearWarmup
+    start_factor: 0.001
+    steps: 1000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0001
+    type: L2
--- a/paddle_detection/configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco.yml
+++ b/paddle_detection/configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco.yml
@@ -0,0 +1,8 @@
+_BASE_: [
+  '../datasets/coco_instance.yml',
+  '../runtime.yml',
+  '_base_/optimizer_1x.yml',
+  '_base_/cascade_mask_rcnn_r50_fpn.yml',
+  '_base_/cascade_mask_fpn_reader.yml',
+]
+weights: output/cascade_mask_rcnn_r50_fpn_1x_coco/model_final
--- a/paddle_detection/configs/cascade_rcnn/cascade_mask_rcnn_r50_vd_fpn_ssld_1x_coco.yml
+++ b/paddle_detection/configs/cascade_rcnn/cascade_mask_rcnn_r50_vd_fpn_ssld_1x_coco.yml
@@ -0,0 +1,18 @@
+_BASE_: [
+  '../datasets/coco_instance.yml',
+  '../runtime.yml',
+  '_base_/optimizer_1x.yml',
+  '_base_/cascade_mask_rcnn_r50_fpn.yml',
+  '_base_/cascade_mask_fpn_reader.yml',
+]
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_vd_ssld_v2_pretrained.pdparams
+weights: output/cascade_mask_rcnn_r50_vd_fpn_ssld_1x_coco/model_final
+
+ResNet:
+  depth: 50
+  variant: d
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+  lr_mult_list: [0.05, 0.05, 0.1, 0.15]
--- a/paddle_detection/configs/cascade_rcnn/cascade_mask_rcnn_r50_vd_fpn_ssld_2x_coco.yml
+++ b/paddle_detection/configs/cascade_rcnn/cascade_mask_rcnn_r50_vd_fpn_ssld_2x_coco.yml
@@ -0,0 +1,29 @@
+_BASE_: [
+  '../datasets/coco_instance.yml',
+  '../runtime.yml',
+  '_base_/optimizer_1x.yml',
+  '_base_/cascade_mask_rcnn_r50_fpn.yml',
+  '_base_/cascade_mask_fpn_reader.yml',
+]
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_vd_ssld_v2_pretrained.pdparams
+weights: output/cascade_mask_rcnn_r50_vd_fpn_ssld_2x_coco/model_final
+
+ResNet:
+  depth: 50
+  variant: d
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+  lr_mult_list: [0.05, 0.05, 0.1, 0.15]
+
+epoch: 24
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [12, 22]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
--- a/paddle_detection/configs/cascade_rcnn/cascade_rcnn_r50_fpn_1x_coco.yml
+++ b/paddle_detection/configs/cascade_rcnn/cascade_rcnn_r50_fpn_1x_coco.yml
@@ -0,0 +1,8 @@
+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  '_base_/optimizer_1x.yml',
+  '_base_/cascade_rcnn_r50_fpn.yml',
+  '_base_/cascade_fpn_reader.yml',
+]
+weights: output/cascade_rcnn_r50_fpn_1x_coco/model_final
--- a/paddle_detection/configs/cascade_rcnn/cascade_rcnn_r50_vd_fpn_ssld_1x_coco.yml
+++ b/paddle_detection/configs/cascade_rcnn/cascade_rcnn_r50_vd_fpn_ssld_1x_coco.yml
@@ -0,0 +1,18 @@
+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  '_base_/optimizer_1x.yml',
+  '_base_/cascade_rcnn_r50_fpn.yml',
+  '_base_/cascade_fpn_reader.yml',
+]
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_vd_ssld_v2_pretrained.pdparams
+weights: output/cascade_rcnn_r50_vd_fpn_ssld_1x_coco/model_final
+
+ResNet:
+  depth: 50
+  variant: d
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+  lr_mult_list: [0.05, 0.05, 0.1, 0.15]
--- a/paddle_detection/configs/cascade_rcnn/cascade_rcnn_r50_vd_fpn_ssld_2x_coco.yml
+++ b/paddle_detection/configs/cascade_rcnn/cascade_rcnn_r50_vd_fpn_ssld_2x_coco.yml
@@ -0,0 +1,29 @@
+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  '_base_/optimizer_1x.yml',
+  '_base_/cascade_rcnn_r50_fpn.yml',
+  '_base_/cascade_fpn_reader.yml',
+]
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_vd_ssld_v2_pretrained.pdparams
+weights: output/cascade_rcnn_r50_vd_fpn_ssld_2x_coco/model_final
+
+ResNet:
+  depth: 50
+  variant: d
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+  lr_mult_list: [0.05, 0.05, 0.1, 0.15]
+
+epoch: 24
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [12, 22]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000