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/semi_det/arsl/README.md
+++ b/paddle_detection/configs/semi_det/arsl/README.md
@@ -0,0 +1,48 @@
+简体中文 | [English](README_en.md)
+
+# Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection (ARSL)
+
+## ARSL-FCOS 模型库
+
+|      模型      |  COCO监督数据比例 | Semi mAP<sup>val<br>0.5:0.95 |  Semi Epochs (Iters)  |  模型下载  |   配置文件   |
+| :------------: | :---------:|:----------------------------: | :------------------: |:--------: |:----------: |
+| ARSL-FCOS     |    1% |  **22.8**  | 240 (87120)   | [download](https://paddledet.bj.bcebos.com/models/arsl_fcos_r50_fpn_coco_semi001.pdparams) | [config](./arsl_fcos_r50_fpn_coco_semi001.yml) |
+| ARSL-FCOS     |    5% |  **33.1**  | 240 (174240)  | [download](https://paddledet.bj.bcebos.com/models/arsl_fcos_r50_fpn_coco_semi005.pdparams) | [config](./arsl_fcos_r50_fpn_coco_semi005.yml ) |
+| ARSL-FCOS     |   10% |  **36.9**  | 240 (174240)  | [download](https://paddledet.bj.bcebos.com/models/arsl_fcos_r50_fpn_coco_semi010.pdparams) | [config](./arsl_fcos_r50_fpn_coco_semi010.yml ) |
+| ARSL-FCOS     |   10% |  **38.5(LSJ)**  | 240 (174240)  | [download](https://paddledet.bj.bcebos.com/models/arsl_fcos_r50_fpn_coco_semi010_lsj.pdparams) | [config](./arsl_fcos_r50_fpn_coco_semi010_lsj.yml ) |
+| ARSL-FCOS     |   full(100%) |  **45.1**  | 240 (174240)  | [download](https://paddledet.bj.bcebos.com/models/arsl_fcos_r50_fpn_coco_full.pdparams) | [config](./arsl_fcos_r50_fpn_coco_full.yml ) |
+
+
+
+## 使用说明
+
+仅训练时必须使用半监督检测的配置文件去训练，评估、预测、部署也可以按基础检测器的配置文件去执行。
+
+### 训练
+
+```bash
+# 单卡训练 (不推荐，需按线性比例相应地调整学习率)
+CUDA_VISIBLE_DEVICES=0 python tools/train.py -c configs/semi_det/arsl/arsl_fcos_r50_fpn_coco_semi010.yml --eval
+
+# 多卡训练
+python -m paddle.distributed.launch --log_dir=arsl_fcos_r50_fpn_coco_semi010/ --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/semi_det/arsl/arsl_fcos_r50_fpn_coco_semi010.yml --eval
+```
+
+### 评估
+
+```bash
+CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/semi_det/arsl/arsl_fcos_r50_fpn_coco_semi010.yml -o weights=output/arsl_fcos_r50_fpn_coco_semi010/model_final.pdparams
+```
+
+### 预测
+
+```bash
+CUDA_VISIBLE_DEVICES=0 python tools/infer.py -c configs/semi_det/arsl/arsl_fcos_r50_fpn_coco_semi010.yml -o weights=output/arsl_fcos_r50_fpn_coco_semi010/model_final.pdparams --infer_img=demo/000000014439.jpg
+```
+
+
+## 引用
+
+```
+
+```
--- a/paddle_detection/configs/semi_det/arsl/_base_/arsl_fcos_r50_fpn.yml
+++ b/paddle_detection/configs/semi_det/arsl/_base_/arsl_fcos_r50_fpn.yml
@@ -0,0 +1,56 @@
+architecture: ARSL_FCOS
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_cos_pretrained.pdparams
+
+ARSL_FCOS:
+  backbone: ResNet
+  neck: FPN
+  fcos_head: FCOSHead_ARSL
+  fcos_cr_loss: FCOSLossCR
+
+
+ResNet:
+  depth: 50
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [1,2,3]
+  num_stages: 4
+
+FPN:
+  out_channel: 256
+  spatial_scales: [0.125, 0.0625, 0.03125]
+  extra_stage: 2
+  has_extra_convs: true
+  use_c5: false
+
+FCOSHead_ARSL:
+  fcos_feat:
+    name: FCOSFeat
+    feat_in: 256
+    feat_out: 256
+    num_convs: 4
+    norm_type: "gn"
+    use_dcn: false
+  fpn_stride: [8, 16, 32, 64, 128]
+  prior_prob: 0.01
+  norm_reg_targets: True
+  centerness_on_reg: True
+  fcos_loss:
+    name: FCOSLossMILC
+    loss_alpha: 0.25
+    loss_gamma: 2.0
+    iou_loss_type: "giou"
+    reg_weights: 1.0
+  nms:
+    name: MultiClassNMS
+    nms_top_k: 1000
+    keep_top_k: 100
+    score_threshold: 0.025
+    nms_threshold: 0.6
+
+
+FCOSLossCR:
+  iou_loss_type: "giou"
+  cls_weight: 2.0
+  reg_weight: 2.0
+  iou_weight: 0.5
+  hard_neg_mining_flag: true
--- a/paddle_detection/configs/semi_det/arsl/_base_/arsl_fcos_reader.yml
+++ b/paddle_detection/configs/semi_det/arsl/_base_/arsl_fcos_reader.yml
@@ -0,0 +1,55 @@
+worker_num: 2
+SemiTrainReader:
+  sample_transforms:
+    - Decode: {}
+    - RandomResize: {target_size: [[640, 1333], [672, 1333], [704, 1333], [736, 1333], [768, 1333], [800, 1333]], keep_ratio: True, interp: 1}
+    - RandomFlip: {}
+  weak_aug:
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: true}
+  strong_aug:
+    - StrongAugImage: {transforms: [
+        RandomColorJitter: {prob: 0.8, brightness: 0.4, contrast: 0.4, saturation: 0.4, hue: 0.1},
+        RandomErasingCrop: {},
+        RandomGaussianBlur: {prob: 0.5, sigma: [0.1, 2.0]},
+        RandomGrayscale: {prob: 0.2},
+      ]}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: true}
+  sup_batch_transforms:
+    - Permute: {}
+    - PadBatch: {pad_to_stride: 32}
+    - Gt2FCOSTarget:
+        object_sizes_boundary: [64, 128, 256, 512]
+        center_sampling_radius: 1.5
+        downsample_ratios: [8, 16, 32, 64, 128]
+        num_shift: 0. # default 0.5
+        multiply_strides_reg_targets: False
+        norm_reg_targets: True
+  unsup_batch_transforms:
+    - Permute: {}
+    - PadBatch: {pad_to_stride: 32}
+  sup_batch_size: 2
+  unsup_batch_size: 2
+  shuffle: True
+  drop_last: True
+
+
+EvalReader:
+  sample_transforms:
+    - Decode: {}
+    - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: true}
+    - Permute: {}
+  batch_transforms:
+    - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+
+
+TestReader:
+  sample_transforms:
+    - Decode: {}
+    - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: true}
+    - Permute: {}
+  batch_transforms:
+    - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
--- a/paddle_detection/configs/semi_det/arsl/_base_/optimizer_360k.yml
+++ b/paddle_detection/configs/semi_det/arsl/_base_/optimizer_360k.yml
@@ -0,0 +1,29 @@
+epoch: 120 # employ iter to control shedule
+LearningRate:
+  base_lr: 0.02 # 0.02 for 8*(4+4) batch
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [3000] # do not decay lr
+  - !LinearWarmup
+    start_factor: 0.3333333333333333
+    steps: 1000
+
+max_iter: 360000 # 360k for 32 batch, 720k for 16 batch
+epoch_iter: 1000 # set epoch_iter for saving checkpoint and eval
+optimize_rate: 1
+SEMISUPNET:
+  BBOX_THRESHOLD: 0.5 # # not used
+  TEACHER_UPDATE_ITER: 1
+  BURN_UP_STEP: 30000
+  EMA_KEEP_RATE: 0.9996
+  UNSUP_LOSS_WEIGHT: 1.0 # detailed weights for cls and loc task can be seen in cr_loss
+  PSEUDO_WARM_UP_STEPS: 2000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0001
+    type: L2
--- a/paddle_detection/configs/semi_det/arsl/_base_/optimizer_90k.yml
+++ b/paddle_detection/configs/semi_det/arsl/_base_/optimizer_90k.yml
@@ -0,0 +1,30 @@
+epoch: 30 # employ iter to control shedule
+LearningRate:
+  base_lr: 0.02 # 0.02 for 8*(4+4) batch
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [300] # do not decay lr
+  - !LinearWarmup
+    start_factor: 0.3333333333333333
+    steps: 1000
+
+max_iter: 90000 # 90k for 32 batch, 180k for 16 batch
+epoch_iter: 1000 # set epoch_iter for saving checkpoint and eval
+# update student params according to loss_grad every X iter.
+optimize_rate: 1
+SEMISUPNET:
+  BBOX_THRESHOLD: 0.5 # not used
+  TEACHER_UPDATE_ITER: 1
+  BURN_UP_STEP: 9000
+  EMA_KEEP_RATE: 0.9996
+  UNSUP_LOSS_WEIGHT: 1.0 # detailed weights for cls and loc task can be seen in cr_loss
+  PSEUDO_WARM_UP_STEPS: 2000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0001
+    type: L2
--- a/paddle_detection/configs/semi_det/arsl/arsl_fcos_r50_fpn_coco_full.yml
+++ b/paddle_detection/configs/semi_det/arsl/arsl_fcos_r50_fpn_coco_full.yml
@@ -0,0 +1,12 @@
+_BASE_: [
+  '../_base_/coco_detection_full.yml',
+  '../../runtime.yml',
+  '_base_/arsl_fcos_r50_fpn.yml',
+  '_base_/optimizer_360k.yml',
+  '_base_/arsl_fcos_reader.yml',
+]
+
+weights: output/fcos_r50_fpn_arsl_360k_coco_full/model_final
+
+#semi detector type
+ssod_method: ARSL
--- a/paddle_detection/configs/semi_det/arsl/arsl_fcos_r50_fpn_coco_semi001.yml
+++ b/paddle_detection/configs/semi_det/arsl/arsl_fcos_r50_fpn_coco_semi001.yml
@@ -0,0 +1,12 @@
+_BASE_: [
+  '../_base_/coco_detection_percent_1.yml',
+  '../../runtime.yml',
+  '_base_/arsl_fcos_r50_fpn.yml',
+  '_base_/optimizer_90k.yml',
+  '_base_/arsl_fcos_reader.yml',
+]
+
+weights: output/arsl_fcos_r50_fpn_coco_semi001/model_final
+
+#semi detector type
+ssod_method: ARSL
--- a/paddle_detection/configs/semi_det/arsl/arsl_fcos_r50_fpn_coco_semi005.yml
+++ b/paddle_detection/configs/semi_det/arsl/arsl_fcos_r50_fpn_coco_semi005.yml
@@ -0,0 +1,12 @@
+_BASE_: [
+  '../_base_/coco_detection_percent_5.yml',
+  '../../runtime.yml',
+  '_base_/arsl_fcos_r50_fpn.yml',
+  '_base_/optimizer_90k.yml',
+  '_base_/arsl_fcos_reader.yml',
+]
+
+weights: output/arsl_fcos_r50_fpn_coco_semi005/model_final
+
+#semi detector type
+ssod_method: ARSL
--- a/paddle_detection/configs/semi_det/arsl/arsl_fcos_r50_fpn_coco_semi010.yml
+++ b/paddle_detection/configs/semi_det/arsl/arsl_fcos_r50_fpn_coco_semi010.yml
@@ -0,0 +1,12 @@
+_BASE_: [
+  '../_base_/coco_detection_percent_10.yml',
+  '../../runtime.yml',
+  '_base_/arsl_fcos_r50_fpn.yml',
+  '_base_/optimizer_360k.yml',
+  '_base_/arsl_fcos_reader.yml',
+]
+
+weights: output/arsl_fcos_r50_fpn_coco_semi010/model_final
+
+#semi detector type
+ssod_method: ARSL
--- a/paddle_detection/configs/semi_det/arsl/arsl_fcos_r50_fpn_coco_semi010_lsj.yml
+++ b/paddle_detection/configs/semi_det/arsl/arsl_fcos_r50_fpn_coco_semi010_lsj.yml
@@ -0,0 +1,47 @@
+_BASE_: [
+  '../_base_/coco_detection_percent_10.yml',
+  '../../runtime.yml',
+  '_base_/arsl_fcos_r50_fpn.yml',
+  '_base_/optimizer_360k.yml',
+  '_base_/arsl_fcos_reader.yml',
+]
+
+weights: output/arsl_fcos_r50_fpn_coco_semi010/model_final
+
+#semi detector type
+ssod_method: ARSL
+
+worker_num: 2
+SemiTrainReader:
+  sample_transforms:
+    - Decode: {}
+    # large-scale jittering
+    - RandomResize: {target_size: [[400, 1333], [1200, 1333]], keep_ratio: True, interp: 1, random_range: True}
+    - RandomFlip: {}
+  weak_aug:
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: true}
+  strong_aug:
+    - StrongAugImage: {transforms: [
+        RandomColorJitter: {prob: 0.8, brightness: 0.4, contrast: 0.4, saturation: 0.4, hue: 0.1},
+        RandomErasingCrop: {},
+        RandomGaussianBlur: {prob: 0.5, sigma: [0.1, 2.0]},
+        RandomGrayscale: {prob: 0.2},
+      ]}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: true}
+  sup_batch_transforms:
+    - Permute: {}
+    - PadBatch: {pad_to_stride: 32}
+    - Gt2FCOSTarget:
+        object_sizes_boundary: [64, 128, 256, 512]
+        center_sampling_radius: 1.5
+        downsample_ratios: [8, 16, 32, 64, 128]
+        num_shift: 0. # default 0.5
+        multiply_strides_reg_targets: False
+        norm_reg_targets: True
+  unsup_batch_transforms:
+    - Permute: {}
+    - PadBatch: {pad_to_stride: 32}
+  sup_batch_size: 2
+  unsup_batch_size: 2
+  shuffle: True
+  drop_last: True