更换文档检测模型

paddle_detection/configs/vitdet/_base_/faster_rcnn_reader.yml

@@ -0,0 +1,41 @@
+worker_num: 2
+TrainReader:
+  sample_transforms:
+  - Decode: {}
+  - RandomResizeCrop: {resizes: [400, 500, 600], cropsizes: [[384, 600], ], prob: 0.5}
+  - RandomResize: {target_size: [[480, 1333], [512, 1333], [544, 1333], [576, 1333], [608, 1333], [640, 1333], [672, 1333], [704, 1333], [736, 1333], [768, 1333], [800, 1333]], keep_ratio: True, interp: 2}
+  - 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: 2
+  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:
+  inputs_def:
+    image_shape: [-1, 3, 640, 640]
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: 640, keep_ratio: True}
+  - Pad: {size: 640}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_size: 1
+  shuffle: false
+  drop_last: false

paddle_detection/configs/vitdet/_base_/mask_rcnn_reader.yml

@@ -0,0 +1,41 @@
+worker_num: 2
+TrainReader:
+  sample_transforms:
+  - Decode: {}
+  # - RandomResizeCrop: {resizes: [400, 500, 600], cropsizes: [[384, 600], ], prob: 0.5}
+  - 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
+  use_shared_memory: true
+
+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

paddle_detection/configs/vitdet/_base_/optimizer_base_1x.yml

@@ -0,0 +1,22 @@
+epoch: 12
+
+LearningRate:
+  base_lr: 0.0001
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [9, 11]
+  - !LinearWarmup
+    start_factor: 0.001
+    steps: 1000
+
+OptimizerBuilder:
+  optimizer:
+    type: AdamWDL
+    betas: [0.9, 0.999]
+    layer_decay: 0.75
+    weight_decay: 0.02
+    num_layers: 12
+    filter_bias_and_bn: True
+    skip_decay_names: ['pos_embed', 'cls_token']
+    set_param_lr_func: 'layerwise_lr_decay'

paddle_detection/configs/vitdet/_base_/optimizer_base_36e.yml

@@ -0,0 +1,20 @@
+
+epoch: 36
+
+LearningRate:
+  base_lr: 0.0001
+  schedulers:
+    - !CosineDecay
+      max_epochs: 36
+      min_lr_ratio: 0.1 # 0.1
+    - !LinearWarmup
+      start_factor: 0.001
+      epochs: 1
+
+
+OptimizerBuilder:
+  clip_grad_by_norm: 0.1
+  regularizer: false
+  optimizer:
+    type: AdamW
+    weight_decay: 0.0001

paddle_detection/configs/vitdet/_base_/ppyoloe_reader.yml

@@ -0,0 +1,40 @@
+worker_num: 4
+eval_height: &eval_height 640
+eval_width: &eval_width 640
+eval_size: &eval_size [*eval_height, *eval_width]
+
+TrainReader:
+  sample_transforms:
+    - Decode: {}
+    - RandomDistort: {}
+    - RandomExpand: {fill_value: [123.675, 116.28, 103.53]}
+    - RandomCrop: {}
+    - RandomFlip: {}
+  batch_transforms:
+    - BatchRandomResize: {target_size: [320, 352, 384, 416, 448, 480, 512, 544, 576, 608, 640, 672, 704, 736, 768], random_size: True, random_interp: True, keep_ratio: False}
+    - NormalizeImage: {mean: [0., 0., 0.], std: [1., 1., 1.], norm_type: none}
+    - Permute: {}
+    - PadGT: {}
+  batch_size: 2
+  shuffle: true
+  drop_last: true
+  use_shared_memory: true
+  collate_batch: true
+
+EvalReader:
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0., 0., 0.], std: [1., 1., 1.], norm_type: none}
+    - Permute: {}
+  batch_size: 2
+
+TestReader:
+  inputs_def:
+    image_shape: [3, *eval_height, *eval_width]
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0., 0., 0.], std: [1., 1., 1.], norm_type: none}
+    - Permute: {}
+  batch_size: 1