# Runtime use_gpu: true use_xpu: false use_mlu: false use_npu: false log_iter: 20 save_dir: output snapshot_epoch: 1 print_flops: false print_params: false use_ema: true # Dataset metric: COCO num_classes: 80 TrainDataset: name: COCODataSet image_dir: train2017 anno_path: annotations/instances_train2017.json dataset_dir: dataset/coco data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd'] EvalDataset: name: COCODataSet image_dir: val2017 anno_path: annotations/instances_val2017.json dataset_dir: dataset/coco allow_empty: true TestDataset: name: ImageFolder anno_path: annotations/instances_val2017.json # also support txt (like VOC's label_list.txt) dataset_dir: dataset/coco # if set, anno_path will be 'dataset_dir/anno_path' # Reader 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 # Model architecture: FasterRCNN # pretrain_weights: # rewrite in SwinTransformer.pretrained in ppdet/modeling/backbones/swin_transformer.py FasterRCNN: backbone: SwinTransformer neck: FPN rpn_head: RPNHead bbox_head: BBoxHead bbox_post_process: BBoxPostProcess SwinTransformer: arch: 'swin_T_224' ape: false drop_path_rate: 0.1 patch_norm: true out_indices: [0, 1, 2, 3] pretrained: https://paddledet.bj.bcebos.com/models/pretrained/swin_tiny_patch4_window7_224_22kto1k_pretrained.pdparams 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: 1000 topk_after_collect: True test_proposal: min_size: 0.0 nms_thresh: 0.7 pre_nms_top_n: 1000 post_nms_top_n: 1000 BBoxHead: head: TwoFCHead 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 use_random: True TwoFCHead: out_channel: 1024 BBoxPostProcess: decode: RCNNBox nms: name: MultiClassNMS keep_top_k: 100 score_threshold: 0.05 nms_threshold: 0.5 # Optimizer epoch: 12 LearningRate: base_lr: 0.0001 schedulers: - !PiecewiseDecay gamma: 0.1 milestones: [8, 11] - !LinearWarmup start_factor: 0.1 steps: 1000 OptimizerBuilder: clip_grad_by_norm: 1.0 optimizer: type: AdamW weight_decay: 0.05 param_groups: - params: ['absolute_pos_embed', 'relative_position_bias_table', 'norm'] weight_decay: 0.0 # Exporting the model export: post_process: True # Whether post-processing is included in the network when export model. nms: True # Whether NMS is included in the network when export model. benchmark: False # It is used to testing model performance, if set `True`, post-process and NMS will not be exported. fuse_conv_bn: False