use_gpu: true log_iter: 20 save_dir: output snapshot_epoch: 1 print_flops: false pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ESNet_x0_75_pretrained.pdparams weights: output/picodet_s_320_pedestrian/model_final find_unused_parameters: True use_ema: true cycle_epoch: 40 snapshot_epoch: 10 epoch: 300 metric: COCO num_classes: 1 architecture: PicoDet PicoDet: backbone: ESNet neck: CSPPAN head: PicoHead ESNet: scale: 0.75 feature_maps: [4, 11, 14] act: hard_swish channel_ratio: [0.875, 0.5, 0.5, 0.5, 0.625, 0.5, 0.625, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5] CSPPAN: out_channels: 96 use_depthwise: True num_csp_blocks: 1 num_features: 4 PicoHead: conv_feat: name: PicoFeat feat_in: 96 feat_out: 96 num_convs: 2 num_fpn_stride: 4 norm_type: bn share_cls_reg: True fpn_stride: [8, 16, 32, 64] feat_in_chan: 96 prior_prob: 0.01 reg_max: 7 cell_offset: 0.5 loss_class: name: VarifocalLoss use_sigmoid: True iou_weighted: True loss_weight: 1.0 loss_dfl: name: DistributionFocalLoss loss_weight: 0.25 loss_bbox: name: GIoULoss loss_weight: 2.0 assigner: name: SimOTAAssigner candidate_topk: 10 iou_weight: 6 nms: name: MultiClassNMS nms_top_k: 1000 keep_top_k: 100 score_threshold: 0.025 nms_threshold: 0.6 LearningRate: base_lr: 0.4 schedulers: - !CosineDecay max_epochs: 300 - !LinearWarmup start_factor: 0.1 steps: 300 OptimizerBuilder: optimizer: momentum: 0.9 type: Momentum regularizer: factor: 0.00004 type: L2 TrainDataset: !COCODataSet image_dir: "" anno_path: aic_coco_train_cocoformat.json dataset_dir: dataset data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd'] EvalDataset: !COCODataSet image_dir: val2017 anno_path: annotations/instances_val2017.json dataset_dir: dataset/coco TestDataset: !ImageFolder anno_path: annotations/instances_val2017.json worker_num: 8 TrainReader: sample_transforms: - Decode: {} - RandomCrop: {} - RandomFlip: {prob: 0.5} - RandomDistort: {} batch_transforms: - BatchRandomResize: {target_size: [256, 288, 320, 352, 384], random_size: True, random_interp: True, keep_ratio: False} - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]} - Permute: {} batch_size: 128 shuffle: true drop_last: true collate_batch: false EvalReader: sample_transforms: - Decode: {} - Resize: {interp: 2, target_size: [320, 320], keep_ratio: False} - 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: 8 shuffle: false TestReader: inputs_def: image_shape: [1, 3, 320, 320] sample_transforms: - Decode: {} - Resize: {interp: 2, target_size: [320, 320], keep_ratio: False} - 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