为什么训练出来所有指标都为0

[youngyohann]

训练后显示：

config：

save_dir: workspace/nanodet-plus-m_320 model: weight_averager: name: ExpMovingAverager decay: 0.9998 arch: name: NanoDetPlus detach_epoch: 10 backbone: name: ShuffleNetV2 model_size: 1.0x out_stages: [2,3,4] activation: LeakyReLU fpn: name: GhostPAN in_channels: [116, 232, 464] out_channels: 96 kernel_size: 5 num_extra_level: 1 use_depthwise: True activation: LeakyReLU head: name: NanoDetPlusHead num_classes: 1 input_channel: 96 feat_channels: 96 stacked_convs: 2 kernel_size: 5 strides: [8, 16, 32, 64] activation: LeakyReLU reg_max: 7 norm_cfg: type: BN loss: loss_qfl: name: QualityFocalLoss use_sigmoid: True beta: 2.0 loss_weight: 1.0 loss_dfl: name: DistributionFocalLoss loss_weight: 0.25 loss_bbox: name: GIoULoss loss_weight: 2.0

Auxiliary head, only use in training time.

aux_head:
  name: SimpleConvHead
  num_classes: 1
  input_channel: 192
  feat_channels: 192
  stacked_convs: 4
  strides: [8, 16, 32, 64]
  activation: LeakyReLU
  reg_max: 7

data: train: name: CocoDataset img_path: cocoCCPD/train ann_path: cocoCCPD/train.json input_size: [320,320] #[w,h] keep_ratio: False pipeline: perspective: 0.0 scale: [0.6, 1.4] stretch: [[0.8, 1.2], [0.8, 1.2]] rotation: 0 shear: 0 translate: 0.2 flip: 0.5 brightness: 0.2 contrast: [0.6, 1.4] saturation: [0.5, 1.2] normalize: [[103.53, 116.28, 123.675], [57.375, 57.12, 58.395]] val: name: CocoDataset img_path: cocoCCPD/val ann_path: cocoCCPD/val.json input_size: [320,320] #[w,h] keep_ratio: False pipeline: normalize: [[103.53, 116.28, 123.675], [57.375, 57.12, 58.395]] device: gpu_ids: [0] # Set like [0, 1, 2, 3] if you have multi-GPUs workers_per_gpu: 8 batchsize_per_gpu: 16 schedule: load_model: nanodet-plus-m_320_checkpoint.ckpt optimizer: name: AdamW lr: 0.001 weight_decay: 0.05 warmup: name: linear steps: 500 ratio: 0.0001 total_epochs: 20 lr_schedule: name: CosineAnnealingLR T_max: 300 eta_min: 0.00005 val_intervals: 2 grad_clip: 35 evaluator: name: CocoDetectionEvaluator save_key: mAP log: interval: 2

class_names: ['license']

数据集格式：

{"info": ["none"], "licenses": ["none"], "categories": [{"id": 1, "name": "license"}], "images": [{"id": 1, "file_name": "1.jpg", "width": 401, "height": 240}], "annotations": [{"id": 1, "image_id": 1, "category_id": 1, "iscrowd": 0, "area": 1426.0, "bbox": [147.0, 202.0, 62.0, 23.0]}]}

只训练了20epoch，大佬们看看哪里有问题呢

[phonver]

我和你一样 voc转coco数据集跑出来全是0

[shihongji1993]

把lr改小试一下

[phonver]

嗯