AIstudio PaddlePaddle 1.7.0 框架 yolov3_r34_voc 训练报错
已关闭
AIstudio PaddlePaddle 1.7.0 框架 yolov3_r34_voc 训练报错
Created by: pele228
W0310 11:11:16.339478 441 device_context.cc:237] Please NOTE: device: 0, CUDA Capability: 70, Driver API Version: 9.2, Runtime API Version: 9.0 W0310 11:11:16.343116 441 device_context.cc:245] device: 0, cuDNN Version: 7.3. 2020-03-10 11:11:17,832-INFO: Found /home/aistudio/.cache/paddle/weights/ResNet34_pretrained 2020-03-10 11:11:17,832-INFO: Loading parameters from /home/aistudio/.cache/paddle/weights/ResNet34_pretrained... 2020-03-10 11:11:17,832-WARNING: /home/aistudio/.cache/paddle/weights/ResNet34_pretrained.pdparams not found, try to load model file saved with [ save_params, save_persistables, save_vars ] 2020-03-10 11:11:17,832-WARNING: /home/aistudio/.cache/paddle/weights/ResNet34_pretrained.pdparams not found, try to load model file saved with [ save_params, save_persistables, save_vars ] 2020-03-10 11:11:17,839-WARNING: variable file [ /home/aistudio/.cache/paddle/weights/ResNet34_pretrained/fc_0.w_0 /home/aistudio/.cache/paddle/weights/ResNet34_pretrained/fc_0.b_0 ] not used 2020-03-10 11:11:17,839-WARNING: variable file [ /home/aistudio/.cache/paddle/weights/ResNet34_pretrained/fc_0.w_0 /home/aistudio/.cache/paddle/weights/ResNet34_pretrained/fc_0.b_0 ] not used Traceback (most recent call last): File "tools/train.py", line 323, in main() File "tools/train.py", line 197, in main devices_num, cfg) File "/home/aistudio/work/PaddleDetection/ppdet/data/reader.py", line 406, in create_reader reader = Reader(**cfg)() File "/home/aistudio/work/PaddleDetection/ppdet/data/reader.py", line 202, in init self._roidbs = self._dataset.get_roidb() File "/home/aistudio/work/PaddleDetection/ppdet/data/source/dataset.py", line 68, in get_roidb self.load_roidb_and_cname2cid() File "/home/aistudio/work/PaddleDetection/ppdet/data/source/voc.py", line 131, in load_roidb_and_cname2cid gt_class[i][0] = cname2cid[cname] KeyError: '25'
同样的数据在1.6框架下没问题,1.7下的config文件如下: architecture: YOLOv3 use_gpu: true max_iters: 240000 log_smooth_window: 20 save_dir: output snapshot_iter: 10000 metric: VOC map_type: 11point pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet34_pretrained.tar weights: output/yolov3_r34_voc_an/model_final num_classes: 28 use_fine_grained_loss: false
YOLOv3: backbone: ResNet yolo_head: YOLOv3Head
ResNet: norm_type: sync_bn freeze_at: 0 freeze_norm: false norm_decay: 0. depth: 34 feature_maps: [3, 4, 5]
YOLOv3Head: anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]] anchors: [[10, 13], [16, 30], [33, 23], [30, 61], [62, 45], [59, 119], [116, 90], [156, 198], [373, 326]] norm_decay: 0. yolo_loss: YOLOv3Loss nms: background_label: -1 keep_top_k: 100 nms_threshold: 0.45 nms_top_k: 1000 normalized: false score_threshold: 0.01
YOLOv3Loss: batch_size: 8 ignore_thresh: 0.7 label_smooth: false
LearningRate: base_lr: 0.0001 schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones:
- 180000
- 205000
- !LinearWarmup start_factor: 0. steps: 1000
OptimizerBuilder: optimizer: momentum: 0.9 type: Momentum regularizer: factor: 0.0005 type: L2
READER: 'yolov3_reader.yml' TrainReader: dataset: !VOCDataSet dataset_dir: dataset/an anno_path: trainval.txt use_default_label: false with_background: false
EvalReader: inputs_def: image_shape: [3, 608, 608] fields: ['image', 'im_size', 'im_id', 'gt_bbox', 'gt_class', 'is_difficult'] num_max_boxes: 50 dataset: !VOCDataSet dataset_dir: dataset/an anno_path: test.txt use_default_label: false with_background: false
TestReader: dataset: !ImageFolder use_default_label: false dataset_dir: dataset/an anno_path: label_list.txt with_background: false