Created by: vxgu86

python -u tools/train.py -c configs/yolov3_darknet_voc.yml --use_vdl=True --vdl_log_dir=vdl_dir/scalar --eval /opt/anaconda3/lib/python3.7/site-packages/sklearn/feature_extraction/text.py:17: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working from collections import Mapping, defaultdict 2020-07-31 14:16:13,051-INFO: If regularizer of a Parameter has been set by 'fluid.ParamAttr' or 'fluid.WeightNormParamAttr' already. The Regularization[L2Decay, regularization_coeff=0.000500] in Optimizer will not take effect, and it will only be applied to other Parameters! Traceback (most recent call last): File "tools/train.py", line 368, in main() File "tools/train.py", line 145, in main eval_reader = create_reader(cfg.EvalReader, devices_num=1) File "/home/vxgu/PaddleDetection-release-0.3/ppdet/data/reader.py", line 410, in create_reader reader = Reader(**cfg)() File "/home/vxgu/PaddleDetection-release-0.3/ppdet/data/reader.py", line 204, in init self._roidbs = self._dataset.get_roidb() File "/home/vxgu/PaddleDetection-release-0.3/ppdet/data/source/dataset.py", line 68, in get_roidb self.load_roidb_and_cname2cid() File "/home/vxgu/PaddleDetection-release-0.3/ppdet/data/source/voc.py", line 143, in load_roidb_and_cname2cid _difficult = int(obj.find('difficult').text) AttributeError: 'NoneType' object has no attribute 'text'

architecture: YOLOv3 use_gpu: true max_iters: 70000 log_smooth_window: 20 save_dir: output snapshot_iter: 2000 metric: VOC map_type: 11point pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/DarkNet53_pretrained.tar weights: output/yolov3_darknet_voc/model_final num_classes: 7 finetune_exclude_pretrained_params: ['yolo_output'] use_fine_grained_loss: false

YOLOv3: backbone: DarkNet yolo_head: YOLOv3Head

DarkNet: norm_type: sync_bn norm_decay: 0. depth: 53

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 here is only used for fine grained loss, not used

for training batch_size setting, training batch_size setting

is in configs/yolov3_reader.yml TrainReader.batch_size, batch

size here should be set as same value as TrainReader.batch_size

batch_size: 8 ignore_thresh: 0.7 label_smooth: false

LearningRate: base_lr: 0.001 schedulers:

• !PiecewiseDecay gamma: 0.1 milestones:
  • 55000
  • 62000
• !LinearWarmup start_factor: 0. steps: 1000

OptimizerBuilder: optimizer: momentum: 0.9 type: Momentum regularizer: factor: 0.0005 type: L2

READER: 'yolov3_reader.yml' TrainReader: inputs_def: fields: ['image', 'gt_bbox', 'gt_class', 'gt_score'] num_max_boxes: 50 dataset: !VOCDataSet dataset_dir: dataset/voc/ anno_path: trainval.txt use_default_label: false with_background: false

EvalReader: inputs_def: fields: ['image', 'im_size', 'im_id', 'gt_bbox', 'gt_class', 'is_difficult'] num_max_boxes: 50 dataset: !VOCDataSet dataset_dir: dataset/voc/ anno_path: test.txt use_default_label: false with_background: false

TestReader: dataset: !ImageFolder use_default_label: false with_background: false