Created by: aixier

环境：

执行文件： https://github.com/PaddlePaddle/PaddleDetection/blob/release/0.1/slim/quantization/compress.py

运行命令：

python compress.py  \
  -s yolov3_mobilenet_v1_slim.yaml \
  -c  ../../configs/yolov3_mobilenet_v1.yml  \
  -d "../../../../data/coco"  \
  -o max_iters=100  \
  LearningRate.base_lr=0.00005  \
  LearningRate.schedulers="[!PiecewiseDecay {gamma: 0.1, milestones: [516, 1012]}]" \  
  YoloTrainFeed.batch_size=2

出错信息：

Traceback (most recent call last):
  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/contrib/slim/core/compressor.py", line 593, in run
    self._eval(context)
  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/contrib/slim/core/compressor.py", line 542, in _eval
    func(self.eval_graph.program, self.scope))
  File "compress.py", line 220, in eval_func
    FLAGS.output_eval)
  File "/home/aistudio/work/PaddleDetection/ppdet/utils/eval_utils.py", line 205, in eval_results
    is_bbox_normalized=is_bbox_normalized)
  File "/home/aistudio/work/PaddleDetection/ppdet/utils/coco_eval.py", line 86, in bbox_eval
    results, clsid2catid, is_bbox_normalized=is_bbox_normalized)
  File "/home/aistudio/work/PaddleDetection/ppdet/utils/coco_eval.py", line 215, in bbox2out
    im_id = int(im_ids[i][0])