Tensorflow Train.py错误没有变量

Question

我一直在关注dat tran的教程。 当按照“ ssd_inception_v2_coco_2017_11_17 ”的指示运行train.py时，给出了以下内容：

INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0

这个错误：

      File "C:path\AppData\Local\Continuum\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\ops\array_ops.py", line 1023, in unstack
          (axis, -value_shape.ndims, value_shape.ndims))
      ValueError: axis = 0 not in [0, 0)

我寻找该错误，解决方案是使用另一个网络进行培训，因此我使用了“ faster_rcnn_resnet101_coco_2018_01_28 ”，该警告给出了很多警告：

    WARNING:root:Variable [resnet_v1_101/conv1/BatchNorm/beta] not available in checkpoint
    WARNING:root:Variable [resnet_v1_101/conv1/BatchNorm/gamma] not available in checkpoint
    WARNING:root:Variable [resnet_v1_101/conv1/BatchNorm/moving_mean] not available in checkpoint
    WARNING:root:Variable [resnet_v1_101/conv1/BatchNorm/moving_variance] not available in checkpoint
    WARNING:root:Variable [resnet_v1_101/conv1/weights] not available in checkpoint

和这个错误：

 File "C:path\AppData\Local\Continuum\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\training\saver.py", line 1251, in _build
     raise ValueError("No variables to save")
 ValueError: No variables to save

Answer 1

从pipeline.config文件修改此行：

从：

from_detection_checkpoint: false

至：

from_detection_checkpoint: true