cifar10模型训练完,用于识别单个图片报错解决方案

(InvalidArgumentError (see above for traceback): Assign requires shapes of both tensors to match. lhs shape= [72,384] rhs shape= [9216,384]
[[Node: save/Assign_5 = Assign[T=DT_FLOAT, _class=["loc:@local3/weights"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](local3/weights, save/RestoreV2_5)]])

解决这种问题一般步骤

1.chenkpoint 先清除再运行

2.设置图片的格式与训练图片格式要一致


相关文章:

  • 2021-07-21
  • 2021-09-02
  • 2021-08-18
  • 2022-12-23
  • 2022-12-23
  • 2022-02-27
  • 2021-05-17
  • 2021-06-12
猜你喜欢
  • 2022-12-23
  • 2021-04-10
  • 2021-07-12
  • 2022-01-04
  • 2021-12-04
  • 2021-07-12
  • 2022-12-23
相关资源
相似解决方案