报错

ValueError: Could not find matching function to call loaded from the SavedModel. Got:Positional arguments (3 total):* <_VariantDataset shapes: ((<unknown>, <unknown>, <unknown>, <unknown>), <unknown>), types: ((tf.float32, tf.float32, tf.float32, tf.float32), tf.float32)>* False* NoneKeyword arguments: {}Expected these arguments to match one of the following 4 option(s):Option 1:Positional arguments (3 total):* (TensorSpec(shape=(None, 3, 24, 72), dtype=tf.float32, name='input_1'), TensorSpec(shape=(None, 3, 24, 72), dtype=tf.float32, name='input_2'), TensorSpec(shape=(None, 3, 24, 72), dtype=tf.float32, name='input_3'), TensorSpec(shape=(None, 3, 24, 72), dtype=tf.float32, name='input_4'))* True* NoneKeyword arguments: {}Option 2:Positional arguments (3 total):* (TensorSpec(shape=(None, 3, 24, 72), dtype=tf.float32, name='inputs/0'), TensorSpec(shape=(None, 3, 24, 72), dtype=tf.float32, name='inputs/1'), TensorSpec(shape=(None, 3, 24, 72), dtype=tf.float32, name='inputs/2'), TensorSpec(shape=(None, 3, 24, 72), dtype=tf.float32, name='inputs/3'))* True* NoneKeyword arguments: {}Option 3:Positional arguments (3 total):* (TensorSpec(shape=(None, 3, 24, 72), dtype=tf.float32, name='inputs/0'), TensorSpec(shape=(None, 3, 24, 72), dtype=tf.float32, name='inputs/1'), TensorSpec(shape=(None, 3, 24, 72), dtype=tf.float32, name='inputs/2'), TensorSpec(shape=(None, 3, 24, 72), dtype=tf.float32, name='inputs/3'))* False* NoneKeyword arguments: {}Option 4:Positional arguments (3 total):* (TensorSpec(shape=(None, 3, 24, 72), dtype=tf.float32, name='input_1'), TensorSpec(shape=(None, 3, 24, 72), dtype=tf.float32, name='input_2'), TensorSpec(shape=(None, 3, 24, 72), dtype=tf.float32, name='input_3'), TensorSpec(shape=(None, 3, 24, 72), dtype=tf.float32, name='input_4'))* False* NoneKeyword arguments: {}

解决方法

检查输入是否和训练时的输入格式、大小一样
如果输入有多个元素，采用tuple作为整体输入

Debug Tensorflow: Expected these arguments to match one of the following 4 option(s):相关推荐

sql: expected 0 arguments, got 1
sql: expected 0 arguments, got 1 golang --->gorm框架代码如下: var plist []*Word err = dao.GetBaikeDb() ...
Debug Tensorflow: TypeError: Cannot convert a symbolic Keras input/output to a numpy array.
问题 'Cannot convert a symbolic Keras input/output to a numpy array. ' TypeError: Cannot convert a sym ...
debug Tensorflow: ‘_UserObject‘ object has no attribute ‘add_slot‘
平台 ubuntu tensoflow 现象 --------------------------------------------------------------------------- A ...
Debug Tensorflow: tensorflow.python.framework.errors_impl.InvalidArgumentError: OpKernel ‘ConcatV2‘
环境 Ubuntu 18.04 Tensorflow-gpu 2.4 报错 Traceback (most recent call last):File "nn/cnn.py", ...
Debug Tensorflow: Object was never used (type ＜class ‘tensorflow.python.ops.tensor_array_ops.TensorA
报错信息环境 ubuntu tensorflow-gpu 解决错误来自对TensorArray的使用上. 原代码: y.write(0,[[20,1,10]]) 修改为: y = y.write( ...
Debug Tensorflow: yolo模型检测框位置正确但类别不正确
平台 tensorflow yolov5 现象标注框没问题,但类别不正确解决首先确保后处理过程没有问题,nms无误由于yolo损失函数包含三部分,参考公众号YueTan.我的猜测是三部分可能没 ...
Debug Tensorflow: 随着训练进行，内存消耗越来越大
环境 ubuntu 18.04 Python 3.8 TensorFlow-gpu 2.3.1 CUDA 11.1 Tensorflow-yolov5 问题内存泄漏.训练时消耗内存越来越多,直到内存 ...
Debug Tensorflow ：Two checkpoint references resolved to different objects
环境 ubuntu 18.04 Python 3.8 TensorFlow-gpu 2.3.1 CUDA 11.1 tensorflow-yolov5 报错 WARNING:tensorflow:In ...
jdk源码写过注释后debug提示source code does not match the bytecode
一.问题说明环境说明: jdk:jdk1.8.0_161 阅读过jdk源码的人,肯定遇到过这个问题:当你在源码中写过注释,然后再次打断点,你就会发现提示你"Source code does ...

Debug Tensorflow: Expected these arguments to match one of the following 4 option(s):

报错

解决方法

Debug Tensorflow: Expected these arguments to match one of the following 4 option(s):相关推荐

最新文章

热门文章