重塑输入层“要求的形状”的大小总是“输入形状”的大小的平方

Question

我正在尝试使用C-API运行SavedModel。在运行TF_SessionRun时，它总是在具有相同错误的各种输入节点上失败。

TF_SessionRun status: 3:Input to reshape is a tensor with 6 values, but the requested shape has 36
TF_SessionRun status: 3:Input to reshape is a tensor with 19 values, but the requested shape has 361
TF_SessionRun status: 3:Input to reshape is a tensor with 3111 values, but the requested shape has 9678321
...

可以看出，请求的形状值的数量始终是预期输入大小的平方。这很奇怪。

[saved_model_cli命令，模型运行正常。输入都是标量DT_STRING或DT_FLOAT，我没有做图像识别。这是该命令的输出：

signature_def['serving_default']:
  The given SavedModel SignatureDef contains the following input(s):
    inputs['f1'] tensor_info:
        dtype: DT_STRING
        shape: (-1)
        name: f1:0
    inputs['f2'] tensor_info:
        dtype: DT_STRING
        shape: (-1)
        name: f2:0
    inputs['f3'] tensor_info:
        dtype: DT_STRING
        shape: (-1)
        name: f3:0
    inputs['f4'] tensor_info:
        dtype: DT_FLOAT
        shape: (-1)
        name: f4:0
    inputs['f5'] tensor_info:
        dtype: DT_STRING
        shape: (-1)
        name: f5:0
  The given SavedModel SignatureDef contains the following output(s):
    outputs['o1_probs'] tensor_info:
        dtype: DT_DOUBLE
        shape: (-1, 2)
        name: output_probs:0
    outputs['o1_values'] tensor_info:
        dtype: DT_STRING
        shape: (-1, 2)
        name: output_labels:0
    outputs['predicted_o1'] tensor_info:
        dtype: DT_STRING
        shape: (-1, 1)
        name: output_class:0
  Method name is: tensorflow/serving/predict

任何有关正在发生的事情的线索，我们都表示赞赏。 saved_model.pb文件来自AutoML，我的代码仅查询该模型。我不更改图表。

Answer 1

事实证明，问题是由我未正确使用TF_AllocateTensor函数引起的。

原始代码是：

TF_Tensor* t = TF_AllocateTensor(TF_STRING, nullptr, 0, sz);

似乎应该是：

int64_t dims = 0;
TF_Tensor* t = TF_AllocateTensor(TF_STRING, &dims, 1, sz);