I am able to run a simple “python tensorflow saved_model” with a input_tensor(-1,1) in c. But when I change my model to an model with input_tensor(-1,2), I get a Segmentation fault.

used versions
g++ (x86_64-posix-seh-rev0, Built by MinGW-W64 project) 8.1.0
tensorflow 2.15.0 (both python and c-lib)

This is how I created a simple python model:

import tensorflow as tf
import numpy as np

print(tf.__version__)

np.random.seed(0)
X = np.random.rand(100, 2)
y = 2 * X + 1 + 0.1 * np.random.randn(100, 1)

# Define the model architecture
model = tf.keras.Sequential([
    tf.keras.layers.Dense(1, input_shape=(2,))
])

# Compile and train the model
model.compile(optimizer='sgd', loss='mean_squared_error')
model.fit(X, y, epochs=100)

tf.saved_model.save(model, 'simple_example')

I checked the model with the command line tool:

saved_model_cli show --dir simple_example --tag_set serve --signature_def serving_default

The given SavedModel SignatureDef contains the following input(s):
  inputs['dense_input'] tensor_info:
      dtype: DT_FLOAT
      shape: (-1, 2)
      name: serving_default_dense_input:0
The given SavedModel SignatureDef contains the following output(s):
  outputs['dense'] tensor_info:
      dtype: DT_FLOAT
      shape: (-1, 1)
      name: StatefulPartitionedCall:0
Method name is: tensorflow/serving/predict

The c-code to run the model is:

#include <stdio.h>
#include <iostream>
#include <vector>
#include <tensorflow/c/c_api.h>

int main(int argc, char *argv[])
{
  TF_Status* status = TF_NewStatus();
  TF_Graph*  graph  = TF_NewGraph();
  TF_Buffer* r_opts = TF_NewBufferFromString("",0);
  TF_Buffer* meta_g = TF_NewBuffer();
  
  const char* dir_name = "..\data\simple_example";
  const char* InputOperationName = "serving_default_dense_input";
  int64_t in_dims[] = {1,2};
  int64_t out_dims[] = {1,1};
  
  //load the model
  TF_SessionOptions* opts = TF_NewSessionOptions();
  const char* tags[] = {"serve"};
  TF_Session* session = TF_LoadSessionFromSavedModel(opts, r_opts, dir_name, tags, 1, graph, meta_g, status);
  if (session == NULL || TF_GetCode(status) != TF_OK )
    return -1;
  
  TF_Output input_op = {TF_GraphOperationByName(graph, InputOperationName ), 0};
  if (input_op.oper == NULL)
    return -1;

  // Define the input tensor
  TF_Tensor* input_tensor = TF_AllocateTensor(TF_FLOAT, in_dims, 2, in_dims[0] * in_dims[1] * sizeof(float));
  float* input_values = (float*)TF_TensorData(input_tensor);
  for (int n=0;n<(in_dims[0] * in_dims[1]);n++)
    input_values[n] = n;

  // Define the output tensor
  TF_Output output_op = {TF_GraphOperationByName(graph, "StatefulPartitionedCall"), 0};
  if (output_op.oper == NULL)
    return -1;
  TF_Tensor* output_tensor = TF_AllocateTensor(TF_FLOAT, out_dims, 2, out_dims[0] * out_dims[1] * sizeof(float));
  
  // Run the session
  TF_SessionRun(session, NULL, &input_op, &input_tensor, in_dims[0]*in_dims[1], &output_op, &output_tensor, out_dims[0]*out_dims[1], NULL, 0, NULL, status);
  if (TF_GetCode(status) != TF_OK)
    std::cout << "failed: " << TF_Message(status) << std::endl;
  
  float* output_values = (float*)TF_TensorData(output_tensor);
  std::cout << "Output values: " << output_values[0] << std::endl;
  
  return 0;
}

my gdb output:

2024-06-21 14:10:16.608082: I tensorflow/cc/saved_model/loader.cc:217] Running initialization op on SavedModel bundle at path: ..datasimple_example
2024-06-21 14:10:17.113501: I tensorflow/cc/saved_model/loader.cc:316] SavedModel load for tags { serve }; Status: success: OK. Took 3129450 microseconds.

Thread 1 received signal SIGSEGV, Segmentation fault.
0x00007ff980b2c346 in tensorflow!?CopyFromInternal@Tensor@tensorflow@@AEAAXAEBV12@AEBVTensorShape@2@@Z ()
   from tensorflowtensorflow.dll