how to solve runtime error while predicting using onnx model?

Question

I have deep learning model trained in matlab using trainNetwork command.I want to use that model in python for predicting, so i exported the network to onnx format in matlab using "exportONNXNetwork" coomand.I imported the onnx model in python using the following code: sess = onnxruntime.InferenceSession("Alma.onnx")

The model accepts image of size(224,224,3).so i resized the image using cv2.resize. When i try run the model using sess.run command, i am getting a error as RuntimeError: Input 'data' must not be empty. Where 'data' is input_name.The command used for prediction is res = sess.run([output_name], {input_name: x}) I am not able to figure out where i am going wrong.I am sharing the full code.

import numpy
import cv2
import tensorflow as tf
sess = onnxruntime.InferenceSession("Alma.onnx")
im = cv2.imread("1.jpg")
img = cv2.cvtColor(im,cv2.COLOR_BGR2RGB)
x = tf.convert_to_tensor(img)





input_name = sess.get_inputs()[0].name
print("input name", input_name)
input_shape = sess.get_inputs()[0].shape
print("input shape", input_shape)
input_type = sess.get_inputs()[0].type
print("input type", input_type)


output_name = sess.get_outputs()[0].name
print("output name", output_name)
output_shape = sess.get_outputs()[0].shape
print("output shape", output_shape)
output_type = sess.get_outputs()[0].type
print("output type", output_type)

res = sess.run([output_name], {input_name: x})
print(res)

The error i am getting is:

  File "C:/Users/Hanamanth/PycharmProjects/cocoon/onnx.py", line 29, in <module>
    res = sess.run([output_name], {input_name: x})
  File "C:\Users\Hanamanth\PycharmProjects\cocoon\venv\lib\site-packages\onnxruntime\capi\session.py", line 72, in run
    return self._sess.run(output_names, input_feed, run_options)
RuntimeError: Input 'data' must not be empty.
input name data
input shape [1, 3, 224, 224]
input type tensor(float)
output name prob
output shape [1, 2]
output type tensor(float)```

Answer 1

x (input to sess.run) should be an np array. For example:

img = cv2.resize(img, (width, height))
# convert image to numpy
x = numpy.asarray(img).astype(<right_type>).reshape(<right_shape>)
res = sess.run([output_name], {input_name: x})