I've tried running this ONNX model but I've ran into a problem. Am I perhaps giving the wrong input?

import onnxruntime
import numpy as np
from PIL import Image

Load the ONNX model

onnx_model_path = "yolow-l.onnx"
ort_session = onnxruntime.InferenceSession(onnx_model_path)

Prepare input data

input_image_path = "images/price_tag_image/c17daf41-de8f-4af0-b4df-20af49c04216.jpg"
input_image = Image.open(input_image_path)
input_image = input_image.resize((640, 640)) # Resize as needed
input_data = np.array(input_image, dtype=np.float32)
input_data = np.transpose(input_data, (2, 0, 1)) # Channels first
input_data = np.expand_dims(input_data, axis=0) # Add batch dimension

Run inference

outputs = ort_session.run(['num_dets', 'boxes', 'scores', 'labels'], {"images": input_data})

2024-04-15 14:12:44.339192 [E:onnxruntime:, sequential_executor.cc:514 ExecuteKernel] Non-zero status code returned while running NonMaxSuppression node. Name:'/NonMaxSuppression' Status Message: non_max_suppression.cc:87 PrepareCompute boxes and scores should have same spatial_dimension.

Fail Traceback (most recent call last)
Cell In[597], line 10
7 input_data = np.expand_dims(input_data, axis=0) # Add batch dimension
9 # Run inference
---> 10 outputs = ort_session.run(['num_dets', 'boxes', 'scores', 'labels'], {"images": input_data})

File /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py:217, in Session.run(self, output_names, input_feed, run_options)
215 output_names = [output.name for output in self._outputs_meta]
216 try:
--> 217 return self._sess.run(output_names, input_feed, run_options)
218 except C.EPFail as err:
219 if self._enable_fallback:

Fail: [ONNXRuntimeError] : 1 : FAIL : Non-zero status code returned while running NonMaxSuppression node. Name:'/NonMaxSuppression' Status Message: non_max_suppression.cc:87 PrepareCompute boxes and scores should have same spatial_dimension.