import cv2
import numpy as np
image_path_list = ['path/img1.jpg', 'path/img2.jpg']
image_input = []
for image_path in image_path_list:
img = cv2.imread(image_path) #bgr image
#resize image as the input size of your selected model
img_size = cv2.resize(img, (640, 640), interpolation=cv2.INTER_AREA)
image_input.append(img_size)
inputs = {"INPUT": np.array(image_input)}
output_names = ["OUTPUT"]
Onnx Inference
import onnxruntime as ort
onnx_file = "/file_path_to/model.onnx"
providers = ["CUDAExecutionProvider", "CPUExecutionProvider"]
# If there is a kernel in the CUDA execution provider ONNX Runtime executes that on GPU.
# If not the kernel is executed on CPU.
sess = ort.InferenceSession(str(onnx_file), providers= providers)
outputs = sess.run(output_names, inputs)
Post-Processing for the output
Output terminology
One detected object: np.array([n_xc, n_yc, n_w, n_h, confidence score, class_idx])
n_xc: normalize box x-center
n_yc: normalize box y-center
n_w: normalize box width
n_h: normalize box height
confidence score
class_idx: class index of training category list
One detection results: array of detected objects
Batch detection results: array of detection results
Post-processing script
# Load category
with open("/path/labels.txt") as f:
category = f.read()
class_list = category.split("\n")
img_w = 1280 # modify as your original image width
img_h = 720 # modify as your original image height
prediction_results = outputs[0]
for img_results in prediction_results:
for obj in img_results:
category = class_list[ int(obj[5])]
confidence_score = obj[4]
x = int(obj[0] * img_w)
y = int(obj[1] * img_h)
w = int(obj[2] * img_w)
h = int(obj[3] * img_h)
# TODO: save the results as your target format
