magicleap / SuperPointPretrainedNetwork

PyTorch pre-trained model for real-time interest point detection, description, and sparse tracking (https://arxiv.org/abs/1712.07629)
Other
1.93k stars 397 forks source link

Onnx Inference #19

Open Zumbalamambo opened 3 years ago

Zumbalamambo commented 3 years ago

I'm using the following code to estimate the keypoints and matches using onnx

import json

import onnxruntime
import numpy as np
import cv2

path = "output/rgb.png"
img = cv2.imread(path)
img = cv2.resize(img, dsize=(640, 480), interpolation=cv2.INTER_AREA)
img.resize((1, 1, 640, 480))
data = json.dumps({'data': img.tolist()})
data = np.array(json.loads(data)['data']).astype('float32')
session = onnxruntime.InferenceSession("output/superpoint_640x480.onnx", None)
input_name = session.get_inputs()[0].name
output_name = session.get_outputs()[0].name

print(input_name)
print(output_name)

result = session.run([output_name], {input_name: data})
print(result)

How do I interpret the result? or is it the proper way of doing it?

bb67ao commented 1 year ago

can you get a right result.I tried to make the whole spnet to onnx before,while got an error when inferenced with ort in c++