maskrcnn导出onnx，onnxruntime输出第一个维度为0.

[YaoJiawei329]

System information

• Have I written custom code:

import torch import onnxruntime as ort import cv2 import torchvision.transforms as transforms import numpy as np import onnx

onnx_model = onnx.load("mask_rcnn_47.onnx") onnx.checker.check_model(onnx_model) providers = ort.get_available_providers() sess = ort.InferenceSession("./mask_rcnn_47.onnx", providers=ort.get_available_providers())

image = cv2.imread("./data/metal_bar/train2017/32022-8-25-metal-16.jpg", 1) cv2.imshow("image", image) cv2.waitKey(1000) img = image[:, :, ::-1].transpose((2, 0, 1)).copy() tensor = torch.Tensor(img_) tensor2 = torch.unsqueeze(tensor, dim=0) print(tensor2.size()) tensor = torch.tensor(tensor2, dtype=torch.float32) img = tensor.numpy()

output = ["boxes", "class", "confidence", "result"] result = sess.run(output, {"images": img})

print("len of output = {}".format(len(result)))

• OS Platform(e.g., window10 or Linux Ubuntu 16.04): window10
• Python version: python3.8
• Deep learning framework and version(e.g., Tensorflow2.1 or Pytorch1.3): Pytorch1.12
• Use GPU or not: onnxruntime inference NOT use GPU
• CUDA/cuDNN version(if you use GPU):CUDA11.6
• The network you trained(e.g., Resnet34 network):

Describe the current behavior maskrcnn导出onnx，onnxruntime输出第一个维度为0. backbone改为inceptionV2，训练出来的pt模型可以正常推理，转完onnx之后推理输出维度为0.

Error info / logs result = {list: 4} [array([], shape=(0, 4), dtype=float32), array([], dtype=int64), array([], dtype=float32), array([], shape=(0, 1, 1624, 920), dtype=float32)]

[WZMIAOMIAO]

抱歉，这个问题我不清楚，可能是你自己导出的ONNX有问题。