【onnx】PSPNet导出onnx模型运行时报错

| name       | about	                             | labels   |
| ---------- | ------------------------------------- | -------- |
| Bug Report | Use this template for reporting a bug | kind/bug |

### Describe the current behavior / 问题描述 (Mandatory / 必填)

### Environment / 环境信息 (Mandatory / 必填)
- **Hardware Environment(`Ascend`/`GPU`/`CPU`)  / 硬件环境**:  GPU
> Please delete the backend not involved / 请删除不涉及的后端:
> /device ascend/GPU/CPU/kirin/等其他芯片

- **Software Environment / 软件环境 (Mandatory / 必填)**:
-- MindSpore version (e.g., 1.7.0.Bxxx) :1.7.0-gpu
-- Python version (e.g., Python 3.7.5) :3.7.5
-- OS platform and distribution (e.g., Linux Ubuntu 16.04):Linux Ubuntu 16.04
-- GCC/Compiler version (if compiled from source):

- **Excute Mode / 执行模式 (Mandatory / 必填)(`PyNative`/`Graph`)**: Graph
> Please delete the mode not involved / 请删除不涉及的模式:
> /mode graph

### Steps to reproduce the issue / 重现步骤 (Mandatory / 必填)
1. 使用Hub上提供的pspnet预训练模型（VOC2012）
2.  导出onnx：
python export.py --yaml_path /home/mindspore/pspnet/PSPNet/config/voc2012_pspnet50.yaml \
--ckpt_file /home/mindspore/pspnet/checkpoints/pspnet_ascend_v170_voc2012_research_cv_miou74.15_allacc94.01.ckpt \
--file_format ONNX
路径请根据自己情况自行修改
3. onnx推理命令：
bash scripts/run_eval_onnx.sh /home/mindspore/pspnet/PSPNet/config/voc2012_pspnet50.yaml 7

为了便于快速复现，工程文件已上传至百度云：
链接：https://pan.baidu.com/s/1wCNS0oJnlI0v5WTV0o7VRQ 
提取码：HW66

### Describe the expected behavior / 预期结果 (Mandatory / 必填)
 模型正确运行并输出结果
### Related log / screenshot / 日志 / 截图 (Mandatory / 必填)
  ![错误信息](https://images.gitee.com/uploads/images/2022/0709/092150_aed739ca_5638098.png "屏幕截图.png")
### Special notes for this issue/备注 (Optional / 选填)

MindSpore/models

内容风险标识

评论 (16)

MindSpore/models .gitee-modal { width: 500px !important; }

内容风险标识