pytorch 模型转onnx时，把torch.nn.functional.interpolate函数转成了Resize ，然后使用atc工具进行转化的时候报错：

ATC run failed, Please check the detail log, Try 'atc --help' for more information 

E10042: [PID: 39712] 2024-12-17-08:08:46.904.822 GenerateOfflineModel execute failed. 

        TraceBack (most recent call last): 

        Input format not support[FUNC:ResizeNearestInferShape][FILE:image_ops.cc][LINE:3162] 

        Call InferShapeAndType for node:PartitionedCall_/Resize_Resize_419(Resize) failed[FUNC:Infer][FILE:infershape_pass.cc][LINE:117] 

        process pass InferShapePass on node:PartitionedCall_/Resize_Resize_419 failed, ret:4294967295[FUNC:RunPassesOnNode][FILE:base_pass.cc][LINE:563] 

        build graph failed, graph id:0, ret:1343242270[FUNC:BuildModelWithGraphId][FILE:ge_generator.cc][LINE:1615] 

        GenerateOfflineModel execute failed.

使用的转化命令：

atc --model=/root/zpq/a2f.onnx --framework=5 --output=a2f --input_shape="input1:1,29333" --soc_version Ascend310P3

torch 代码：

x= F.interpolate(outputs.transpose(1, 2), size=55, align_corners=True, mode='linear')

outputs 的shape为torch.Size([1, 91, 768])

转化成onnx的信息如下：

%/Resize_output_0 = Resize[coordinate_transformation_mode = 'align_corners', cubic_coeff_a = -0.75, mode = 'linear', nearest_mode = 'floor'](%/Transpose_output_0, %, %, %/Concat_1_output_0)

opset_version=12

请问大神们这个问题怎么解决