export ONNX and onnxsim

[pcb9382]

@zjjMaiMai
`
parser.add_argument("--images", nargs=2, required=False)
parser.add_argument("--model", type=str, default="HITNet_SF")
parser.add_argument("--ckpt", type=str, default="ckpt/hitnet_sf_finalpass.ckpt")
parser.add_argument("--width", type=int, default=None)
parser.add_argument("--output", default="./")
args = parser.parse_args()

model = PredictModel(**vars(args))
model.eval()
ckpt = torch.load("ckpt/hitnet_sf_finalpass.ckpt")
# for name in ckpt['state_dict']:
#     print('name is {}'.format(name))
model.load_state_dict(ckpt["state_dict"])
device = torch.device("cuda")
model = model.to(device)
input_names = ["input0"]#,"input1"
#output_names = ["output0"]
output_names=["output_%d" % i for i in range(1)]
#output_names = ["output0","output1","output2","output3"]
print(output_names)
left = torch.randn(1, 3, 480, 640).to(device)
right = torch.randn(1, 3, 480, 640).to(device)
a=(left, right)
export_onnx_file = "./HITNet_SF_5.onnx"
# torch_out = torch.onnx._export(model(left,right),(left,right), output_onnx, export_params=True, verbose=False,
#                                input_names=input_names, output_names=output_names)
torch_out = torch.onnx.export(model,args=(left,right),f=export_onnx_file,verbose=False,input_names=input_names,
                              output_names=output_names, export_params=True,opset_version=11)
`

I use the above code to export onnx and can get an onnx model of about 1.9M
python3 -m onnxsim HITNet_SF_5.onnx HITNet_SF_5-smi.onnx

When I optimized the onnx model, the following error occurred. After investigation, it was found that the max operation caused the optimization error;

How to solve it please, thank you！