Created by: Septend-fun

x2paddle --framework=paddle2onnx --model=export --save_dir=onnx_model paddle.version = 1.8.1 Translating PaddlePaddle to ONNX...

Total:262, Current:260 : multiclass_nms lib/python3.6/site-packages/x2paddle/op_mapper/paddle_custom_layer/multiclass_nms.py:47: UserWarning: The parameter normalized of multiclass_nms OP of Paddle is False, which has diff with ONNX. Please set normalized=True in multiclass_nms of Paddle Please set normalized=True in multiclass_nms of Paddle' Total:262, Current:262 : fetch Traceback (most recent call last): File "/home/bin/x2paddle", line 11, in sys.exit(main()) File "/home/lib/python3.6/site-packages/x2paddle/convert.py", line 272, in main paddle2onnx(args.model, args.save_dir) File "/home/lib/python3.6/site-packages/x2paddle/convert.py", line 194, in paddle2onnx mapper.convert(model.program, save_dir) File "/home/lib/python3.6/site-packages/x2paddle/op_mapper/paddle_op_mapper.py", line 815, in convert onnx.checker.check_model(model) File "/home/lib/python3.6/site-packages/onnx/checker.py", line 91, in check_model C.check_model(model.SerializeToString()) onnx.onnx_cpp2py_export.checker.ValidationError: Unrecognized attribute: max for operator Clip

==> Context: Bad node spec: input: "yolo_box0.tmp_0@pred_box_x1_decode" output: "yolo_box0.tmp_0@pred_box_x1_clip" op_type: "Clip" attribute { name: "max" f: inf type: FLOAT } attribute { name: "min" f: 0 type: FLOAT }