Paddle 3.3.0 PaddleDetection2.9.0 export ppyoloe+ model error

### bug描述 Describe the Bug 环境 ``` cuda12.8 RTX5060 Window10 paddlepadle-gpu 3.3.0 PaddleDetection 2.9.0 ``` 导出命令 ``` cd PaddleDetection python tools/export_model.py ^ -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml ^ --output_dir=output/inference_model ^ -o weights=../models/ppyoloe/ppyoloe_plus_crn_l_80e_coco.pdparams ``` 报错如下 ``` PaddleDetection_2_9_0>python tools/export_model.py ^ More? -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml ^ More? --output_dir=output/inference_model ^ More? -o weights=../models/ppyoloe/ppyoloe_plus_crn_l_80e_coco.pdparams 信息: 用提供的模式无法找到文件。 [05/11 14:23:03] ppdet.utils.checkpoint INFO: Skipping import of the encryption module. [05/11 14:23:08] ppdet.utils.checkpoint INFO: Finish loading model weights: ../models/ppyoloe/ppyoloe_plus_crn_l_80e_coco.pdparams W0511 14:23:12.831914 25436 eager_utils.cc:3584] Paddle static graph(PIR) not support input out tensor for now!!!!! [05/11 14:23:18] ppdet.data.source.category WARNING: anno_file 'dataset/coco\annotations/instances_val2017.json' is None or not set or not exist, please recheck TrainDataset/EvalDataset/TestDataset.anno_path, otherwise the default categories will be used by metric_type. [05/11 14:23:18] ppdet.data.source.category WARNING: metric_type: COCO, load default categories of COCO. [05/11 14:23:18] ppdet.engine INFO: Export inference config file to output/inference_model\ppyoloe_plus_crn_l_80e_coco\infer_cfg.yml [05/11 14:23:18] ppdet.engine INFO: Skipping import of the encryption module. Traceback (most recent call last): File "G:\paddle\paddle_3_x_test\PaddleDetection_2_9_0\tools\export_model.py", line 121, in <module> main() File "G:\paddle\paddle_3_x_test\PaddleDetection_2_9_0\tools\export_model.py", line 118, in main run(FLAGS, cfg) File "G:\paddle\paddle_3_x_test\PaddleDetection_2_9_0\tools\export_model.py", line 80, in run trainer.export(FLAGS.output_dir, for_fd=FLAGS.for_fd) File "G:\paddle\paddle_3_x_test\PaddleDetection_2_9_0\ppdet\engine\trainer.py", line 1458, in export static_model, pruned_input_spec = self._model_to_static( ^^^^^^^^^^^^^^^^^^^^^^ File "G:\paddle\paddle_3_x_test\PaddleDetection_2_9_0\ppdet\engine\trainer.py", line 1299, in _model_to_static input_spec, static_model.forward.main_program, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\mytest\cu128_pt271_py311_env\Lib\site-packages\paddle\jit\dy2static\program_translator.py", line 1101, in main_program concrete_program = self.concrete_program ^^^^^^^^^^^^^^^^^^^^^ File "G:\mytest\cu128_pt271_py311_env\Lib\site-packages\paddle\jit\dy2static\program_translator.py", line 985, in concrete_program return self.concrete_program_specify_input_spec(input_spec=None) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\mytest\cu128_pt271_py311_env\Lib\site-packages\paddle\jit\dy2static\program_translator.py", line 1029, in concrete_program_specify_input_spec concrete_program, _ = self.get_concrete_program( ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\mytest\cu128_pt271_py311_env\Lib\site-packages\paddle\jit\dy2static\program_translator.py", line 918, in get_concrete_program concrete_program, partial_program_layer = self._program_cache[ ^^^^^^^^^^^^^^^^^^^^ File "G:\mytest\cu128_pt271_py311_env\Lib\site-packages\paddle\jit\dy2static\program_translator.py", line 1690, in __getitem__ self._caches[item_id] = self._build_once(item) ^^^^^^^^^^^^^^^^^^^^^^ File "G:\mytest\cu128_pt271_py311_env\Lib\site-packages\paddle\jit\dy2static\program_translator.py", line 1635, in _build_once concrete_program = ConcreteProgram.from_func_spec( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\mytest\cu128_pt271_py311_env\Lib\site-packages\paddle\base\wrapped_decorator.py", line 50, in wrapper return decorated(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\mytest\cu128_pt271_py311_env\Lib\site-packages\paddle\base\dygraph\base.py", line 114, in __impl__ return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "G:\mytest\cu128_pt271_py311_env\Lib\site-packages\paddle\jit\dy2static\program_translator.py", line 1407, in from_func_spec error_data.raise_new_exception() File "G:\mytest\cu128_pt271_py311_env\Lib\site-packages\paddle\jit\dy2static\error.py", line 454, in raise_new_exception raise new_exception from None TypeError: In transformed code: File "G:\paddle\paddle_3_x_test\PaddleDetection_2_9_0\ppdet\modeling\architectures\meta_arch.py", line 55, in forward if self.training: File "G:\paddle\paddle_3_x_test\PaddleDetection_2_9_0\ppdet\modeling\architectures\meta_arch.py", line 65, in forward for inp in inputs_list: File "G:\paddle\paddle_3_x_test\PaddleDetection_2_9_0\ppdet\modeling\architectures\meta_arch.py", line 69, in forward outs.append(self.get_pred()) File "G:\paddle\paddle_3_x_test\PaddleDetection_2_9_0\ppdet\modeling\architectures\yolo.py", line 150, in get_pred return self._forward() File "G:\paddle\paddle_3_x_test\PaddleDetection_2_9_0\ppdet\modeling\architectures\yolo.py", line 92, in _forward if self.training: File "G:\paddle\paddle_3_x_test\PaddleDetection_2_9_0\ppdet\modeling\architectures\yolo.py", line 101, in _forward yolo_head_outs = self.yolo_head(neck_feats) File "G:\paddle\paddle_3_x_test\PaddleDetection_2_9_0\ppdet\modeling\heads\ppyoloe_head.py", line 277, in forward if self.training: File "G:\paddle\paddle_3_x_test\PaddleDetection_2_9_0\ppdet\modeling\heads\ppyoloe_head.py", line 288, in forward return self.forward_eval(feats) File "G:\paddle\paddle_3_x_test\PaddleDetection_2_9_0\ppdet\modeling\heads\ppyoloe_head.py", line 242, in forward_eval for i, feat in enumerate(feats): File "G:\paddle\paddle_3_x_test\PaddleDetection_2_9_0\ppdet\modeling\heads\ppyoloe_head.py", line 249, in forward_eval cls_logit = self.pred_cls[i](self.stem_cls[i](feat, avg_feat) + File "G:\paddle\paddle_3_x_test\PaddleDetection_2_9_0\ppdet\modeling\heads\ppyoloe_head.py", line 50, in forward def forward(self, feat, avg_feat): weight = F.sigmoid(self.fc(avg_feat)) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ <--- HERE if self.conv: return self.conv(feat * weight) File "G:\mytest\cu128_pt271_py311_env\Lib\site-packages\paddle\base\dygraph\generated_tensor_methods_patch.py", line 106, in _sigmoid return _C_ops.sigmoid(*args, **kwargs) TypeError: (InvalidType) sigmoid(): argument (position 1) must be Value, but got Variable (at ..\paddle\fluid\pybind\eager_utils.cc:2313) ``` @jzhang533 @claude @wanglun @lileding @newway 大佬们，请教一下，这是什么原因，有没有解决方法？我看有些是说将paddlepaddle-gpu降到2.6.2，但是paddlepaddle-gpu==2.6.2不支持rtx50显卡！能不能直接在paddlepaddle-gpu3.3.0版本修复？ ### 其他补充信息 Additional Supplementary Information _No response_