C++进行生成的test_seg中,使用matting模型，会报错

[xiefuwei390]

问题确认 Search before asking

• 我已经搜索过问题，但是没有找到解答。I have searched the question and found no related answer.

请提出你的问题 Please ask your question

日志如下:当我用cmake生成了windows的工程后,运行有如下错误**,请问如何解决?**
D:\wks\padlepadle\PaddleSeg-release-2.10\deploy\cpp\build-win\Release>.\test_seg.exe --model_dir=pp-matting-hrnet_w18-human_512 --img_path=human.png --devices=GPU --save_dir=output
WARNING: Logging before InitGoogleLogging() is written to STDERR
I0128 20:42:54.466872 47784 test_seg.cc:74] Use GPU
e[1me[35m--- Running analysis [ir_graph_build_pass]e[0m
e[1me[35m--- Running analysis [ir_graph_clean_pass]e[0m
e[1me[35m--- Running analysis [ir_analysis_pass]e[0m
e[32m--- Running IR pass [is_test_pass]e[0m
e[32m--- Running IR pass [simplify_with_basic_ops_pass]e[0m
e[32m--- Running IR pass [conv_bn_fuse_pass]e[0m
WARNING: Logging before InitGoogleLogging() is written to STDERR
I0128 20:42:58.785944 47784 fuse_pass_base.cc:57] --- detected 305 subgraphs
e[32m--- Running IR pass [conv_eltwiseadd_bn_fuse_pass]e[0m
I0128 20:42:59.515856 47784 fuse_pass_base.cc:57] --- detected 28 subgraphs
e[32m--- Running IR pass [embedding_eltwise_layernorm_fuse_pass]e[0m
e[32m--- Running IR pass [multihead_matmul_fuse_pass_v2]e[0m
e[32m--- Running IR pass [gpu_cpu_squeeze2_matmul_fuse_pass]e[0m
e[32m--- Running IR pass [gpu_cpu_reshape2_matmul_fuse_pass]e[0m
e[32m--- Running IR pass [gpu_cpu_flatten2_matmul_fuse_pass]e[0m
e[32m--- Running IR pass [gpu_cpu_map_matmul_v2_to_mul_pass]e[0m
e[32m--- Running IR pass [gpu_cpu_map_matmul_v2_to_matmul_pass]e[0m
e[32m--- Running IR pass [matmul_scale_fuse_pass]e[0m
e[32m--- Running IR pass [multihead_matmul_fuse_pass_v3]e[0m
e[32m--- Running IR pass [gpu_cpu_map_matmul_to_mul_pass]e[0m
e[32m--- Running IR pass [fc_fuse_pass]e[0m
e[32m--- Running IR pass [fc_elementwise_layernorm_fuse_pass]e[0m
e[32m--- Running IR pass [conv_elementwise_add_act_fuse_pass]e[0m
e[32m--- Running IR pass [conv_elementwise_add2_act_fuse_pass]e[0m
e[32m--- Running IR pass [conv_elementwise_add_fuse_pass]e[0m
I0128 20:43:01.226245 47784 fuse_pass_base.cc:57] --- detected 167 subgraphs
e[32m--- Running IR pass [transpose_flatten_concat_fuse_pass]e[0m
e[32m--- Running IR pass [runtime_context_cache_pass]e[0m
e[1me[35m--- Running analysis [ir_params_sync_among_devices_pass]e[0m
I0128 20:43:01.262872 47784 ir_params_sync_among_devices_pass.cc:100] Sync params from CPU to GPU
e[1me[35m--- Running analysis [adjust_cudnn_workspace_size_pass]e[0m
e[1me[35m--- Running analysis [inference_op_replace_pass]e[0m
e[1me[35m--- Running analysis [memory_optimize_pass]e[0m
I0128 20:43:01.347045 47784 memory_optimize_pass.cc:216] Cluster name : relu_270.tmp_0 size: 14400
I0128 20:43:01.347728 47784 memory_optimize_pass.cc:216] Cluster name : relu_0.tmp_0 size: 256
I0128 20:43:01.347728 47784 memory_optimize_pass.cc:216] Cluster name : relu_251.tmp_0 size: 288
I0128 20:43:01.348111 47784 memory_optimize_pass.cc:216] Cluster name : pool2d_2.tmp_0 size: 14400
I0128 20:43:01.348189 47784 memory_optimize_pass.cc:216] Cluster name : relu_271.tmp_0 size: 2048
I0128 20:43:01.348366 47784 memory_optimize_pass.cc:216] Cluster name : relu_267.tmp_0 size: 576
I0128 20:43:01.348366 47784 memory_optimize_pass.cc:216] Cluster name : relu_274.tmp_0 size: 1024
I0128 20:43:01.348366 47784 memory_optimize_pass.cc:216] Cluster name : relu_211.tmp_0 size: 288
I0128 20:43:01.348366 47784 memory_optimize_pass.cc:216] Cluster name : relu_243.tmp_0 size: 144
I0128 20:43:01.348366 47784 memory_optimize_pass.cc:216] Cluster name : relu_235.tmp_0 size: 72
I0128 20:43:01.348366 47784 memory_optimize_pass.cc:216] Cluster name : shape_0.tmp_0 size: 16
I0128 20:43:01.348366 47784 memory_optimize_pass.cc:216] Cluster name : img size: 12
I0128 20:43:01.348366 47784 memory_optimize_pass.cc:216] Cluster name : shape_16.tmp_0_slice_0 size: 8
e[1me[35m--- Running analysis [ir_graph_to_program_pass]e[0m
I0128 20:43:01.677953 47784 analysis_predictor.cc:1035] ======= optimize end =======
I0128 20:43:01.678951 47784 naive_executor.cc:102] --- skip [feed], feed -> img
I0128 20:43:01.692044 47784 naive_executor.cc:102] --- skip [tmp_75], fetch -> fetch
W0128 20:43:01.693042 47784 gpu_resources.cc:61] Please NOTE: device: 0, GPU Compute Capability: 8.6, Driver API Version: 12.3, Runtime API Version: 11.6
W0128 20:43:01.697043 47784 gpu_resources.cc:91] device: 0, cuDNN Version: 8.5.

---

C++ Traceback (most recent call last):

Not support stack backtrace yet.

---

Error Message Summary:

InvalidArgumentError: The type of data we are trying to retrieve does not match the type of data currently contained in the container. (at ..\paddle\phi\core\dense_tensor.cc:148)

[xiefuwei390]

以上我修改了代码中的输出为float的向量后, std::vector out_data(out_num) 没有报错了,但是我使用以上的模型做抠图,输出的图形不对的？是我使用得不对吗? 我换成ppmattingv2-stdc1-human_512 这个做模型,也依然是不对，

[cuicheng01]

paddle的版本用的是哪个呢？方便的话降低到2.5试试呢？

[TingquanGao]

The issue has no response for a long time and will be closed. You can reopen or new another issue if are still confused.

---

From Bot