-
Notifications
You must be signed in to change notification settings - Fork 7.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
C++ Inference Throws Error #4174
Comments
Please check the shape of the input image, and try to convert this image to other sizes before predicting. |
Thanks. |
I've the same error, ask for help OS: $ ./ppocr system --det_model_dir=/home/mreo/repo/MeoAssistantArknights/3rdparty/resource/PaddleOCR/det --rec_model_dir=/home/mreo/repo/MeoAssistantArknights/3rdparty/resource/PaddleOCR/rec --image_dir=/home/mreo/cpp_infer_pred_12.png
mode: system
total images num: 1
WARNING: Logging before InitGoogleLogging() is written to STDERR
I1227 00:43:03.032341 103269 analysis_predictor.cc:155] Profiler is deactivated, and no profiling report will be generated.
--- Running analysis [ir_graph_build_pass]
--- Running analysis [ir_graph_clean_pass]
--- Running analysis [ir_analysis_pass]
--- Running IR pass [simplify_with_basic_ops_pass]
--- Running IR pass [attention_lstm_fuse_pass]
--- Running IR pass [seqconv_eltadd_relu_fuse_pass]
--- Running IR pass [seqpool_cvm_concat_fuse_pass]
--- Running IR pass [mul_lstm_fuse_pass]
--- Running IR pass [fc_gru_fuse_pass]
--- Running IR pass [mul_gru_fuse_pass]
--- Running IR pass [seq_concat_fc_fuse_pass]
--- Running IR pass [squeeze2_matmul_fuse_pass]
--- Running IR pass [reshape2_matmul_fuse_pass]
--- Running IR pass [flatten2_matmul_fuse_pass]
--- Running IR pass [map_matmul_to_mul_pass]
--- Running IR pass [fc_fuse_pass]
--- Running IR pass [repeated_fc_relu_fuse_pass]
--- Running IR pass [squared_mat_sub_fuse_pass]
--- Running IR pass [conv_bn_fuse_pass]
I1227 00:43:03.142690 103269 graph_pattern_detector.cc:101] --- detected 34 subgraphs
--- Running IR pass [conv_eltwiseadd_bn_fuse_pass]
--- Running IR pass [conv_transpose_bn_fuse_pass]
--- Running IR pass [conv_transpose_eltwiseadd_bn_fuse_pass]
I1227 00:43:03.150655 103269 graph_pattern_detector.cc:101] --- detected 2 subgraphs
--- Running IR pass [is_test_pass]
--- Running IR pass [runtime_context_cache_pass]
--- Running analysis [ir_params_sync_among_devices_pass]
--- Running analysis [adjust_cudnn_workspace_size_pass]
--- Running analysis [inference_op_replace_pass]
--- Running analysis [memory_optimize_pass]
I1227 00:43:03.166231 103269 memory_optimize_pass.cc:201] Cluster name : x size: 12
I1227 00:43:03.166283 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_58.tmp_0 size: 24
I1227 00:43:03.166316 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_61.tmp_0 size: 52
I1227 00:43:03.166323 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_96.tmp_0 size: 76
I1227 00:43:03.166326 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_65.tmp_0 size: 76
I1227 00:43:03.166329 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_60.tmp_0 size: 104
I1227 00:43:03.166332 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_57.tmp_0 size: 24
I1227 00:43:03.166349 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_69.tmp_0 size: 76
I1227 00:43:03.166354 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_78.tmp_0 size: 960
I1227 00:43:03.166370 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_82.tmp_0 size: 1076
I1227 00:43:03.166378 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_85.tmp_0 size: 256
I1227 00:43:03.166380 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_80.tmp_0 size: 1344
I1227 00:43:03.166383 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_86.tmp_0 size: 1536
I1227 00:43:03.166386 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_88.tmp_0 size: 1920
I1227 00:43:03.166390 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_87.tmp_0 size: 256
I1227 00:43:03.166393 103269 memory_optimize_pass.cc:201] Cluster name : batch_norm_44.tmp_3 size: 1536
I1227 00:43:03.166396 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_59.tmp_0 size: 24
I1227 00:43:03.166399 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_84.tmp_0 size: 1536
I1227 00:43:03.166404 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_75.tmp_0 size: 128
I1227 00:43:03.166406 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_76.tmp_0 size: 308
I1227 00:43:03.166409 103269 memory_optimize_pass.cc:201] Cluster name : hardswish_19.tmp_0 size: 1920
I1227 00:43:03.166411 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_70.tmp_0 size: 480
I1227 00:43:03.166414 103269 memory_optimize_pass.cc:201] Cluster name : batch_norm_46.tmp_3 size: 1920
I1227 00:43:03.166419 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_66.tmp_0 size: 204
I1227 00:43:03.166422 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_74.tmp_0 size: 308
I1227 00:43:03.166424 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_92.tmp_0 size: 308
I1227 00:43:03.166429 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_77.tmp_0 size: 128
I1227 00:43:03.166431 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_63.tmp_0 size: 52
I1227 00:43:03.166433 103269 memory_optimize_pass.cc:201] Cluster name : tmp_0 size: 308
I1227 00:43:03.166436 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_81.tmp_0 size: 180
I1227 00:43:03.166440 103269 memory_optimize_pass.cc:201] Cluster name : nearest_interp_v2_1220.tmp_0 size: 308
I1227 00:43:03.166442 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_67.tmp_0 size: 76
I1227 00:43:03.166445 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_72.tmp_0 size: 332
I1227 00:43:03.166447 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_83.tmp_0 size: 256
I1227 00:43:03.166465 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_68.tmp_0 size: 256
I1227 00:43:03.166481 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_79.tmp_0 size: 180
I1227 00:43:03.166486 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_64.tmp_0 size: 160
I1227 00:43:03.166501 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_71.tmp_0 size: 128
I1227 00:43:03.166505 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_73.tmp_0 size: 128
I1227 00:43:03.166508 103269 memory_optimize_pass.cc:201] Cluster name : conv2d_62.tmp_0 size: 128
--- Running analysis [ir_graph_to_program_pass]
I1227 00:43:03.196521 103269 analysis_predictor.cc:598] ======= optimize end =======
I1227 00:43:03.196640 103269 naive_executor.cc:107] --- skip [feed], feed -> x
I1227 00:43:03.197862 103269 naive_executor.cc:107] --- skip [tmp_0], fetch -> fetch
label file: ./ppocr_keys_v1.txt
I1227 00:43:03.198449 103269 analysis_predictor.cc:155] Profiler is deactivated, and no profiling report will be generated.
--- Running analysis [ir_graph_build_pass]
--- Running analysis [ir_graph_clean_pass]
--- Running analysis [ir_analysis_pass]
--- Running IR pass [simplify_with_basic_ops_pass]
--- Running IR pass [attention_lstm_fuse_pass]
--- Running IR pass [seqconv_eltadd_relu_fuse_pass]
--- Running IR pass [seqpool_cvm_concat_fuse_pass]
--- Running IR pass [mul_lstm_fuse_pass]
--- Running IR pass [fc_gru_fuse_pass]
--- Running IR pass [mul_gru_fuse_pass]
--- Running IR pass [seq_concat_fc_fuse_pass]
--- Running IR pass [squeeze2_matmul_fuse_pass]
--- Running IR pass [reshape2_matmul_fuse_pass]
--- Running IR pass [flatten2_matmul_fuse_pass]
--- Running IR pass [map_matmul_to_mul_pass]
I1227 00:43:03.244259 103269 graph_pattern_detector.cc:101] --- detected 1 subgraphs
--- Running IR pass [fc_fuse_pass]
--- Running IR pass [repeated_fc_relu_fuse_pass]
--- Running IR pass [squared_mat_sub_fuse_pass]
--- Running IR pass [conv_bn_fuse_pass]
--- Running IR pass [conv_eltwiseadd_bn_fuse_pass]
--- Running IR pass [conv_transpose_bn_fuse_pass]
--- Running IR pass [conv_transpose_eltwiseadd_bn_fuse_pass]
--- Running IR pass [is_test_pass]
--- Running IR pass [runtime_context_cache_pass]
--- Running analysis [ir_params_sync_among_devices_pass]
--- Running analysis [adjust_cudnn_workspace_size_pass]
--- Running analysis [inference_op_replace_pass]
--- Running analysis [memory_optimize_pass]
I1227 00:43:03.281141 103269 memory_optimize_pass.cc:201] Cluster name : lstm_0._generated_var_0 size: 1
I1227 00:43:03.281186 103269 memory_optimize_pass.cc:201] Cluster name : fill_constant_batch_size_like_149.tmp_0 size: 768
I1227 00:43:03.281190 103269 memory_optimize_pass.cc:201] Cluster name : elementwise_add_5 size: 19200
I1227 00:43:03.281191 103269 memory_optimize_pass.cc:201] Cluster name : batch_norm_6.tmp_2 size: 25600
I1227 00:43:03.281193 103269 memory_optimize_pass.cc:201] Cluster name : x size: 38400
I1227 00:43:03.281194 103269 memory_optimize_pass.cc:201] Cluster name : ctc_fc.tmp_1 size: 662500
I1227 00:43:03.281195 103269 memory_optimize_pass.cc:201] Cluster name : lstm_0.tmp_3 size: 1
I1227 00:43:03.281198 103269 memory_optimize_pass.cc:201] Cluster name : ctc_fc.tmp_0 size: 662500
I1227 00:43:03.281198 103269 memory_optimize_pass.cc:201] Cluster name : ctc_fc_w_attr.quantized.dequantized size: 2544000
--- Running analysis [ir_graph_to_program_pass]
I1227 00:43:03.332463 103269 analysis_predictor.cc:598] ======= optimize end =======
I1227 00:43:03.332615 103269 naive_executor.cc:107] --- skip [feed], feed -> x
I1227 00:43:03.336149 103269 naive_executor.cc:107] --- skip [ctc_fc.tmp_0], fetch -> fetch
WARNING: Logging before InitGoogleLogging() is written to STDERR
I1227 00:43:03.336280 103269 main.cpp:215] The predict img: /home/mreo/cpp_infer_pred_12.png
terminate called after throwing an instance of 'paddle::platform::EnforceNotMet'
what():
Compile Traceback (most recent call last):
File "deploy/slim/prune/export_prune_model.py", line 149, in <module>
main(config, device, logger, vdl_writer)
File "deploy/slim/prune/export_prune_model.py", line 143, in main
paddle.jit.save(model, save_path)
File "<decorator-gen-59>", line 2, in save
File "/usr/local/lib/python3.7/site-packages/paddle/fluid/wrapped_decorator.py", line 25, in __impl__
return wrapped_func(*args, **kwargs)
File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/base.py", line 40, in __impl__
return func(*args, **kwargs)
File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/jit.py", line 681, in save
inner_input_spec)
File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/program_translator.py", line 488, in concrete_program_specify_input_spec
*desired_input_spec)
File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/program_translator.py", line 402, in get_concrete_program
concrete_program, partial_program_layer = self._program_cache[cache_key]
File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/program_translator.py", line 711, in __getitem__
self._caches[item] = self._build_once(item)
File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/program_translator.py", line 702, in _build_once
class_instance=cache_key.class_instance)
File "<decorator-gen-57>", line 2, in from_func_spec
File "/usr/local/lib/python3.7/site-packages/paddle/fluid/wrapped_decorator.py", line 25, in __impl__
return wrapped_func(*args, **kwargs)
File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/base.py", line 40, in __impl__
return func(*args, **kwargs)
File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/program_translator.py", line 652, in from_func_spec
outputs = static_func(*inputs)
File "deploy/slim/prune/../../../ppocr/modeling/architectures/base_model.py", line 74, in forward
x = self.backbone(x)
File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py", line 912, in __call__
outputs = self.forward(*inputs, **kwargs)
File "deploy/slim/prune/../../../ppocr/modeling/backbones/det_mobilenet_v3.py", line 148, in forward
x = self.conv(x)
File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py", line 912, in __call__
outputs = self.forward(*inputs, **kwargs)
File "/tmp/tmp8arpb725.py", line 35, in forward
false_fn_4, (self, x), (x,), (x,))
File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/convert_operators.py", line 210, in convert_ifelse
return _run_py_ifelse(pred, true_fn, false_fn, true_args, false_args)
File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/convert_operators.py", line 235, in _run_py_ifelse
return true_fn(*true_args) if pred else false_fn(*false_args)
File "/tmp/tmp8arpb725.py", line 29, in true_fn_4
true_fn_3, false_fn_3, (x,), (self, x), (x,))
File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/convert_operators.py", line 210, in convert_ifelse
return _run_py_ifelse(pred, true_fn, false_fn, true_args, false_args)
File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/convert_operators.py", line 235, in _run_py_ifelse
return true_fn(*true_args) if pred else false_fn(*false_args)
File "/tmp/tmp8arpb725.py", line 26, in false_fn_3
true_fn_2, false_fn_2, (x,), (x,), (x,))
File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/convert_operators.py", line 210, in convert_ifelse
return _run_py_ifelse(pred, true_fn, false_fn, true_args, false_args)
File "/usr/local/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/convert_operators.py", line 235, in _run_py_ifelse
return true_fn(*true_args) if pred else false_fn(*false_args)
File "deploy/slim/prune/../../../ppocr/modeling/backbones/det_mobilenet_v3.py", line 195, in forward
x = F.activation.hardswish(x)
File "/usr/local/lib/python3.7/site-packages/paddle/nn/functional/activation.py", line 375, in hardswish
helper.append_op(type='hard_swish', inputs={'X': x}, outputs={'Out': out})
File "/usr/local/lib/python3.7/site-packages/paddle/fluid/layer_helper.py", line 43, in append_op
return self.main_program.current_block().append_op(*args, **kwargs)
File "/usr/local/lib/python3.7/site-packages/paddle/fluid/framework.py", line 3225, in append_op
attrs=kwargs.get("attrs", None))
File "/usr/local/lib/python3.7/site-packages/paddle/fluid/framework.py", line 2305, in __init__
for frame in traceback.extract_stack():
--------------------------------------
C++ Traceback (most recent call last):
--------------------------------------
0 paddle::AnalysisPredictor::ZeroCopyRun()
1 paddle::framework::NaiveExecutor::Run()
2 paddle::framework::OperatorBase::Run(paddle::framework::Scope const&, paddle::platform::Place const&)
3 paddle::framework::OperatorWithKernel::RunImpl(paddle::framework::Scope const&, paddle::platform::Place const&) const
4 paddle::framework::OperatorWithKernel::RunImpl(paddle::framework::Scope const&, paddle::platform::Place const&, paddle::framework::RuntimeContext*) const
5 paddle::framework::OperatorWithKernel::ChooseKernel(paddle::framework::RuntimeContext const&, paddle::framework::Scope const&, paddle::platform::Place const&) const
6 paddle::operators::ActivationOp::GetExpectedKernelType(paddle::framework::ExecutionContext const&) const
7 paddle::operators::GetKernelType(paddle::framework::ExecutionContext const&, paddle::framework::OperatorWithKernel const&, std::string const&)
8 paddle::framework::OperatorWithKernel::IndicateVarDataType(paddle::framework::ExecutionContext const&, std::string const&) const
9 paddle::framework::OperatorWithKernel::ParseInputDataType(paddle::framework::ExecutionContext const&, std::string const&, paddle::framework::proto::VarType_Type*) const
10 paddle::platform::EnforceNotMet::EnforceNotMet(paddle::platform::ErrorSummary const&, char const*, int)
11 paddle::platform::GetCurrentTraceBackString[abi:cxx11]()
----------------------
Error Message Summary:
----------------------
InvalidArgumentError: The Tensor in the hard_swish Op's Input Variable X(conv2d_88.tmp_0) is not initialized.
[Hint: Expected t->IsInitialized() == true, but received t->IsInitialized():0 != true:1.] (at /paddle/paddle/fluid/framework/operator.cc:1511)
[operator < hard_swish > error]
[1] 103269 abort (core dumped) ./ppocr system --image_dir=/home/mreo/cpp_infer_pred_12.png |
In my case, calling rec->Run (or running recognition) without cls by specifying NULL for the argument solved this problem. |
Thanks for your reply. I tried it, but it didn't work, the error not changed 😟 I will look for more ways to try to solve it. |
Hello, |
Since you haven't replied for more than 3 months, we have closed this issue/pr. |
* [ce tests] add trt_mode in ppyolo * [ce tests] set amp in tests.sh
I use PaddleOCR 2.3.0.1 + PaddlePaddle 2.1.2 and got the following error at inference with C++. Note the inference succeeded several times and terminated with the error. Any idea?
The text was updated successfully, but these errors were encountered: