Linux FastDeploy docker OCR推理报错 #1687
Comments
|
好，后面我复现一下看看 |
|
你好，目前在 registry.baidubce.com/paddlepaddle/fastdeploy:1.0.5-cpu-only-21.10 这个镜像中，已复现出问题. paddle inference后端会出现上述问题. |
|
@yunyaoXYY 请问这个问题修复了没 |
没有，你必须用paddleinference吗，其他的后端是否能满足你的需求呢 |
|
@yunyaoXYY paddleinference ocr推理的精度视乎高一些，另外想请教一下不同的后端都支持这些参数设置吗？https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_ch/inference_args.md |
|
@yunyaoXYY |
|
同上，无论openvino还是paddle都不行 |
@yunyaoXYY |
|
同样，改成openvino还是没有结果 |
温馨提示：根据社区不完全统计，按照模板提问，可以加快回复和解决问题的速度
环境
按照https://github.com/PaddlePaddle/PaddleOCR/tree/dygraph/deploy/fastdeploy/serving/fastdeploy_serving文档进行操作。
server端，执行fastdeployserver --model-repository=/ocr_serving/models 启动服务成功 ，日志如下：
I0323 02:13:45.461891 1362 model_repository_manager.cc:1022] loading: cls_runtime:1
I0323 02:13:45.562215 1362 model_repository_manager.cc:1022] loading: det_preprocess:1
I0323 02:13:45.662454 1362 model_repository_manager.cc:1022] loading: det_runtime:1
I0323 02:13:45.699268 1362 fastdeploy_runtime.cc:1182] TRITONBACKEND_Initialize: fastdeploy
I0323 02:13:45.699309 1362 fastdeploy_runtime.cc:1191] Triton TRITONBACKEND API version: 1.6
I0323 02:13:45.699326 1362 fastdeploy_runtime.cc:1196] 'fastdeploy' TRITONBACKEND API version: 1.6
I0323 02:13:45.699348 1362 fastdeploy_runtime.cc:1225] backend configuration:
{}
I0323 02:13:45.699429 1362 fastdeploy_runtime.cc:1255] TRITONBACKEND_ModelInitialize: cls_runtime (version 1)
[WARNING] fastdeploy/runtime/runtime_option.cc(189)::SetPaddleMKLDNN
RuntimeOption::SetPaddleMKLDNNwill be removed in v1.2.0, please modify its member variable directly, e.goption.paddle_infer_option.enable_mkldnn = trueI0323 02:13:45.702743 1362 fastdeploy_runtime.cc:1294] TRITONBACKEND_ModelInstanceInitialize: cls_runtime_0 (CPU device 0)
WARNING: Logging before InitGoogleLogging() is written to STDERR
W0323 10:13:45.716488 1363 analysis_config.cc:972] It is detected that mkldnn and memory_optimize_pass are enabled at the same time, but they are not supported yet. Currently, memory_optimize_pass is explicitly disabled
I0323 02:13:45.762764 1362 model_repository_manager.cc:1022] loading: rec_postprocess:1
I0323 02:13:45.863142 1362 model_repository_manager.cc:1022] loading: det_postprocess:1
I0323 02:13:45.963409 1362 model_repository_manager.cc:1022] loading: cls_postprocess:1
[INFO] fastdeploy/runtime/runtime.cc(266)::CreatePaddleBackend Runtime initialized with Backend::PDINFER in Device::CPU.
I0323 02:13:46.030319 1362 model_repository_manager.cc:1183] successfully loaded 'cls_runtime' version 1
I0323 02:13:46.030720 1362 fastdeploy_runtime.cc:1255] TRITONBACKEND_ModelInitialize: det_runtime (version 1)
[WARNING] fastdeploy/runtime/runtime_option.cc(189)::SetPaddleMKLDNN
RuntimeOption::SetPaddleMKLDNNwill be removed in v1.2.0, please modify its member variable directly, e.goption.paddle_infer_option.enable_mkldnn = trueI0323 02:13:46.032259 1362 python.cc:1875] TRITONBACKEND_ModelInstanceInitialize: det_preprocess_0 (CPU device 0)
I0323 02:13:46.063790 1362 model_repository_manager.cc:1022] loading: rec_runtime:1
/usr/lib/python3/dist-packages/requests/init.py:89: RequestsDependencyWarning: urllib3 (1.26.14) or chardet (3.0.4) doesn't match a supported version!
warnings.warn("urllib3 ({}) or chardet ({}) doesn't match a supported "
model_config: {'name': 'det_preprocess', 'platform': '', 'backend': 'python', 'version_policy': {'latest': {'num_versions': 1}}, 'max_batch_size': 1, 'input': [{'name': 'INPUT_0', 'data_type': 'TYPE_UINT8', 'format': 'FORMAT_NONE', 'dims': [-1, -1, 3], 'is_shape_tensor': False, 'allow_ragged_batch': False}], 'output': [{'name': 'OUTPUT_0', 'data_type': 'TYPE_FP32', 'dims': [3, -1, -1], 'label_filename': '', 'is_shape_tensor': False}, {'name': 'OUTPUT_1', 'data_type': 'TYPE_INT32', 'dims': [4], 'label_filename': '', 'is_shape_tensor': False}], 'batch_input': [], 'batch_output': [], 'optimization': {'priority': 'PRIORITY_DEFAULT', 'input_pinned_memory': {'enable': True}, 'output_pinned_memory': {'enable': True}, 'gather_kernel_buffer_threshold': 0, 'eager_batching': False}, 'instance_group': [{'name': 'det_preprocess_0', 'kind': 'KIND_CPU', 'count': 1, 'gpus': [], 'secondary_devices': [], 'profile': [], 'passive': False, 'host_policy': ''}], 'default_model_filename': '', 'cc_model_filenames': {}, 'metric_tags': {}, 'parameters': {}, 'model_warmup': []}
preprocess input names: ['INPUT_0']
preprocess output names: ['OUTPUT_0', 'OUTPUT_1']
I0323 02:13:46.460128 1362 fastdeploy_runtime.cc:1294] TRITONBACKEND_ModelInstanceInitialize: det_runtime_0 (CPU device 0)
I0323 02:13:46.460377 1362 model_repository_manager.cc:1183] successfully loaded 'det_preprocess' version 1
[INFO] fastdeploy/runtime/runtime.cc(266)::CreatePaddleBackend Runtime initialized with Backend::PDINFER in Device::CPU.
I0323 02:13:46.933564 1362 python.cc:1875] TRITONBACKEND_ModelInstanceInitialize: rec_postprocess_0 (CPU device 0)
I0323 02:13:46.933794 1362 model_repository_manager.cc:1183] successfully loaded 'det_runtime' version 1
/usr/lib/python3/dist-packages/requests/init.py:89: RequestsDependencyWarning: urllib3 (1.26.14) or chardet (3.0.4) doesn't match a supported version!
warnings.warn("urllib3 ({}) or chardet ({}) doesn't match a supported "
model_config: {'name': 'rec_postprocess', 'platform': '', 'backend': 'python', 'version_policy': {'latest': {'num_versions': 1}}, 'max_batch_size': 128, 'input': [{'name': 'POST_INPUT_0', 'data_type': 'TYPE_FP32', 'format': 'FORMAT_NONE', 'dims': [-1, 6625], 'is_shape_tensor': False, 'allow_ragged_batch': False}], 'output': [{'name': 'POST_OUTPUT_0', 'data_type': 'TYPE_STRING', 'dims': [1], 'label_filename': '', 'is_shape_tensor': False}, {'name': 'POST_OUTPUT_1', 'data_type': 'TYPE_FP32', 'dims': [1], 'label_filename': '', 'is_shape_tensor': False}], 'batch_input': [], 'batch_output': [], 'optimization': {'priority': 'PRIORITY_DEFAULT', 'input_pinned_memory': {'enable': True}, 'output_pinned_memory': {'enable': True}, 'gather_kernel_buffer_threshold': 0, 'eager_batching': False}, 'instance_group': [{'name': 'rec_postprocess_0', 'kind': 'KIND_CPU', 'count': 1, 'gpus': [], 'secondary_devices': [], 'profile': [], 'passive': False, 'host_policy': ''}], 'default_model_filename': '', 'cc_model_filenames': {}, 'metric_tags': {}, 'parameters': {}, 'model_warmup': []}
postprocess input names: ['POST_INPUT_0']
postprocess output names: ['POST_OUTPUT_0', 'POST_OUTPUT_1']
I0323 02:13:47.301404 1362 python.cc:1875] TRITONBACKEND_ModelInstanceInitialize: det_postprocess_0 (CPU device 0)
I0323 02:13:47.301628 1362 model_repository_manager.cc:1183] successfully loaded 'rec_postprocess' version 1
/usr/lib/python3/dist-packages/requests/init.py:89: RequestsDependencyWarning: urllib3 (1.26.14) or chardet (3.0.4) doesn't match a supported version!
warnings.warn("urllib3 ({}) or chardet ({}) doesn't match a supported "
model_config: {'name': 'det_postprocess', 'platform': '', 'backend': 'python', 'version_policy': {'latest': {'num_versions': 1}}, 'max_batch_size': 128, 'input': [{'name': 'POST_INPUT_0', 'data_type': 'TYPE_FP32', 'format': 'FORMAT_NONE', 'dims': [1, -1, -1], 'is_shape_tensor': False, 'allow_ragged_batch': False}, {'name': 'POST_INPUT_1', 'data_type': 'TYPE_INT32', 'format': 'FORMAT_NONE', 'dims': [4], 'is_shape_tensor': False, 'allow_ragged_batch': False}, {'name': 'ORI_IMG', 'data_type': 'TYPE_UINT8', 'format': 'FORMAT_NONE', 'dims': [-1, -1, 3], 'is_shape_tensor': False, 'allow_ragged_batch': False}], 'output': [{'name': 'POST_OUTPUT_0', 'data_type': 'TYPE_STRING', 'dims': [-1, 1], 'label_filename': '', 'is_shape_tensor': False}, {'name': 'POST_OUTPUT_1', 'data_type': 'TYPE_FP32', 'dims': [-1, 1], 'label_filename': '', 'is_shape_tensor': False}, {'name': 'POST_OUTPUT_2', 'data_type': 'TYPE_FP32', 'dims': [-1, -1, 1], 'label_filename': '', 'is_shape_tensor': False}], 'batch_input': [], 'batch_output': [], 'optimization': {'priority': 'PRIORITY_DEFAULT', 'input_pinned_memory': {'enable': True}, 'output_pinned_memory': {'enable': True}, 'gather_kernel_buffer_threshold': 0, 'eager_batching': False}, 'instance_group': [{'name': 'det_postprocess_0', 'kind': 'KIND_CPU', 'count': 1, 'gpus': [], 'secondary_devices': [], 'profile': [], 'passive': False, 'host_policy': ''}], 'default_model_filename': '', 'cc_model_filenames': {}, 'metric_tags': {}, 'parameters': {}, 'model_warmup': []}
postprocess input names: ['POST_INPUT_0', 'POST_INPUT_1', 'ORI_IMG']
postprocess output names: ['POST_OUTPUT_0', 'POST_OUTPUT_1', 'POST_OUTPUT_2']
I0323 02:13:47.691956 1362 model_repository_manager.cc:1183] successfully loaded 'det_postprocess' version 1
I0323 02:13:47.692282 1362 fastdeploy_runtime.cc:1255] TRITONBACKEND_ModelInitialize: rec_runtime (version 1)
[WARNING] fastdeploy/runtime/runtime_option.cc(189)::SetPaddleMKLDNN
RuntimeOption::SetPaddleMKLDNNwill be removed in v1.2.0, please modify its member variable directly, e.goption.paddle_infer_option.enable_mkldnn = trueI0323 02:13:47.693223 1362 python.cc:1875] TRITONBACKEND_ModelInstanceInitialize: cls_postprocess_0 (CPU device 0)
/usr/lib/python3/dist-packages/requests/init.py:89: RequestsDependencyWarning: urllib3 (1.26.14) or chardet (3.0.4) doesn't match a supported version!
warnings.warn("urllib3 ({}) or chardet ({}) doesn't match a supported "
model_config: {'name': 'cls_postprocess', 'platform': '', 'backend': 'python', 'version_policy': {'latest': {'num_versions': 1}}, 'max_batch_size': 128, 'input': [{'name': 'POST_INPUT_0', 'data_type': 'TYPE_FP32', 'format': 'FORMAT_NONE', 'dims': [2], 'is_shape_tensor': False, 'allow_ragged_batch': False}], 'output': [{'name': 'POST_OUTPUT_0', 'data_type': 'TYPE_INT32', 'dims': [1], 'label_filename': '', 'is_shape_tensor': False}, {'name': 'POST_OUTPUT_1', 'data_type': 'TYPE_FP32', 'dims': [1], 'label_filename': '', 'is_shape_tensor': False}], 'batch_input': [], 'batch_output': [], 'optimization': {'priority': 'PRIORITY_DEFAULT', 'input_pinned_memory': {'enable': True}, 'output_pinned_memory': {'enable': True}, 'gather_kernel_buffer_threshold': 0, 'eager_batching': False}, 'instance_group': [{'name': 'cls_postprocess_0', 'kind': 'KIND_CPU', 'count': 1, 'gpus': [], 'secondary_devices': [], 'profile': [], 'passive': False, 'host_policy': ''}], 'default_model_filename': '', 'cc_model_filenames': {}, 'metric_tags': {}, 'parameters': {}, 'model_warmup': []}
postprocess input names: ['POST_INPUT_0']
postprocess output names: ['POST_OUTPUT_0', 'POST_OUTPUT_1']
I0323 02:13:48.052532 1362 fastdeploy_runtime.cc:1294] TRITONBACKEND_ModelInstanceInitialize: rec_runtime_0 (CPU device 0)
I0323 02:13:48.052826 1362 model_repository_manager.cc:1183] successfully loaded 'cls_postprocess' version 1
[INFO] fastdeploy/runtime/runtime.cc(266)::CreatePaddleBackend Runtime initialized with Backend::PDINFER in Device::CPU.
I0323 02:13:48.440503 1362 model_repository_manager.cc:1183] successfully loaded 'rec_runtime' version 1
I0323 02:13:48.440929 1362 model_repository_manager.cc:1022] loading: cls_pp:1
I0323 02:13:48.541282 1362 model_repository_manager.cc:1022] loading: pp_ocr:1
I0323 02:13:48.641614 1362 model_repository_manager.cc:1022] loading: rec_pp:1
I0323 02:13:48.741941 1362 model_repository_manager.cc:1183] successfully loaded 'cls_pp' version 1
I0323 02:13:48.741959 1362 model_repository_manager.cc:1183] successfully loaded 'pp_ocr' version 1
I0323 02:13:48.742065 1362 model_repository_manager.cc:1183] successfully loaded 'rec_pp' version 1
I0323 02:13:48.742231 1362 server.cc:522]
+------------------+------+
| Repository Agent | Path |
+------------------+------+
+------------------+------+
I0323 02:13:48.742308 1362 server.cc:549]
+------------+---------------------------------------------------------------+--------+
| Backend | Path | Config |
+------------+---------------------------------------------------------------+--------+
| fastdeploy | /opt/tritonserver/backends/fastdeploy/libtriton_fastdeploy.so | {} |
| python | /opt/tritonserver/backends/python/libtriton_python.so | {} |
+------------+---------------------------------------------------------------+--------+
I0323 02:13:48.742378 1362 server.cc:592]
+-----------------+---------+--------+
| Model | Version | Status |
+-----------------+---------+--------+
| cls_postprocess | 1 | READY |
| cls_pp | 1 | READY |
| cls_runtime | 1 | READY |
| det_postprocess | 1 | READY |
| det_preprocess | 1 | READY |
| det_runtime | 1 | READY |
| pp_ocr | 1 | READY |
| rec_postprocess | 1 | READY |
| rec_pp | 1 | READY |
| rec_runtime | 1 | READY |
+-----------------+---------+--------+
I0323 02:13:48.742484 1362 tritonserver.cc:1920]
+----------------------------------+------------------------------------------------------------------------------------------+
| Option | Value |
+----------------------------------+------------------------------------------------------------------------------------------+
| server_id | triton |
| server_version | 2.15.0 |
| server_extensions | classification sequence model_repository model_repository(unload_dependents) schedule_po |
| | licy model_configuration system_shared_memory cuda_shared_memory binary_tensor_data stat |
| | istics |
| model_repository_path[0] | /ocr_serving/models |
| model_control_mode | MODE_NONE |
| strict_model_config | 1 |
| rate_limit | OFF |
| pinned_memory_pool_byte_size | 268435456 |
| response_cache_byte_size | 0 |
| min_supported_compute_capability | 0.0 |
| strict_readiness | 1 |
| exit_timeout | 30 |
+----------------------------------+------------------------------------------------------------------------------------------+
I0323 02:13:48.743927 1362 grpc_server.cc:4117] Started GRPCInferenceService at 0.0.0.0:8001
I0323 02:13:48.744215 1362 http_server.cc:2815] Started HTTPService at 0.0.0.0:8000
I0323 02:13:48.785501 1362 http_server.cc:167] Started Metrics Service at 0.0.0.0:8002
W0323 02:14:32.827865 1362 pinned_memory_manager.cc:133] failed to allocate pinned system memory: no pinned memory pool, falling back to non-pinned system memory
client端，执行python3 client.py报错：
Traceback (most recent call last):
File "client.py", line 112, in
scores[i_box], ' bbox=', bboxes[i_box])
IndexError: index 0 is out of bounds for axis 0 with size 0
将rec_texts、rec_scores、det_bboxes结果打印都为空
The text was updated successfully, but these errors were encountered: