pp-shituv2 使用paddleserving部署后启动服务运行python3.7 pipeline_http_client.py报/home/aistudio/PaddleClas/deploy/paddleserving/recognition {'err_no': 8, 'err_msg': "(data_id=0 log_id=0) [det|0] Failed to postprocess: 'scale_factor.lod'", 'key': [], 'value': [], 'tensors': []}

[sloyqi]

paddleServing部署时，启动http客户端，报错

/home/aistudio/PaddleClas/deploy/paddleserving/recognition {'err_no': 8, 'err_msg': "(data_id=0 log_id=0) [det|0] Failed to postprocess: 'scale_factor.lod'", 'key': [], 'value': [], 'tensors': []}

识别推理模型serving_server_conf.prototxt文件是：
feed_var {
name: "x"
alias_name: "x"
is_lod_tensor: false
feed_type: 1
shape: 3
shape: 224
shape: 224
}
fetch_var {
name: "scale_factor"
alias_name: "features"
is_lod_tensor: false
fetch_type: 1
shape: 512
}

通用检测模型.prototxt文件是：
feed_var {
name: "im_shape"
alias_name: "im_shape"
is_lod_tensor: false
feed_type: 1
shape: 2
}
feed_var {
name: "image"
alias_name: "image"
is_lod_tensor: false
feed_type: 1
shape: 3
shape: 416
shape: 416
}
feed_var {
name: "scale_factor"
alias_name: "scale_factor"
is_lod_tensor: false
feed_type: 1
shape: 2
}
fetch_var {
name: "save_infer_model/scale_0.tmp_1"
alias_name: "save_infer_model/scale_0.tmp_1"
is_lod_tensor: true
fetch_type: 1
shape: -1
}
fetch_var {
name: "save_infer_model/scale_1.tmp_1"
alias_name: "save_infer_model/scale_1.tmp_1"
is_lod_tensor: false
fetch_type: 2
}

config.yml
#worker_num, 最大并发数。当build_dag_each_worker=True时, 框架会创建worker_num个进程，每个进程内构建grpcSever和DAG
##当build_dag_each_worker=False时，框架会设置主线程grpc线程池的max_workers=worker_num
worker_num: 1

#http端口, rpc_port和http_port不允许同时为空。当rpc_port可用且http_port为空时，不自动生成http_port
http_port: 18080
rpc_port: 9993

dag:
#op资源类型, True, 为线程模型；False，为进程模型
is_thread_op: False
op:
imagenet:
#并发数，is_thread_op=True时，为线程并发；否则为进程并发
concurrency: 1

#当op配置没有server_endpoints时，从local_service_conf读取本地服务配置
local_service_conf:

    #uci模型路径
    model_config: ResNet50_vd_serving

    #计算硬件类型: 空缺时由devices决定(CPU/GPU)，0=cpu, 1=gpu, 2=tensorRT, 3=arm cpu, 4=kunlun xpu
    device_type: 1

    #计算硬件ID，当devices为""或不写时为CPU预测；当devices为"0", "0,1,2"时为GPU预测，表示使用的GPU卡
    devices: "0" # "0,1"

    #client类型，包括brpc, grpc和local_predictor.local_predictor不启动Serving服务，进程内预测
    client_type: local_predictor

    #Fetch结果列表，以client_config中fetch_var的alias_name为准
    fetch_list: ["prediction"]

pipeline.log中报错显示
Traceback (most recent call last):
File "/home/aistudio/.data/webide/pip/lib/python3.7/site-packages/paddle_serving_server/pipeline/operator.py", line 1105, in _run_postprocess
logid_dict.get(data_id))
File "recognition_web_service.py", line 94, in postprocess
boxes = self.img_postprocess(fetch_dict, visualize=False)
File "/home/aistudio/.data/webide/pip/lib/python3.7/site-packages/paddle_serving_app/reader/image_reader.py", line 427, in call
self.clsid2catid)
File "/home/aistudio/.data/webide/pip/lib/python3.7/site-packages/paddle_serving_app/reader/image_reader.py", line 344, in _get_bbox_result
lod = [fetch_map[fetch_name + '.lod']]
KeyError: 'scale_factor.lod'
ERROR 2024-03-18 19:23:33,028 [dag.py:410] (data_id=0 log_id=0) Failed to predict: (data_id=0 log_id=0) [det|0] Failed to postprocess: 'scale_factor.lod'

[cuicheng01]

您好，PP-ShiTuV2的离线部署可以走通吗？

[sloyqi]

没有，我是通过百度ai studio 云端跑的项目，我用ppshutuv2跑不通，但是我又训练了一个ppshituv1却可以跑的通，我查看了一下v2的输出名称好像不对，但是我不知道怎么查看输出模型名称

…

---原始邮件--- 发件人: ***@***.***> 发送时间: 2024年5月13日(周一) 下午2:38 收件人: ***@***.***>; 抄送: ***@***.******@***.***>; 主题: Re: [PaddlePaddle/PaddleClas] pp-shituv2 使用paddleserving部署后启动服务运行python3.7 pipeline_http_client.py报/home/aistudio/PaddleClas/deploy/paddleserving/recognition {'err_no': 8, 'err_msg': "(data_id=0 log_id=0) [det|0] Failed to postprocess: 'scale_factor.lod'", 'key': [], 'value': [], 'tensors': []} (Issue #3134) 您好，PP-ShiTuV2的离线部署可以走通吗？ — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: ***@***.***>