Serving
Serving copied to clipboard
PaddlePaddle
0.7.0版本client端：No module named 'paddle_serving_client.serving_client'
win10客户端使用test_client 报 F:\ruanjian\anaconda3\envs\paddle\lib\site-packages\paddle_serving_client\client.py:149: in init from .serving_client import PredictorRes E ModuleNotFoundError: No module named 'paddle_serving_client.serving_client' 求解，版本是0.7.0 client端的采用pip安装的paddle_serving_client
我是已经这样装了的
https://github.com/PaddlePaddle/Serving/blob/v0.7.0/doc/Install_EN.md
我在windows上只是client调用，我的服务是启在ubuntu的，我目前只是想在windows上使用client端 但是不知道为什么一直给我报标题中所述的错误
https://github.com/PaddlePaddle/Serving/blob/v0.7.0/doc/Install_EN.md
我就是按照这里的文档装的client端，但是ModuleNotFoundError: No module named 'paddle_serving_client.serving_client'这个错误一直存在 而且在这行代码中也定位不到PredictorRes File "F:\ruanjian\anaconda3\envs\paddle\lib\site-packages\paddle_serving_client\client.py", line 149, in init from .serving_client import PredictorRes
https://github.com/PaddlePaddle/Serving/blob/v0.7.0/doc/Install_EN.md
还是说win10环境 的python 端（pycharm跑的）无法执行Client，client端也必须依靠docker才能够执行？
您的情况，建议您先使用curl的方式，试试能不能通。 https://github.com/PaddlePaddle/Serving/blob/v0.7.0/doc/Quick_Start_CN.md#http%E6%9C%8D%E5%8A%A1
也可以使用不带C++的版本试试。 https://github.com/PaddlePaddle/Serving/blob/v0.7.0/examples/C%2B%2B/fit_a_line/test_httpclient.py
还是说win10环境 的python 端（pycharm跑的）无法执行Client，client端也必须依靠docker才能够执行？
是的，windows上必须要用docker
还是说win10环境 的python 端（pycharm跑的）无法执行Client，client端也必须依靠docker才能够执行？
是的，windows上必须要用docker
感谢大佬 我在ubuntu上起client调用出现这个维度问题 ，预测的图片也是我训练的图片其中之一 以下是服务端报的错误 ：terminate called after throwing an instance of 'paddle::platform::EnforceNotMet' what():
Compile Traceback (most recent call last):
File "tools/export_model.py", line 115, in
File "/home/ubuntu01/anaconda3/envs/paddle/lib/python3.8/site-packages/paddle/fluid/wrapped_decorator.py", line 25, in __impl__
return wrapped_func(*args, **kwargs)
File "/home/ubuntu01/anaconda3/envs/paddle/lib/python3.8/site-packages/paddle/fluid/dygraph/base.py", line 40, in __impl__
return func(*args, **kwargs)
File "/home/ubuntu01/anaconda3/envs/paddle/lib/python3.8/site-packages/paddle/fluid/dygraph/dygraph_to_static/program_translator.py", line 652, in from_func_spec
outputs = static_func(*inputs)
File "/tmp/tmph1_a7fhe.py", line 38, in forward
out = paddle.jit.dy2static.convert_ifelse(self.training, true_fn_2,
File "/home/ubuntu01/anaconda3/envs/paddle/lib/python3.8/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 "/home/ubuntu01/anaconda3/envs/paddle/lib/python3.8/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 "/home/code/paddle/PaddleDetection-release-2.3/ppdet/modeling/architectures/meta_arch.py", line 56, in forward
out = self.get_pred()
File "/home/code/paddle/PaddleDetection-release-2.3/ppdet/modeling/architectures/yolo.py", line 124, in get_pred
return self._forward()
File "/tmp/tmp2mzjjyyx.py", line 94, in _forward
__return_value_0 = paddle.jit.dy2static.convert_ifelse(self.training,
File "/home/ubuntu01/anaconda3/envs/paddle/lib/python3.8/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 "/home/ubuntu01/anaconda3/envs/paddle/lib/python3.8/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 "/home/code/paddle/PaddleDetection-release-2.3/ppdet/modeling/architectures/yolo.py", line 96, in _forward
yolo_head_outs = self.yolo_head(neck_feats)
File "/home/ubuntu01/anaconda3/envs/paddle/lib/python3.8/site-packages/paddle/fluid/dygraph/layers.py", line 898, in __call__
outputs = self.forward(*inputs, **kwargs)
File "/tmp/tmp73h2ebgz.py", line 115, in forward
__return_value_2, i, yolo_outputs = paddle.jit.dy2static.convert_ifelse(
File "/home/ubuntu01/anaconda3/envs/paddle/lib/python3.8/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 "/home/ubuntu01/anaconda3/envs/paddle/lib/python3.8/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/tmp73h2ebgz.py", line 110, in false_fn_26
__return_value_2, i, yolo_outputs = (paddle.jit.dy2static.
File "/home/ubuntu01/anaconda3/envs/paddle/lib/python3.8/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 "/home/ubuntu01/anaconda3/envs/paddle/lib/python3.8/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/tmp73h2ebgz.py", line 97, in true_fn_25
] = paddle.jit.dy2static.convert_while_loop(
File "/home/ubuntu01/anaconda3/envs/paddle/lib/python3.8/site-packages/paddle/fluid/dygraph/dygraph_to_static/convert_operators.py", line 44, in convert_while_loop
loop_vars = _run_py_while(cond, body, loop_vars)
File "/home/ubuntu01/anaconda3/envs/paddle/lib/python3.8/site-packages/paddle/fluid/dygraph/dygraph_to_static/convert_operators.py", line 58, in _run_py_while
loop_vars = body(*loop_vars)
File "/home/code/paddle/PaddleDetection-release-2.3/ppdet/modeling/heads/yolo_head.py", line 105, in forward
x = x.reshape((b, na, no, h * w))
File "/home/ubuntu01/anaconda3/envs/paddle/lib/python3.8/site-packages/paddle/tensor/manipulation.py", line 1570, in reshape
return paddle.fluid.layers.reshape(x=x, shape=shape, name=name)
File "/home/ubuntu01/anaconda3/envs/paddle/lib/python3.8/site-packages/paddle/fluid/layers/nn.py", line 6202, in reshape
helper.append_op(
File "/home/ubuntu01/anaconda3/envs/paddle/lib/python3.8/site-packages/paddle/fluid/layer_helper.py", line 43, in append_op
return self.main_program.current_block().append_op(*args, **kwargs)
File "/home/ubuntu01/anaconda3/envs/paddle/lib/python3.8/site-packages/paddle/fluid/framework.py", line 3226, in append_op
op = Operator(
File "/home/ubuntu01/anaconda3/envs/paddle/lib/python3.8/site-packages/paddle/fluid/framework.py", line 2312, in __init__
for frame in traceback.extract_stack():
C++ Traceback (most recent call last):
Error Message Summary:
InvalidArgumentError: The 'shape' attribute in ReshapeOp is invalid. The input tensor X'size must be divisible by known capacity of 'shape'. But received X's shape = [1, 33, 19, 19], X's size = 11913, 'shape' is [-1, 3, 11, 400], known capacity of 'shape' is -13200. [Hint: Expected output_shape[unk_dim_idx] * capacity == -in_size, but received output_shape[unk_dim_idx] * capacity:0 != -in_size:-11913.] (at /paddle/paddle/fluid/operators/reshape_op.cc:210) [operator < reshape2 > error] Aborted (core dumped)
Serving部署的模型是yolov3_darknet53_270e_coco, paddle_serving_client和paddle_serving_app版本为0.9.0 在windows下使用http方式获取服务，参考resnet50_http_client.py和test_client.py 转化方法比较暴力，但可用
import sys
import numpy as np
from paddle_serving_client import HttpClient
from paddle_serving_app.reader import *
import cv2
def main(argv):
preprocess = Sequential([
File2Image(), BGR2RGB(), Resize(
(608, 608), interpolation=cv2.INTER_LINEAR), Div(255.0), Transpose(
(2, 0, 1))
])
postprocess = RCNNPostprocess(argv[1], "output", [608, 608])
client = HttpClient()
# prototxt文件需要修改成自己的路径
client.load_client_config("yolov3_darknet53_270e_coco/serving_client/serving_client_conf.prototxt")
client.connect(['127.0.0.1:9393'])
im = preprocess(argv[2])
fetch_map = client.predict(
feed={
"image": im,
"im_shape": np.array(list(im.shape[1:])).reshape(-1),
"scale_factor": np.array([1.0, 1.0]).reshape(-1),
},
fetch=["multiclass_nms3_0.tmp_0"],
batch=False)
# print(fetch_map)
# 处理
result = fetch_map.outputs[0].tensor[0] # 要处理的数据都在里面了，只需要进行写转化就行了
value_shape = result.shape
value = np.array(list(result.float_data), dtype="float32").reshape(value_shape) # 转成ndarray，并进行reshape
fetch_map_dict = {}
fetch_map_dict[result.name] = value
fetch_map_dict[result.name+'.lod'] = result.lod
print(fetch_map_dict)
fetch_map_dict["image"] = argv[2]
postprocess(fetch_map_dict)
if __name__ == "__main__":
main(sys.argv)
win10客户端使用test_client 报 F:\ruanjian\anaconda3\envs\paddle\lib\site-packages\paddle_serving_client\client.py:149: in init from .serving_client import PredictorRes E ModuleNotFoundError: No module named 'paddle_serving_client.serving_client' 求解，版本是0.7.0 client端的采用pip安装的paddle_serving_client
from paddle_serving_client import HttpClient as Client
