I had two 2 docker container in the server. One is Triton Client Server whose GRPC port I set is 1747. Triton Client Server port had a TorchScript model running on it. The other container is where I want to call grpcclient.InferenceServerClient to the Triton container but I got the error:
Traceback (most recent call last):
File "/home/user/miniconda/bin/uvicorn", line 8, in <module>
sys.exit(main())
File "/home/user/miniconda/lib/python3.8/site-packages/click/core.py", line 1130, in __call__
return self.main(*args, **kwargs)
File "/home/user/miniconda/lib/python3.8/site-packages/click/core.py", line 1055, in main
rv = self.invoke(ctx)
File "/home/user/miniconda/lib/python3.8/site-packages/click/core.py", line 1404, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "/home/user/miniconda/lib/python3.8/site-packages/click/core.py", line 760, in invoke
return __callback(*args, **kwargs)
File "/home/user/miniconda/lib/python3.8/site-packages/uvicorn/main.py", line 404, in main
run(
File "/home/user/miniconda/lib/python3.8/site-packages/uvicorn/main.py", line 569, in run
server.run()
File "/home/user/miniconda/lib/python3.8/site-packages/uvicorn/server.py", line 60, in run
return asyncio.run(self.serve(sockets=sockets))
File "/home/user/miniconda/lib/python3.8/asyncio/runners.py", line 43, in run
return loop.run_until_complete(main)
File "/home/user/miniconda/lib/python3.8/asyncio/base_events.py", line 616, in run_until_complete
return future.result()
File "/home/user/miniconda/lib/python3.8/site-packages/uvicorn/server.py", line 67, in serve
config.load()
File "/home/user/miniconda/lib/python3.8/site-packages/uvicorn/config.py", line 477, in load
self.loaded_app = import_from_string(self.app)
File "/home/user/miniconda/lib/python3.8/site-packages/uvicorn/importer.py", line 21, in import_from_string
module = importlib.import_module(module_str)
File "/home/user/miniconda/lib/python3.8/importlib/__init__.py", line 127, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "<frozen importlib._bootstrap>", line 1014, in _gcd_import
File "<frozen importlib._bootstrap>", line 991, in _find_and_load
File "<frozen importlib._bootstrap>", line 975, in _find_and_load_unlocked
File "<frozen importlib._bootstrap>", line 671, in _load_unlocked
File "<frozen importlib._bootstrap_external>", line 783, in exec_module
File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed
File "./api_control.py", line 5, in <module>
import helpers
File "./helpers.py", line 79, in <module>
timi_triton = TritonInferTTS(url=TRITON_URL,model_name=TIMI_MODEL_NAME,model_version=TIMI_MODEL_VERSION)
File "./triton_client.py", line 22, in __init__
self.triton_client = grpcclient.InferenceServerClient(url=self.url, verbose=VERBOSE)
File "/home/user/miniconda/lib/python3.8/site-packages/tritonclient/grpc/__init__.py", line 273, in __init__
self._channel = grpc.insecure_channel(url, options=channel_opt)
File "/home/user/miniconda/lib/python3.8/site-packages/grpc/__init__.py", line 1977, in insecure_channel
return _channel.Channel(target, () if options is None else options, None,
File "/home/user/miniconda/lib/python3.8/site-packages/grpc/_channel.py", line 1479, in __init__
_common.encode(target), _augment_options(core_options, compression),
File "/home/user/miniconda/lib/python3.8/site-packages/grpc/_common.py", line 74, in encode
return s.encode('utf8')
AttributeError: 'NoneType' object has no attribute 'encode'
Exception ignored in: <function InferenceServerClient.__del__ at 0x7f41eb398550>
Traceback (most recent call last):
File "/home/user/miniconda/lib/python3.8/site-packages/tritonclient/grpc/__init__.py", line 286, in __del__
File "/home/user/miniconda/lib/python3.8/site-packages/tritonclient/grpc/__init__.py", line 293, in close
File "/home/user/miniconda/lib/python3.8/site-packages/tritonclient/grpc/__init__.py", line 1649, in stop_stream
AttributeError: 'InferenceServerClient' object has no attribute '_stream'
Here is the code:
import os
import numpy as np
import sys
from functools import partial
import tritonclient.grpc as grpcclient
from tritonclient.utils import *
VERBOSE = False
TRITON_URL = 'localhost:1747'
TIMI_MODEL_NAME = os.getenv("TIMI_MODEL_NAME")
TIMI_MODEL_VERSION = os.getenv('TIMI_MODEL_VERSION')
class TritonInferTTS():
def __init__(self, url, model_name, model_version):
self.url = url
self.model_name = model_name
self.model_version = model_version
self.input_name = ['INPUT__0', 'INPUT__1','INPUT__2','INPUT__3','INPUT__4']
self.output_name = ['OUTPUT__0']
self.triton_client = grpcclient.InferenceServerClient(url=self.url, verbose=VERBOSE)
model_metadata = self.triton_client.get_model_metadata(model_name=self.model_name, model_version=self.model_version)
model_config = self.triton_client.get_model_config(model_name=self.model_name, model_version=self.model_version)
def triton_infer_grpc(self, x, x_length,noise_scale,length_scale,noise_scale_w):
# x = np.array([x])
# alpha = np.array([alpha], dtype=np.float32)
input0 = InferInput(self.input_name[0], x.shape, 'INT64')
input0 = x
input1 = InferInput(self.input_name[1], x_length.shape, 'INT64')
input1 = x_length
input2 = InferInput(self.input_name[2], noise_scale.shape, 'FP32')
input2 = noise_scale
input3 = InferInput(self.input_name[3], length_scale.shape, 'FP32')
input3 = length_scale
input4 = InferInput(self.input_name[4], noise_scale_w.shape, 'FP32')
input4 = noise_scale_w
output0 = grpcclient.ssInferRequestedOutput(self.output_name[0])
# output1 = InferRequestedOutput(self.output_name[1])
response = self.triton_client.infer(self.model_name, model_version=self.model_version, inputs=[input0, input1,input2,input3,input4], outputs=[output0])
audio = response[0]
return audio
Please help me. I'm so desperate
I changed the Triton Url to 'host.docker.internal:1747' and '<my_public_ip>:1747' but i got the same error
