I am trying to build and deploy a simple neural network in MXNet and deploy it on a server using mxnet-model-server.
The biggest issue is to deploy the model - model server crashes after uploading the .mar file but I have no idea what the problem could be.
I used the following code to create a custom (but very simple) neural network for testing:
from __future__ import print_function
import numpy as np
import mxnet as mx
from mxnet import nd, autograd, gluon
data_ctx = mx.cpu()
model_ctx = mx.cpu()
# fix the seed
np.random.seed(42)
mx.random.seed(42)
num_examples = 1000
X = mx.random.uniform(shape=(num_examples, 49))
y = mx.random.uniform(shape=(num_examples, 1))
dataset_train = mx.gluon.data.dataset.ArrayDataset(X, y)
dataset_test = dataset_train
data_loader_train = mx.gluon.data.DataLoader(dataset_train, batch_size=25)
data_loader_test = mx.gluon.data.DataLoader(dataset_test, batch_size=25)
num_outputs = 2
net = gluon.nn.HybridSequential()
net.hybridize()
with net.name_scope():
net.add(gluon.nn.Dense(49, activation="relu"))
net.add(gluon.nn.Dense(64, activation="relu"))
net.add(gluon.nn.Dense(num_outputs))
net.collect_params().initialize(mx.init.Normal(sigma=.1), ctx=model_ctx)
softmax_cross_entropy = gluon.loss.SoftmaxCrossEntropyLoss()
trainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': .01})
epochs = 1
smoothing_constant = .01
for e in range(epochs):
cumulative_loss = 0
for i, (data, label) in enumerate(data_loader_train):
data = data.as_in_context(model_ctx).reshape((-1, 49))
label = label.as_in_context(model_ctx)
with autograd.record():
output = net(data)
loss = softmax_cross_entropy(output, label)
loss.backward()
trainer.step(data.shape[0])
cumulative_loss += nd.sum(loss).asscalar()
Following, exported the model using:
net.export("model_files/my_project")
The result are a .json and .params file.
I created a signature.json
{
"inputs": [
{
"data_name": "data",
"data_shape": [
1,
49
]
}
]
}
The model handler is the same from the mxnet tutorial:
# Copyright 2018 Amazon.com, Inc. or its affiliates. All Rights Reserved.
# Licensed under the Apache License, Version 2.0 (the "License").
# You may not use this file except in compliance with the License.
# A copy of the License is located at
# http://www.apache.org/licenses/LICENSE-2.0
# or in the "license" file accompanying this file. This file is distributed
# on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either
# express or implied. See the License for the specific language governing
# permissions and limitations under the License.
"""
ModelHandler defines a base model handler.
"""
import logging
import time
class ModelHandler(object):
"""
A base Model handler implementation.
"""
def __init__(self):
self.error = None
self._context = None
self._batch_size = 0
self.initialized = False
def initialize(self, context):
"""
Initialize model. This will be called during model loading time
:param context: Initial context contains model server system properties.
:return:
"""
self._context = context
self._batch_size = context.system_properties["batch_size"]
self.initialized = True
def preprocess(self, batch):
"""
Transform raw input into model input data.
:param batch: list of raw requests, should match batch size
:return: list of preprocessed model input data
"""
assert self._batch_size == len(batch), "Invalid input batch size: {}".format(len(batch))
return None
def inference(self, model_input):
"""
Internal inference methods
:param model_input: transformed model input data
:return: list of inference output in NDArray
"""
return None
def postprocess(self, inference_output):
"""
Return predict result in batch.
:param inference_output: list of inference output
:return: list of predict results
"""
return ["OK"] * self._batch_size
def handle(self, data, context):
"""
Custom service entry point function.
:param data: list of objects, raw input from request
:param context: model server context
:return: list of outputs to be send back to client
"""
self.error = None # reset earlier errors
try:
preprocess_start = time.time()
data = self.preprocess(data)
inference_start = time.time()
data = self.inference(data)
postprocess_start = time.time()
data = self.postprocess(data)
end_time = time.time()
metrics = context.metrics
metrics.add_time("PreprocessTime", round((inference_start - preprocess_start) * 1000, 2))
metrics.add_time("InferenceTime", round((postprocess_start - inference_start) * 1000, 2))
metrics.add_time("PostprocessTime", round((end_time - postprocess_start) * 1000, 2))
return data
except Exception as e:
logging.error(e, exc_info=True)
request_processor = context.request_processor
request_processor.report_status(500, "Unknown inference error")
return [str(e)] * self._batch_size
Following, I created the .mar file using:
model-archiver --model-name my_project --model-path my_project --handler ssd_service:handle
Starting the model on the server:
mxnet-model-server --start --model_store my_project --models ssd=my_project.mar
I literally followed every tutorial on: https://github.com/awslabs/mxnet-model-server
However, the server is crashing. The worker die, backend worker die, workers are disconnected, Load model failed: ssd, error: worker died
I have absolutely no clue what to do so I would be very glad if you helped me out!
Best
