Basic classification: Classify images of clothing¶
BentoML makes moving trained ML models to production easy:
- Package models trained with any ML framework and reproduce them for model serving in production
- Deploy anywhere for online API serving or offline batch serving
- High-Performance API model server with adaptive micro-batching support
- Central hub for managing models and deployment process via Web UI and APIs
- Modular and flexible design making it adaptable to your infrastrcuture
BentoML is a framework for serving, managing, and deploying machine learning models. It is aiming to bridge the gap between Data Science and DevOps, and enable teams to deliver prediction services in a fast, repeatable, and scalable way.
In [2]:
%reload_ext autoreload
%autoreload 2
%matplotlib inline
In [1]:
!pip install -q bentoml tensorflow matplotlib
In [2]:
from __future__ import absolute_import, division, print_function, unicode_literals
import io
# TensorFlow
import tensorflow as tf
# Helper libraries
import numpy as np
import matplotlib.pyplot as plt
print(tf.__version__)
In [3]:
fashion_mnist = tf.keras.datasets.fashion_mnist
(_train_images, train_labels), (_test_images, test_labels) = fashion_mnist.load_data()
class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',
'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']
train_images = _train_images / 255.0
test_images = _test_images / 255.0
In [4]:
class FashionMnist(tf.keras.Model):
def __init__(self):
super(FashionMnist, self).__init__()
self.cnn = tf.keras.Sequential([
tf.keras.layers.Flatten(input_shape=(28, 28)),
tf.keras.layers.Dense(128, activation='relu'),
tf.keras.layers.Dense(10, activation='softmax')
])
@staticmethod
def image_bytes2tensor(inputs):
with tf.device("cpu:0"): # map_fn has issues on GPU https://github.com/tensorflow/tensorflow/issues/28007
inputs = tf.map_fn(lambda i: tf.io.decode_png(i, channels=1), inputs, dtype=tf.uint8)
inputs = tf.cast(inputs, tf.float32)
inputs = (255.0 - inputs) / 255.0
inputs = tf.reshape(inputs, [-1, 28, 28])
return inputs
@tf.function(input_signature=[tf.TensorSpec(shape=(None,), dtype=tf.string)])
def predict_image(self, inputs):
inputs = self.image_bytes2tensor(inputs)
return self(inputs)
def call(self, inputs):
return self.cnn(inputs)
Build the image preprocessing¶
In [5]:
# pick up a test image
d_test_img = _test_images[0]
print(class_names[test_labels[0]])
plt.imshow(255.0 - d_test_img, cmap='gray')
plt.imsave("test.png", 255.0 - d_test_img, cmap='gray')
# read bytes
with open("test.png", "rb") as f:
img_bytes = f.read()
# verify saved image
assert tf.reduce_mean(FashionMnist.image_bytes2tensor(tf.constant([img_bytes])) - d_test_img) < 0.01
Train the model¶
In [9]:
model = FashionMnist()
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
model.fit(train_images, train_labels, epochs=50)
Out[9]:
Model inference test run¶
In [10]:
predict = model.predict_image(tf.constant([img_bytes]))
klass = tf.argmax(predict, axis=1)
[class_names[c] for c in klass]
Out[10]:
And the model predicts a label as expected.
Create BentoService class¶
In [18]:
%%writefile tensorflow_fashion_mnist.py
import bentoml
import tensorflow as tf
from bentoml.artifact import TensorflowSavedModelArtifact
from bentoml.adapters import TfTensorInput
FASHION_MNIST_CLASSES = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',
'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']
@bentoml.env(pip_dependencies=['tensorflow', 'numpy', 'pillow'])
@bentoml.artifacts([TensorflowSavedModelArtifact('model')])
class FashionMnistTensorflow(bentoml.BentoService):
@bentoml.api(input=TfTensorInput(), batch=True)
def predict(self, inputs):
outputs = self.artifacts.model.predict_image(inputs)
output_classes = tf.math.argmax(outputs, axis=1)
return [FASHION_MNIST_CLASSES[c] for c in output_classes]
In [19]:
from tensorflow_fashion_mnist import FashionMnistTensorflow
bento_svc = FashionMnistTensorflow()
bento_svc.pack("model", model)
saved_path = bento_svc.save()
Use BentoService with BentoML CLI¶
bentoml get <BentoService Name> list all of BentoService's versions
In [ ]:
!bentoml get FashionMnistTensorflow
bentoml get <BentoService name>:<bentoService version> display detailed information of the specific BentoService version
In [7]:
!bentoml get FashionMnistTensorflow:latest
Serve bentoml REST server locally
In [2]:
!bentoml serve FashionMnistTensorflow:latest
Query REST API with python¶
In [8]:
import base64
import json
import requests
with open("test.png", "rb") as f:
img_bytes = f.read()
img_b64 = base64.b64encode(img_bytes).decode()
headers = {"content-type": "application/json"}
data = json.dumps(
{"instances": [{"b64": img_b64}]}
)
print('Data: {} ... {}'.format(data[:50], data[len(data)-52:]))
json_response = requests.post(f'http://localhost:5000/predict', data=data, headers=headers)
print(json_response)
print(json_response.text)
Use BentoService as PyPI package¶
pip install $SAVED_PATH also installs a CLI tool for accessing the BentoML service
In [10]:
!pip install -q {saved_path}
In [11]:
!FashionMnistTensorflow --help
Run 'predict' api with json data:¶
In [13]:
!echo '{\"instances\":[{\"b64\":\"'$(base64 test.png)'\"}]}' > test.json
!cat test.json | xargs -I {} FashionMnistTensorflow run predict --input {}
Build realtime prediction service in docker with BentoService¶
In [14]:
!docker build --quiet -t tensorflow2-fashion-mnist {saved_path}
In [15]:
!docker run -p 5000:5000 tensorflow2-fashion-mnist --workers 1 --enable-microbatch
Deploy BentoService as REST API server to the cloud¶
BentoML support deployment to multiply cloud provider services, such as AWS Lambda, AWS Sagemaker, Google Cloudrun and etc. You can find the full list and guide on the documentation site at https://docs.bentoml.org/en/latest/deployment/index.html
For this demo, we are going to deploy to AWS Sagemaker
In [ ]:
bento_service_tag = f'{bento_svc.name}:{bento_svc.version}'
print(bento_service_tag)
In [ ]:
!bentoml sagemaker deploy first-tf-fashion -b {bento_service_tag} --api-name predict --verbose
In [ ]:
!bentoml sagemaker get first-tf-fashion
In [ ]:
!aws sagemaker-runtime invoke-endpoint --endpoint-name dev-first-tf-fashion --content-type 'application/json' \
--body "{\"instances\":[{\"b64\":\"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\"}]}" \
output.json && cat output.json
In [ ]:
!bentoml sagemaker delete first-tf-fashion --force
In [ ]: