使用Amazon SageMaker训练汽车型号图像识别的模型

#!/usr/bin/env bash
## The process file for image classification data transform to the recordio format
# current directory contains only one zip file : my_traindataset.zip
#image to record tool
git clone https://github.com/apache/incubator-mxnet.git
source activate amazonei_mxnet_p36
#unzip your own dataset
unzip *.zip
mkdir train
mkdir validation

#need to fill with your own data path
data_path=/home/ec2-user/Sagemaker/yourowndatafile/
echo "data_path: ${data_path}"
train_path=train/
echo "train_path: ${train_path}"
val_path=validation/
echo "val_path: ${val_path}"

python incubator-mxnet/tools/im2rec.py \
  --list \
  --train-ratio 0.8 \
  --recursive \
  $data_path/data $data_path

python incubator-mxnet/tools/im2rec.py \
    --resize 224 \
    --center-crop \
    --num-thread 4 \
$data_path/data $data_path

#move the xxx.rec file to train & test file
mv ${data_path}data_train.rec $train_path
mv ${data_path}data_val.rec $val_path

import os 
import boto3

     
def upload_to_s3(file):
    s3 = boto3.resource('s3')
    data = open(file, "rb")
    key = file
    s3.Bucket(bucket).put_object(Key=key, Body=data)


# caltech-256
s3_train_key = "car_data_sample/train"
s3_validation_key = "car_data_sample/validation"
s3_train = 's3://{}/{}/'.format(bucket, s3_train_key)
s3_validation = 's3://{}/{}/'.format(bucket, s3_validation_key)

upload_to_s3('car_data_sample/train/data_train.rec')

upload_to_s3('car_data_sample/validation/data_val.rec')

# The algorithm supports multiple network depth (number of layers). They are 18, 34, 50, 101, 152 and 200
# For this training, we will use 18 layers
num_layers = 18
# we need to specify the input image shape for the training data
image_shape = "3,224,224"
# we also need to specify the number of training samples in the training set
# for caltech it is 15420
num_training_samples = 96
# specify the number of output classes
num_classes = 3
# batch size for training
mini_batch_size =  30
# number of epochs
epochs = 100
# learning rate
learning_rate = 0.01
top_k=2
# Since we are using transfer learning, we set use_pretrained_model to 1 so that weights can be 
# initialized with pre-trained weights
use_pretrained_model = 1

%%time
import time
import boto3
from time import gmtime, strftime


s3 = boto3.client('s3')
# create unique job name 
job_name_prefix = 'cars-imageclassification'
timestamp = time.strftime('-%Y-%m-%d-%H-%M-%S', time.gmtime())
job_name = job_name_prefix + timestamp
training_params = \
{
    # specify the training docker image
    "AlgorithmSpecification": {
        "TrainingImage": training_image,
        "TrainingInputMode": "File"
    },
    "RoleArn": role,
    "OutputDataConfig": {
        "S3OutputPath": 's3://{}/{}/output'.format(bucket, job_name_prefix)
    },
    "ResourceConfig": {
        "InstanceCount": 1,
        "InstanceType": "ml.p2.xlarge",
        "VolumeSizeInGB": 50
    },
    "TrainingJobName": job_name,
    "HyperParameters": {
        "image_shape": image_shape,
        "num_layers": str(num_layers),
        "num_training_samples": str(num_training_samples),
        "num_classes": str(num_classes),
        "mini_batch_size": str(mini_batch_size),
        "epochs": str(epochs),
        "learning_rate": str(learning_rate),
        "use_pretrained_model": str(use_pretrained_model)
    },
    "StoppingCondition": {
        "MaxRuntimeInSeconds": 360000
    },
#Training data should be inside a subdirectory called "train"
#Validation data should be inside a subdirectory called "validation"
#The algorithm currently only supports fullyreplicated model (where data is copied onto each machine)
    "InputDataConfig": [
        {
            "ChannelName": "train",
            "DataSource": {
                "S3DataSource": {
                    "S3DataType": "S3Prefix",
                    "S3Uri": s3_train,
                    "S3DataDistributionType": "FullyReplicated"
                }
            },
            "ContentType": "application/x-recordio",
            "CompressionType": "None"
        },
        {
            "ChannelName": "validation",
            "DataSource": {
                "S3DataSource": {
                    "S3DataType": "S3Prefix",
                    "S3Uri": s3_validation,
                    "S3DataDistributionType": "FullyReplicated"
                }
            },
            "ContentType": "application/x-recordio",
            "CompressionType": "None"
        }
    ]
}
print('Training job name: {}'.format(job_name))
print('\nInput Data Location: {}'.format(training_params['InputDataConfig'][0]['DataSource']['S3DataSource']))

%%time
import boto3
from time import gmtime, strftime

sage = boto3.Session().client(service_name='sagemaker') 

model_name="cars-imageclassification-" + time.strftime('-%Y-%m-%d-%H-%M-%S', time.gmtime())
print(model_name)
info = sage.describe_training_job(TrainingJobName=job_name)
model_data = info['ModelArtifacts']['S3ModelArtifacts']
print(model_data)

hosting_image = get_image_uri(boto3.Session().region_name, 'image-classification')

primary_container = {
    'Image': hosting_image,
    'ModelDataUrl': model_data,
}

create_model_response = sage.create_model(
    ModelName = model_name,
    ExecutionRoleArn = role,
    PrimaryContainer = primary_container)

print(create_model_response['ModelArn'])

from time import gmtime, strftime

timestamp = time.strftime('-%Y-%m-%d-%H-%M-%S', time.gmtime())
endpoint_config_name = job_name_prefix + '-epc-' + timestamp
endpoint_config_response = sage.create_endpoint_config(
    EndpointConfigName = endpoint_config_name,
    ProductionVariants=[{
        'InstanceType':'ml.m4.xlarge',
        'InitialInstanceCount':1,
        'ModelName':model_name,
        'VariantName':'AllTraffic'}])

print('Endpoint configuration name: {}'.format(endpoint_config_name))
print('Endpoint configuration arn:  {}'.format(endpoint_config_response['EndpointConfigArn']))

%%time
import time

timestamp = time.strftime('-%Y-%m-%d-%H-%M-%S', time.gmtime())
endpoint_name = job_name_prefix + '-ep-' + timestamp
print('Endpoint name: {}'.format(endpoint_name))

endpoint_params = {
    'EndpointName': endpoint_name,
    'EndpointConfigName': endpoint_config_name,
}
endpoint_response = sagemaker.create_endpoint(**endpoint_params)
print('EndpointArn = {}'.format(endpoint_response['EndpointArn']))
# get the status of the endpoint
response = sagemaker.describe_endpoint(EndpointName=endpoint_name)
status = response['EndpointStatus']
print('EndpointStatus = {}'.format(status))
# wait until the status has changed
sagemaker.get_waiter('endpoint_in_service').wait(EndpointName=endpoint_name)
# print the status of the endpoint
endpoint_response = sagemaker.describe_endpoint(EndpointName=endpoint_name)
status = endpoint_response['EndpointStatus']
print('Endpoint creation ended with EndpointStatus = {}'.format(status))