Amazon SageMaker を使用して Word-Pronunciation シーケンスツーシーケンスモデルを作成する

ソース: ACKNOWLEDGEMENT
ターゲット: AE0 K N AA1 L IH0 JH M AH0 N T

Source:['A', 'C', 'K', 'N', 'O', 'W', 'L', 'E', 'D', 'G', 'E', 'M', 'E', 'N', 'T']
Target:['AE0', 'K', 'N', 'AA1', 'L', 'IH0', 'JH', 'M', 'AH0', 'N', 'T']

Source:[14 34 61 64 66 88 62 38 36 49 38 63 38 64 78]
Target:[18 61 64 16 62 53 60 63 21 64 78]

vocab_dict =

	{
 '<pad>': 0,'<unk>': 1,'<s>': 2,'</s>': 3,'0': 4,'1': 5,'2': 6,
 '3': 7,'4': 8,'5': 9,'6': 10,'7': 11,'8': 12,'9': 13,'A': 14,
 'AA0': 15,'AA1': 16,'AA2': 17,'AE0': 18,'AE1': 19,'AE2': 20,
 'AH0': 21,'AH1': 22,'AH2': 23,'AO0': 24,'AO1': 25,'AO2': 26,
 'AW0': 27,'AW1': 28,'AW2': 29,'AY0': 30,'AY1': 31,'AY2': 32,
 'B': 33,'C': 34,'CH': 35,'D': 36,'DH': 37,'E': 38,'EH0': 39,
 'EH1': 40,'EH2': 41,'ER0': 42,'ER1': 43,'ER2': 44,'EY0': 45,
 'EY1': 46,'EY2': 47,'F': 48,'G': 49,'H': 50,'HH': 51,'I': 52,
 'IH0': 53,'IH1': 54,'IH2': 55,'IY0': 56,'IY1': 57,'IY2': 58,
 'J': 59,'JH': 60,'K': 61,'L': 62,'M': 63,'N': 64,'NG': 65,
 'O': 66,'OW0': 67,'OW1': 68,'OW2': 69,'OY0': 70,'OY1': 71,
 'OY2': 72,'P': 73,'Q': 74,'R': 75,'S': 76,'SH': 77,'T': 78,
 'TH': 79,'U': 80,'UH0': 81,'UH1': 82,'UH2': 83,'UW0': 84,
 'UW1': 85,'UW2': 86,'V': 87,'W': 88,'X': 89,'Y': 90,'Z': 91,
 'ZH': 92
	}

PAD_SYMBOL = "<pad>" #0
UNK_SYMBOL = "<unk>" #1
BOS_SYMBOL = "<s>" #2
EOS_SYMBOL = "</s>" #3

VOCAB_SYMBOLS = [PAD_SYMBOL, UNK_SYMBOL, BOS_SYMBOL, EOS_SYMBOL]
vocab_dict[PAD_SYMBOL] = 0
vocab_dict[UNK_SYMBOL] = 1
vocab_dict[BOS_SYMBOL] = 2
vocab_dict[EOS_SYMBOL] = 3

import json
with open('vocab.src.json', 'w') as fp:
    json.dump(vocab_dict, fp, indent=4, ensure_ascii=False)
        
with open('vocab.trg.json', 'w') as fp:
    json.dump(vocab_dict, fp, indent=4, ensure_ascii=False)

file_type = 'train'
output_file = "train.rec"
write_to_file(trainX, trainY, file_type, output_file)

file_type = 'validation'
output_file = "val.rec"
write_to_file(valX, valY, file_type, output_file)

Stack of tokenized source sequence
	[array([36, 80, 36, 14, 75]) array([62, 52, 62, 14])
 	array([88, 38, 52, 64, 49, 14, 75, 78]) array([… …]
	
Stack of tokenized target sequence	
	[array([36, 85, 36, 42]) array([62, 57, 62, 21])
 	array([88, 31, 65, 49, 15, 75, 78]) array([… …]

# S3 bucket and prefix
bucket = '<your_s3_bucket_name_here>'
prefix = 'seq2seq/word-pronunciation'  
# i.e.'<your_s3_bucket>/seq2seq/word-pronunciation'

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

upload_to_s3(bucket, prefix, 'train', 'train.rec') 
#/<your s3 bucket>/seq2seq/word-pronunciation/train/train.rec
upload_to_s3(bucket, prefix, 'validation', 'val.rec') 
#/<your s3 bucket>/seq2seq/word-pronunciation/validation/val.rec 
upload_to_s3(bucket, prefix, 'vocab', 'vocab.src.json') 
#/<your s3 bucket>/seq2seq/word-pronunciation/vocab/vocab.src.json
upload_to_s3(bucket, prefix, 'vocab', 'vocab.trg.json') 
#/<your s3 bucket>/seq2seq/word-pronunciation/vocab/vocab.trg.json

containers = {'us-west-2': '433757028032.dkr.ecr.us-west-2.amazonaws.com/seq2seq:latest',
              'us-east-1': '811284229777.dkr.ecr.us-east-1.amazonaws.com/seq2seq:latest',
              'us-east-2': '825641698319.dkr.ecr.us-east-2.amazonaws.com/seq2seq:latest',
              'eu-west-1': '685385470294.dkr.ecr.eu-west-1.amazonaws.com/seq2seq:latest'}
container = containers[region_name]
print('Using SageMaker Seq2Seq container: {} ({})'.format(container, region_name))

job_name = 'seq2seq-wrd-phn-p2-xlarge-' + strftime("%Y-%m-%d-%H-%M", gmtime())
print("Training job", job_name)

create_training_params = \
{
    "AlgorithmSpecification": {
        "TrainingImage": container,
        "TrainingInputMode": "File"
    },
    "RoleArn": role,
    "OutputDataConfig": {
        "S3OutputPath": "s3://{}/{}/".format(bucket, prefix)
    },
    "ResourceConfig": {
        # Seq2Seq does not support multiple machines. 現在、これは単一マシン、複数の GPU のみをサポートしています
        "InstanceCount": 1,
        "InstanceType": "ml.p2.xlarge", # We suggest one of ["ml.p2.16xlarge", "ml.p2.8xlarge", "ml.p2.xlarge"]
        "VolumeSizeInGB": 50
    },
    "TrainingJobName": job_name,
    "HyperParameters": {
        # Please refer to the documentation for complete list of parameters
        "max_seq_len_source": str(source_sequence_length),
        "max_seq_len_target": str(target_sequence_length),
        "optimized_metric": "bleu", 
        "batch_size": "64", # Please use a larger batch size (256 or 512) if using ml.p2.8xlarge or ml.p2.16xlarge
        "checkpoint_frequency_num_batches": "1000",
        "rnn_num_hidden": "512",
        "num_layers_encoder": "1",
        "num_layers_decoder": "1",
        "num_embed_source": "512",
        "num_embed_target": "512",
        "checkpoint_threshold": "3",
        #"max_num_batches": "2100"
        # Training will stop after 2100 iterations/batches.
        # This is just for demo purposes. より優れたモデルが必要な場合、上記のパラメーターを削除します。
    },
    "StoppingCondition": {
        "MaxRuntimeInSeconds": 48 * 3600
    },
    "InputDataConfig": [
        {
            "ChannelName": "train",
            "DataSource": {
                "S3DataSource": {
                    "S3DataType": "S3Prefix",
                    "S3Uri": "s3://{}/{}/train/".format(bucket, prefix),
                    "S3DataDistributionType": "FullyReplicated"
                }
            },
        },
        {
            "ChannelName": "vocab",
            "DataSource": {
                "S3DataSource": {
                    "S3DataType": "S3Prefix",
                    "S3Uri": "s3://{}/{}/vocab/".format(bucket, prefix),
                    "S3DataDistributionType": "FullyReplicated"
                }
            },
        },
        {
            "ChannelName": "validation",
            "DataSource": {
                "S3DataSource": {
                    "S3DataType": "S3Prefix",
                    "S3Uri": "s3://{}/{}/validation/".format(bucket, prefix),
                    "S3DataDistributionType": "FullyReplicated"
                }
            },
        }
    ]
}

sagemaker_client = boto3.Session().client(service_name='sagemaker')
sagemaker_client.create_training_job(**create_training_params) 

### ステータスのチェックは「Completed (完了)」のメッセージが表示されるまで継続してください。###

status = sagemaker_client.describe_training_job(TrainingJobName=job_name)['TrainingJobStatus']
print(status)
# if the job failed, determine why
if status == 'Failed':
    message = sagemaker_client.describe_training_job(TrainingJobName=job_name)['FailureReason']
    print('Training failed with the following error: {}'.format(message))
    raise Exception('Training job failed') 

%%time

sage = boto3.client('sagemaker')

info = sage.describe_training_job(TrainingJobName=job_name)
model_name=job_name
model_data = info['ModelArtifacts']['S3ModelArtifacts']

print(model_name)
print(model_data)

primary_container = {
    'Image': container,
    '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

endpoint_config_name = 'Seq2SeqEndpointConfig-' + strftime("%Y-%m-%d-%H-%M-%S", gmtime())
print(endpoint_config_name)
create_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 Config Arn: " + create_endpoint_config_response['EndpointConfigArn'])

%%time
import time

endpoint_name = 'Seq2SeqEndpoint-' + strftime("%Y-%m-%d-%H-%M-%S", gmtime())
print(endpoint_name)
create_endpoint_response = sage.create_endpoint(
    EndpointName=endpoint_name,
    EndpointConfigName=endpoint_config_name)
print(create_endpoint_response['EndpointArn'])

resp = sage.describe_endpoint(EndpointName=endpoint_name)
status = resp['EndpointStatus']
print("Status: " + status)

# wait until the status has changed
sage.get_waiter('endpoint_in_service').wait(EndpointName=endpoint_name)

# print the status of the endpoint
endpoint_response = sage.describe_endpoint(EndpointName=endpoint_name)
status = endpoint_response['EndpointStatus']
print('Endpoint creation ended with EndpointStatus = {}'.format(status))

if status != 'InService':
    raise Exception('Endpoint creation failed.')

words_infr = ["car",
        "cat",
        "tapeworm",
        "tapdance",
        "supercalifragilistic",
        "expialidocious"]

payload = {"instances" : []}
for word_infr in words_infr:
    
    payload["instances"].append({"data" : " ".join(list(word_infr.upper()))})

response = runtime.invoke_endpoint(EndpointName=endpoint_name, 
                                   ContentType='application/json', 
                                   Body=json.dumps(payload))

response = response["Body"].read().decode("utf-8")
response = json.loads(response)
print(response)

'car': 'K AA1 R'
'cat': 'K AE1 T'
'tapeworm': 'T EY1 P W ER2 M'
'tapdance': 'T AE1 P D AE2 N S'
'supercalifragilistic': 'S UW2 P ER0 K AE2 L AH0 F R AE1 JH AH0 L IH2 S T IH0 K' 
'expialidocious': 'EH2 K S P IY2 AH0 L AH0 D OW1 SH AH0 S'