Amazon SageMaker + Stable Diffusion 搭建文本生成图像模型

​

​

​

pip install --upgrade -q aiobotocore
 
pip install -q xgboost==1.3.1

import pandas as pd
import boto3
import sagemaker
import json
import joblib
import xgboost as xgb
from sklearn.metrics import roc_auc_score
 
# Set SageMaker and S3 client variables
sess = sagemaker.Session()
 
region = sess.boto_region_name
s3_client = boto3.client("s3", region_name=region)
 
sagemaker_role = sagemaker.get_execution_role()
 
# Set read and write S3 buckets and locations
write_bucket = sess.default_bucket()
write_prefix = "fraud-detect-demo"
 
read_bucket = "sagemaker-sample-files"
read_prefix = "datasets/tabular/synthetic_automobile_claims" 
 
train_data_key = f"{read_prefix}/train.csv"
test_data_key = f"{read_prefix}/test.csv"
model_key = f"{write_prefix}/model"
output_key = f"{write_prefix}/output"
 
train_data_uri = f"s3://{read_bucket}/{train_data_key}"
test_data_uri = f"s3://{read_bucket}/{test_data_key}"
hyperparams = {
                "max_depth": 3,
                "eta": 0.2,
                "objective": "binary:logistic",
                "subsample" : 0.8,
                "colsample_bytree" : 0.8,
                "min_child_weight" : 3
              }
 
num_boost_round = 100
nfold = 3
early_stopping_rounds = 10
 
 
 
# Set up data input
label_col = "fraud"
data = pd.read_csv(train_data_uri)
 
# Read training data and target
train_features = data.drop(label_col, axis=1)
train_label = pd.DataFrame(data[label_col])
dtrain = xgb.DMatrix(train_features, label=train_label)
 
# Cross-validate on training data
cv_results = xgb.cv(
    params=hyperparams,
    dtrain=dtrain,
    num_boost_round=num_boost_round,
    nfold=nfold,
    early_stopping_rounds=early_stopping_rounds,
    metrics=["auc"],
    seed=10,
)
 
 
metrics_data = {
    "binary_classification_metrics": {
        "validation:auc": {
            "value": cv_results.iloc[-1]["test-auc-mean"],
            "standard_deviation": cv_results.iloc[-1]["test-auc-std"]
        },
        "train:auc": {
            "value": cv_results.iloc[-1]["train-auc-mean"],
            "standard_deviation": cv_results.iloc[-1]["train-auc-std"]
        },
    }
}
 
 
print(f"Cross-validated train-auc:{cv_results.iloc[-1]['train-auc-mean']:.2f}")
print(f"Cross-validated validation-auc:{cv_results.iloc[-1]['test-auc-mean']:.2f}")

​

​

from PIL import Image
from io import BytesIO
import base64
 
# helper decoderdef decode_base64_image(image_string):
    base64_image = base64.b64decode(image_string)
    buffer = BytesIO(base64_image)
    return Image.open(buffer)
 
#run prediction
response = predictor[SD_MODEL].predict(data={
    "prompt": [
        "A cute panda is sitting on the sofa",
        "a siamese cat wearing glasses,  working hard at the computer",
    ],
    "height" : 512,
    "width" : 512,
    "num_images_per_prompt":1
  }
)
 
#decode images
decoded_images = [decode_base64_image(image) for image in response["generated_images"]]
 
#visualize generationfor image in decoded_images:
    display(image)

​

​

​

​