问题
I am following this documentation on custom prediction routines and I am trying to understand how the inputs for custom prediction routine looks like. The code to send the input looks like this:
instances = [
[6.7, 3.1, 4.7, 1.5],
[4.6, 3.1, 1.5, 0.2],
]
service = discovery.build('ml', 'v1')
name = 'projects/{}/models/{}'.format(project, model)
if version is not None:
name += '/versions/{}'.format(version)
response = service.projects().predict(
name=name,
body={'instances': instances}
).execute()
and the Predictor.py
at the moment is very simple. I am just trying to understand how the input looks like...
class Predictor(object):
"""An example Predictor for an AI Platform custom prediction routine."""
def __init__(self, model):
self._model = model
def predict(self, instances, **kwargs):
inputs = np.asarray(instances)
if kwargs.get('max'):
return np.argmax(inputs, axis=1)
return np.sum(inputs)
@classmethod
def from_path(cls, model_dir):
return cls(None)
But when I try to get the response i get the following error:
{
"error": "Prediction failed: unknown error."
}
Furthermore it is extremely difficult to debug the code, because there is no way to step into the code or print logs... I have no idea what's going on... How the input looks like? how should i access them? This is just a simple test, but eventually I want to send images, it will be even more difficult to debug then. How will I receive them? How will I preprocess them in the preprocessor? Let's assume that the proporcessing i have done at training time looks like this
data = cv2.imread(str(img_path))
data = cv2.resize(data, (224, 224))
data = cv2.cvtColor(data, cv2.COLOR_BGR2RGB)
x = data.astype(np.float32) / 255.
return np.expand_dims(x, axis=0)
How the instances
object looks like so i can construct the preprocessor accordingly?
thank you in advance.
回答1:
I'm builiding a new sample for Custom Prediction which may be useful for your to debug: First I write file locally via a Notebook (Colab)
%%writefile model_prediction.py
import numpy as np
import os
import pickle
import pandas as pd
import importlib
class CustomModelPrediction(object):
_UNUSED_COLUMNS = ['fnlwgt', 'education', 'gender']
_CSV_COLUMNS = [
'age', 'workclass', 'fnlwgt', 'education', 'education_num',
'marital_status', 'occupation', 'relationship', 'race', 'gender',
'capital_gain', 'capital_loss', 'hours_per_week', 'native_country',
'income_bracket'
]
_CATEGORICAL_TYPES = {
'workclass': pd.api.types.CategoricalDtype(categories=[
'Federal-gov', 'Local-gov', 'Never-worked', 'Private',
'Self-emp-inc',
'Self-emp-not-inc', 'State-gov', 'Without-pay'
]),
'marital_status': pd.api.types.CategoricalDtype(categories=[
'Divorced', 'Married-AF-spouse', 'Married-civ-spouse',
'Married-spouse-absent', 'Never-married', 'Separated', 'Widowed'
]),
'occupation': pd.api.types.CategoricalDtype([
'Adm-clerical', 'Armed-Forces', 'Craft-repair',
'Exec-managerial',
'Farming-fishing', 'Handlers-cleaners', 'Machine-op-inspct',
'Other-service', 'Priv-house-serv', 'Prof-specialty',
'Protective-serv',
'Sales', 'Tech-support', 'Transport-moving'
]),
'relationship': pd.api.types.CategoricalDtype(categories=[
'Husband', 'Not-in-family', 'Other-relative', 'Own-child',
'Unmarried',
'Wife'
]),
'race': pd.api.types.CategoricalDtype(categories=[
'Amer-Indian-Eskimo', 'Asian-Pac-Islander', 'Black', 'Other',
'White'
]),
'native_country': pd.api.types.CategoricalDtype(categories=[
'Cambodia', 'Canada', 'China', 'Columbia', 'Cuba',
'Dominican-Republic',
'Ecuador', 'El-Salvador', 'England', 'France', 'Germany',
'Greece',
'Guatemala', 'Haiti', 'Holand-Netherlands', 'Honduras', 'Hong',
'Hungary',
'India', 'Iran', 'Ireland', 'Italy', 'Jamaica', 'Japan', 'Laos',
'Mexico',
'Nicaragua', 'Outlying-US(Guam-USVI-etc)', 'Peru',
'Philippines', 'Poland',
'Portugal', 'Puerto-Rico', 'Scotland', 'South', 'Taiwan',
'Thailand',
'Trinadad&Tobago', 'United-States', 'Vietnam', 'Yugoslavia'
])
}
def __init__(self, model, processor):
self._model = model
self._processor = processor
self._class_names = ['<=50K', '>50K']
def _preprocess(self, instances):
"""Dataframe contains both numeric and categorical features, convert
categorical features to numeric.
Args:
dataframe: A `Pandas.Dataframe` to process.
"""
dataframe = pd.DataFrame(data=[instances], columns=self._CSV_COLUMNS[:-1])
dataframe = dataframe.drop(columns=self._UNUSED_COLUMNS)
# Convert integer valued (numeric) columns to floating point
numeric_columns = dataframe.select_dtypes(['int64']).columns
dataframe[numeric_columns] = dataframe[numeric_columns].astype(
'float32')
# Convert categorical columns to numeric
cat_columns = dataframe.select_dtypes(['object']).columns
# Keep categorical columns always using same values based on dict.
dataframe[cat_columns] = dataframe[cat_columns].apply(
lambda x: x.astype(self._CATEGORICAL_TYPES[x.name]))
dataframe[cat_columns] = dataframe[cat_columns].apply(
lambda x: x.cat.codes)
return dataframe
def predict(self, instances, **kwargs):
preprocessed_data = self._preprocess(instances)
preprocessed_inputs = self._processor.preprocess(preprocessed_data)
outputs = self._model.predict_classes(preprocessed_inputs)
if kwargs.get('probabilities'):
return outputs.tolist()
else:
return [self._class_names[index] for index in
np.argmax(outputs, axis=1)]
@classmethod
def from_path(cls, model_dir):
import tensorflow as tf
model_path = os.path.join(model_dir, 'model.h5')
model = tf.keras.models.load_model(model_path)
preprocessor_path = os.path.join(model_dir, 'preprocessor.pkl')
with open(preprocessor_path, 'rb') as f:
preprocessor = pickle.load(f)
return cls(model, preprocessor)
Once file is written I can test it like this locally before deploying the model:
from model_prediction import CustomModelPrediction
model = CustomModelPrediction.from_path('.')
instance = [25, 'Private', 226802, '11th', 7, 'Never-married', 'Machine-op-inspct', 'Own-child', 'Black', 'Male', 0, 0, 40, 'United-States']
model.predict(instance)
Other option is once you build the setup package you can also test installation locally where my_custom_code-0.1.tar.gz
is the file intended to be deployed in AI Platform:
pip install --target=/tmp/custom_lib --no-cache-dir -b /tmp/pip_builds my_custom_code-0.1.tar.gz
Also take a look at this section:
You can use the --enable-console-logging
to get logs exported to your project. You may need to create a new Model.
回答2:
It looks like that using debug code (at the time of this post) without a model do not work. I used the following code to have everything worked for my image prediction use case:
image_filename = 'your image path'
PROJECT_ID = ''
MODEL_NAME = ''
VERSION_NAME = ''
img = base64.b64encode(open(image_filename, "rb").read()).decode()
image_bite_dict = {"key": "0", "image_bytes": {"b64": img}}
instances = [
image_bite_dict
]
service = googleapiclient.discovery.build('ml', 'v1')
name = 'projects/{}/models/{}/versions/{}'.format(PROJECT_ID, MODEL_NAME, VERSION_NAME)
response = service.projects().predict(
name=name,
body={'instances': instances}
).execute()
来源:https://stackoverflow.com/questions/56259751/understanding-inputs-for-google-ai-platform-custom-prediction-routines