I am trying to deploy model to AKS. I am using AML SDK to register the model in the aml workspace. I am using PipelineModel module to save the model. And I am trying to load the model using PipelineModel.load. My entry script looks like below:
`
import os
import json
import pandas as pd
from azureml.core.model import Model
from pyspark.ml import PipelineModel
from mmlspark import ComputeModelStatistics
def init():
import mmlspark # this is needed to load mmlspark libraries
import logging
# extract and load model
global model, model_path
model_path = Model.get_model_path("{model_name}")
print(model_path)
print(os.stat(model_path))
print(os.path.exists(model_path))
#model_path = os.path.join(os.getenv("AZUREML_MODEL_DIR"), "{model_name}")
logging.basicConfig(level=logging.DEBUG)
#print(model_path)
#with ZipFile(model_path, 'r') as f:
# f.extractall('model')
model = PipelineModel.load(model_path)
#model = PipelineModel.read().load(model_path)
def run(input_json):
try:
output_df = model.transform(pd.read_json(input_json))
evaluator = ComputeModelStatistics().setScoredLabelsCol("prediction").setLabelCol("label").setEvaluationMetric("AUC")
result = evaluator.transform(predictions)
auc = result.select("AUC").collect()[0][0]
result = auc
except Exception as e:
result = str(e)
return json.dumps({{"result": result}})
`
It's giving error like below:
org.apache.hadoop.mapred.InvalidInputException: Input path does not exist: file:/var/azureml-app/azureml-models/lightgbm.model/2/lightgbm.model/metadata\n\tat org.apache.hadoop.mapred.FileInputFormat.singleThreadedListStatus(FileInputFormat.java:287)\n\tat org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:229)\n\tat org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:315).
os.path.exists returns true the path fetched from Model.get_model_path.
Am I missing something here?
Related
I build Flask app with sqlite3 database and app.route add and app.route save
I have a problem with validators some of them works some does not works
validators.DataRequired() works
URLField() works
but validators.Length(min=1,max=15) does not works at all
from flask_wtf import FlaskForm #I aslo I also tried with Form
from wtforms import BooleanField, StringField, IntegerField, validators,SubmitField
from wtforms.fields.html5 import URLField
class AddRecValidators(FlaskForm): # <---I aslo I also tried with Form
title = StringField('Title:',[validators.DataRequired(), validators.Length(min=1,max=35,message="Title too long max 35 characters")])
authors = StringField('Authors:',[validators.Length(min=1,max=100)])
published_date = IntegerField('Published date:',[validators.Length(min=1,max=4)])
isbn_or_identifier = StringField('ISBN:',[validators.Length(min=1,max=15)])
page_count = IntegerField('Page count:',[ validators.Length(min=1,max=10000)])
language = StringField('Language:',[ validators.Length(min=1,max=3)])
image_links = URLField('Image links:')
submit = SubmitField(label=('Add to library'))
It looks like you're using the wrong validators for the type of input you're validating.
validators.Length() is for strings, see here
For the integers, try using NumberRange
from flask_wtf import FlaskForm
from wtforms import BooleanField, StringField, IntegerField, validators,SubmitField
from wtforms.fields.html5 import URLField
class AddRecValidators(FlaskForm):
title = StringField('Title:',[validators.DataRequired(), validators.Length(min=1,max=35,message="Title too long max 35 characters")])
authors = StringField('Authors:',[validators.Length(min=1,max=100)])
published_date = IntegerField('Published date:',[validators.NumberRange(min=1,max=4)]) # <-- note change to NumberRange
isbn_or_identifier = StringField('ISBN:',[validators.Length(min=1,max=15)])
page_count = IntegerField('Page count:',[ validators.NumberRange(min=1,max=10000)]) # <-- note change to NumberRange
language = StringField('Language:',[ validators.Length(min=1,max=3)])
image_links = URLField('Image links:')
submit = SubmitField(label=('Add to library'))
Also, here are the docs for flask-wtforms validators.
I am trying to create a tag using ec2.resource method NOT ec2.CLIENT... I can create it with client but trying to figure out with resource. I am getting an error "errorMessage": "'dict' object has no attribute 'create_tags'". I have provided my code. I am comparing certain tag which I am using if statement but when I use create_tag method I get an error.
import boto3
import collections
import sys
ec2 = boto3.resource('ec2',region_name='us-east-2')
def lambda_handler(event, context):
vol = ec2.Volume(id='1256')
for delV in vol.tags:
delV.create_tags(Tags=[{'Key':'Name', 'Value':'Test1'}])
Try this, you don't need to iterate over the existing tags like you are doing;
import boto3
import collections
import sys
ec2 = boto3.resource('ec2',region_name='us-east-2')
def lambda_handler(event, context):
my_list_of_ids = [1256, 1234, 2300]
for volid in my_list_of_ids:
vol = ec2.Volume(id=volid)
for tag in vol.tags:
if tag['Name'] == 'Name' and tag['Value'] == Value:
print("Exists")
vol.create_tags(Tags=[{'Key':'Name', 'Value':'Test1'}])
I am trying to deploy my tensorflow model in a tensorflow serving using tensorflow saved model. Input for my tf model is a string value and i have defined my signature as below
prediction_signature = (
tf.saved_model.signature_def_utils.build_signature_def(
inputs={'input_path': tensor_info_input},
outputs={'output_prediction': tensor_info_output},
method_name=tf.saved_model.signature_constants.PREDICT_METHOD_NAME))
builder.add_meta_graph_and_variables(
sess, [tf.saved_model.tag_constants.SERVING],
signature_def_map={
'predict_images':
prediction_signature,
})
My objective is to read a image from the path specified in signature definition. How do i get the input_path from input definition and convert the tensor into actual string value to read the path
I think you need to add some "reading operation" in your model file.
Like this:
def inference(image_path_string):
# read image from a image path string
image_file = tf.read_file(image_path_string)
image_raw = tf.cond(tf.image.is_jpeg(image_file),
lambda: tf.image.decode_jpeg(image_file, channels= 3 if rgb, else 1),
lambda: tf.image.decode_bmp(image_file))
# image preprocessing code
...
...
# your prediction model code
...
...
You can place the below mentioned code in a Python file say, Client.py. And for inference, you can run the below mentioned command in the Terminal
python Client.py --image abc/0.png --model mnist --signature_name predict
This will take the path of the image, "abc/0.png" and will convert it to Numeric Values, and will run the inference.
Code for Client.py is mentioned below. The below code is for MNIST Images. You can reshape your images accordingly:
from __future__ import print_function
import argparse
import time
import numpy as np
from scipy.misc import imread
import grpc
from tensorflow.contrib.util import make_tensor_proto
from tensorflow_serving.apis import predict_pb2
from tensorflow_serving.apis import prediction_service_pb2_grpc
def run(host, port, image, model, signature_name):
channel = grpc.insecure_channel('{host}:{port}'.format(host=host, port=port))
stub = prediction_service_pb2_grpc.PredictionServiceStub(channel)
# Read an image
data = imread(image)
data = data.astype(np.float32)
print(data)
start = time.time()
# Call classification model to make prediction on the image
request = predict_pb2.PredictRequest()
request.model_spec.name = model
request.model_spec.signature_name = signature_name
request.inputs['image'].CopyFrom(make_tensor_proto(data, shape=[1, 28, 28, 1]))
result = stub.Predict(request, 10.0)
end = time.time()
time_diff = end - start
# Reference:
# How to access nested values
# https://stackoverflow.com/questions/44785847/how-to-retrieve-float-val-from-a-predictresponse-object
print(result)
print('time elapased: {}'.format(time_diff))
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--host', help='Tensorflow server host name', default='localhost', type=str)
parser.add_argument('--port', help='Tensorflow server port number', default=8500, type=int)
parser.add_argument('--image', help='input image', type=str)
parser.add_argument('--model', help='model name', type=str)
parser.add_argument('--signature_name', help='Signature name of saved TF model',
default='serving_default', type=str)
args = parser.parse_args()
run(args.host, args.port, args.image, args.model, args.signature_name)
For more information, you can refer this beautiful article on Tensorflow Serving,
https://medium.com/#yuu.ishikawa/serving-pre-modeled-and-custom-tensorflow-estimator-with-tensorflow-serving-12833b4be421
what changes should i do in this code so i don't have to save image to disk in step [A] then again read it from disk in step [B]. as showing in code. can anyone help me this with changes in the code or some tips?
import io
import os
import six
from google.cloud import vision
from google.cloud import translate
from google.cloud.vision import types
import json
from wand.image import Image
client = vision.ImageAnnotatorClient()
sample_pdf = Image(filename='CMB72_CMB0720160.pdf[0]', resolution=500)
blank = Image(filename='Untitled.png')
all_ = sample_pdf.clone()
polling_ = sample_pdf.clone()
voters = sample_pdf.clone()
all_.crop(3000,2800,3800,3860)
polling_.crop(870,4330,2900,4500)
voters.crop(1300,4980,2000,5250)
blank.composite(all_,left=0,top=0)
blank.composite(voters,left=0,top=1100)
blank.composite(polling_,left=0,top=1420)
blank.save('CMB72_CMB0720122.jpg')---------------[A]
file_name = 'CMB72_CMB0720122.jpg'-------------|
with io.open(file_name,'rb') as image_file:----|>[B]
content = image_file.read()---------------|
image = types.Image(content= content)
image_context = vision.types.ImageContext(
language_hints=['hi'])
response = client.document_text_detection(image=image)
texts = response.text_annotations
file = open('jin.txt','w+',encoding='utf-8')
file.write(texts[0].description)
file.close()
Use the wand.image.Image.make_blob method.
content = blank.make_blob('JPEG')
I am trying to run a keras model in Go. First I train the model in python:
import keras as krs
from keras import backend as K
import tensorflow as tf
sess = tf.Session()
K.set_session(sess)
K._LEARNING_PHASE = tf.constant(0)
K.set_learning_phase(0)
m1 = krs.models.Sequential()
m1.Add(krs.layers.Dense(..., name="inputNode"))
...
m1.Add(krs.layers.Dense(..., activation="softmax", name="outputNode"))
m1.compile(...)
m1.fit(...)
Then I understand that it is advised that the model is frozen - to convert placeholder to constants.
saver = tf.train.Saver()
tf.train.write_graph(sess.graph_def, '.', 'my_model.pbtxt')
saver.save(sess, save_path="my_model.ckpt")
from tensorflow.python.tools import freeze_graph
from tensorflow.python.tools import optimize_for_inference_lib
freeze_graph.freeze_graph(input_graph = 'my_model.pbtxt', input_saver = "",
input_binary = False, input_checkpoint = "my_model.ckpt", output_node_names = "outputNode/Softmax",
restore_op_name = "save/restore_all", filename_tensor_name = "save/Const:0",
output_graph = "frozen_my_model.pb", clear_devices = True, initializer_nodes = "")
When trying to use the frozen model in Golang:
model, err := tf.LoadSavedModel("frozen_my_model.pb", []string{"serve"}, nil)
It returns an error that the tag serve is not found SavedModel load for tags { serve }; Status: fail.
My questions are therefore:
How do you freeze a model in python, then load it in Go
I do this to speed up inference in Go - is it correct that freezing
models will improve inference speed?
I have noted that another function exists optimize_for_inference, how would this implemented in the above setting?
You have to "tag" the trained model, using
# Create a builder to export the model
builder = tf.saved_model.builder.SavedModelBuilder("export")
# Tag the model in order to be capable of restoring it specifying the tag set
builder.add_meta_graph_and_variables(sess, ["tag"])
builder.save()
After that, you can load it in Go.
However, a more handy solution is to use tfgo
As you can see in the README, there's the code for both: train in python and inference in Go.
I'll report here for you:
Python: train LeNet on MNIST (example)
import sys
import tensorflow as tf
from dytb.inputs.predefined.MNIST import MNIST
from dytb.models.predefined.LeNetDropout import LeNetDropout
from dytb.train import train
def main():
"""main executes the operations described in the module docstring"""
lenet = LeNetDropout()
mnist = MNIST()
info = train(
model=lenet,
dataset=mnist,
hyperparameters={"epochs": 2},)
checkpoint_path = info["paths"]["best"]
with tf.Session() as sess:
# Define a new model, import the weights from best model trained
# Change the input structure to use a placeholder
images = tf.placeholder(tf.float32, shape=(None, 28, 28, 1), name="input_")
# define in the default graph the model that uses placeholder as input
_ = lenet.get(images, mnist.num_classes)
# The best checkpoint path contains just one checkpoint, thus the last is the best
saver = tf.train.Saver()
saver.restore(sess, tf.train.latest_checkpoint(checkpoint_path))
# Create a builder to export the model
builder = tf.saved_model.builder.SavedModelBuilder("export")
# Tag the model in order to be capable of restoring it specifying the tag set
builder.add_meta_graph_and_variables(sess, ["tag"])
builder.save()
return 0
if __name__ == '__main__':
sys.exit(main())
Go: inference
package main
import (
"fmt"
tg "github.com/galeone/tfgo"
tf "github.com/tensorflow/tensorflow/tensorflow/go"
)
func main() {
model := tg.LoadModel("test_models/export", []string{"tag"}, nil)
fakeInput, _ := tf.NewTensor([1][28][28][1]float32{})
results := model.Exec([]tf.Output{
model.Op("LeNetDropout/softmax_linear/Identity", 0),
}, map[tf.Output]*tf.Tensor{
model.Op("input_", 0): fakeInput,
})
predictions := results[0].Value().([][]float32)
fmt.Println(predictions)
}