I was able to deploy tensorflow for poets onto the cloud ml engine by creating a saved model using this script by rhaertel80
import tensorflow as tf
from tensorflow.python.saved_model import signature_constants
from tensorflow.python.saved_model import tag_constants
from tensorflow.python.saved_model import builder as saved_model_builder
input_graph = 'retrained_graph.pb'
saved_model_dir = 'my_model'
with tf.Graph().as_default() as graph:
# Read in the export graph
with tf.gfile.FastGFile(input_graph, 'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
tf.import_graph_def(graph_def, name='')
# Define SavedModel Signature (inputs and outputs)
in_image = graph.get_tensor_by_name('DecodeJpeg/contents:0')
inputs = {'image_bytes': tf.saved_model.utils.build_tensor_info(in_image)}
out_classes = graph.get_tensor_by_name('final_result:0')
outputs = {'prediction': tf.saved_model.utils.build_tensor_info(out_classes)}
signature = tf.saved_model.signature_def_utils.build_signature_def(
inputs=inputs,
outputs=outputs,
method_name='tensorflow/serving/predict'
)
with tf.Session(graph=graph) as sess:
# Save out the SavedModel.
b = saved_model_builder.SavedModelBuilder(saved_model_dir)
b.add_meta_graph_and_variables(sess,
[tf.saved_model.tag_constants.SERVING],
signature_def_map={'serving_default': signature})
b.save()
The current version of tensorflow for poets uses mobilenet architecture which wasn't working with the above script, I used the default inceptionv3 by not specifying the architecture and then ran the above script which worked successfully. I then uploaded the above savedmodel onto my bucket and created a new model and version from the console and specified the directory to my bucket and used runtime version 1.5.
After deploying my model succesfully i wrote a short script to test my model like here :
from oauth2client.client import GoogleCredentials
from googleapiclient import discovery
from googleapiclient import errors
# Store your full project ID in a variable in the format the API needs.
projectID = 'projects/{}'.format('edocoto-186909')
# Build a representation of the Cloud ML API.
ml = discovery.build('ml', 'v1')
# Create a dictionary with the fields from the request body.
name1 = 'projects/{}/models/{}'.format('edocoto-186909','flower_inception')
# Create a request to call projects.models.create.
request = ml.projects().predict(
name=name1,
body={'instances': [{'image_bytes': {'b64': b64imagedata }, 'key': '0'}]})
print (request)
# Make the call.
try:
response = request.execute()
print(response)
except errors.HttpError as err:
# Something went wrong, print out some information.
print('There was an error creating the model. Check the details:')
print(err._get_reason())
This gave the following error :
{'error': "Prediction failed: Expected tensor name: image_bytes, got tensor name: [u'image_bytes', u'key']."}
I removed the key variable
body={'instances': {'image_bytes': {'b64': b64imagedata }}})
and now i get the following error :
{'error': 'Prediction failed: Error during model execution: AbortionError(code=StatusCode.INVALID_ARGUMENT, details="NodeDef mentions attr \'dilations\' not in Op<name=Conv2D; signature=input:T, filter:T -> output:T; attr=T:type,allowed=[DT_HALF, DT_FLOAT]; attr=strides:list(int); attr=use_cudnn_on_gpu:bool,default=true; attr=padding:string,allowed=["SAME", "VALID"]; attr=data_format:string,default="NHWC",allowed=["NHWC", "NCHW"]>; NodeDef: conv/Conv2D = Conv2D[T=DT_FLOAT, _output_shapes=[[1,149,149,32]], data_format="NHWC", dilations=[1, 1, 1, 1], padding="VALID", strides=[1, 2, 2, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](Mul, conv/conv2d_params). (Check whether your GraphDef-interpreting binary is up to date with your GraphDef-generating binary.).\n\t [[Node: conv/Conv2D = Conv2D[T=DT_FLOAT, _output_shapes=[[1,149,149,32]], data_format="NHWC", dilations=[1, 1, 1, 1], padding="VALID", strides=[1, 2, 2, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](Mul, conv/conv2d_params)]]")'}
I have no idea what to do now and any help would be appreciated
Edit1: After training the model on tensorflow 1.5, i redeployed it too cloud-ml and ran the above script and now i am getting this error:
{u'error': u'Prediction failed: Error during model execution: AbortionError(code=StatusCode.INVALID_ARGUMENT, details="contents must be scalar, got shape [1]\n\t [[Node: DecodeJpeg = DecodeJpeg[_output_shapes=[[?,?,3]], acceptable_fraction=1, channels=3, dct_method="", fancy_upscaling=true, ratio=1, try_recover_truncated=false, _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_DecodeJpeg/contents_0_0)]]")'}
Edit2: After so long and thanks to the efforts of rhaertel80, I have successfully deployed to ml engine. Here is the final converter script refrenced here courtesy of rhaertel80
import tensorflow as tf
from tensorflow.contrib import layers
from tensorflow.python.saved_model import builder as saved_model_builder
from tensorflow.python.saved_model import signature_constants
from tensorflow.python.saved_model import signature_def_utils
from tensorflow.python.saved_model import tag_constants
from tensorflow.python.saved_model import utils as saved_model_utils
import tensorflow.python.saved_model.simple_save
export_dir = 'my_model2'
retrained_graph = 'retrained_graph.pb'
label_count = 5
class Model(object):
def __init__(self, label_count):
self.label_count = label_count
def build_prediction_graph(self, g):
inputs = {
'key': keys_placeholder,
'image_bytes': tensors.input_jpeg
}
keys = tf.identity(keys_placeholder)
outputs = {
'key': keys,
'prediction': g.get_tensor_by_name('final_result:0')
}
return inputs, outputs
def export(self, output_dir):
with tf.Session(graph=tf.Graph()) as sess:
# This will be our input that accepts a batch of inputs
image_bytes = tf.placeholder(tf.string, name='input', shape=(None,))
# Force it to be a single input; will raise an error if we send a batch.
coerced = tf.squeeze(image_bytes)
# When we import the graph, we'll connect `coerced` to `DecodeJPGInput:0`
input_map = {'DecodeJpeg/contents:0': coerced}
with tf.gfile.GFile(retrained_graph, "rb") as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
tf.import_graph_def(graph_def, input_map=input_map, name="")
keys_placeholder = tf.placeholder(tf.string, shape=[None])
inputs = {'image_bytes': image_bytes, 'key': keys_placeholder}
keys = tf.identity(keys_placeholder)
outputs = {
'key': keys,
'prediction': tf.get_default_graph().get_tensor_by_name('final_result:0')}
tf.saved_model.simple_save(sess, output_dir, inputs, outputs)
model = Model(label_count)
model.export(export_dir)
main difference from rhaertel80's code is the change from DecodeJPGInput:0 to DecodeJpeg/contents:0 since it was giviing an error stating that there is no such reference in the graph for the former
