Base64 Images with Keras and Google Cloud ML

Question

I predict image classes using Keras. It works in Google Cloud ML (GCML), but for efficiency, you need to change it to pass base64 strings instead of a json array. Additional documentation

I can easily run python code to decode a base64 string in a json array, but when using GCML I have no way to start the preprocessing step (unless you possibly use the Lambda layer in Keras, but I don't think this is the right approach).

Another answer suggested adding tf.placeholderwith a type tf.stringthat makes sense, but how to include it in the Keras model?

Here is the complete code for training the model and saving the exported model for GCML ...

import os
import numpy as np
import tensorflow as tf
import keras
from keras import backend as K
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.preprocessing import image
from tensorflow.python.platform import gfile

IMAGE_HEIGHT = 138
IMAGE_WIDTH = 106
NUM_CLASSES = 329

def preprocess(filename):
    # decode the image file starting from the filename
    # end up with pixel values that are in the -1, 1 range
    image_contents = tf.read_file(filename)
    image = tf.image.decode_png(image_contents, channels=1)
    image = tf.image.convert_image_dtype(image, dtype=tf.float32) # 0-1
    image = tf.expand_dims(image, 0) # resize_bilinear needs batches
    image = tf.image.resize_bilinear(image, [IMAGE_HEIGHT, IMAGE_WIDTH], align_corners=False)
    image = tf.subtract(image, 0.5)
    image = tf.multiply(image, 2.0) # -1 to 1
    image = tf.squeeze(image,[0])
    return image



filelist = gfile.ListDirectory("images")
sess = tf.Session()
with sess.as_default():
    x = np.array([np.array(     preprocess(os.path.join("images", filename)).eval()      ) for filename in filelist])

input_shape = (IMAGE_HEIGHT, IMAGE_WIDTH, 1)   # 1, because preprocessing made grayscale

# in our case the labels come from part of the filename
y = np.array([int(filename[filename.index('_')+1:-4]) for filename in filelist])
# convert class labels to numbers
y = keras.utils.to_categorical(y, NUM_CLASSES)

########## TODO: something here? ##########
image = K.placeholder(shape=(), dtype=tf.string)
decoded = tf.image.decode_jpeg(image, channels=3)
# scores = build_model(decoded)


model = Sequential()

# model.add(decoded)

model.add(Conv2D(32, kernel_size=(2, 2), activation='relu', input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.25))
model.add(Dense(num_classes, activation='softmax'))

model.compile(loss=keras.losses.categorical_crossentropy,
            optimizer=keras.optimizers.Adadelta(),
            metrics=['accuracy'])

model.fit(
    x,
    y,
    batch_size=64,
    epochs=20,
    verbose=1,
    validation_split=0.2,
    shuffle=False
    )

predict_signature = tf.saved_model.signature_def_utils.build_signature_def(
    inputs={'input_bytes':tf.saved_model.utils.build_tensor_info(model.input)},
    ########## TODO: something here? ##########
    # inputs={'input': image },    # input name must have "_bytes" suffix to use base64.
    outputs={'formId': tf.saved_model.utils.build_tensor_info(model.output)},
    method_name=tf.saved_model.signature_constants.PREDICT_METHOD_NAME
)

builder = tf.saved_model.builder.SavedModelBuilder("exported_model")

builder.add_meta_graph_and_variables(
    sess=K.get_session(),
    tags=[tf.saved_model.tag_constants.SERVING],
    signature_def_map={
        tf.saved_model.signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY: predict_signature
    },
    legacy_init_op=tf.group(tf.tables_initializer(), name='legacy_init_op')
)

builder.save()

This is related to my previous question.

Update:

, , Keras. , , base64 , , Keras? , .

image = K.placeholder(shape=(), dtype=tf.string)
decoded = tf.image.decode_jpeg(image, channels=3)
model = Sequential()

# Something like this, but this fails because it is a tensor, not a Keras layer.  Possibly this is where a Lambda layer comes in?
model.add(decoded)
model.add(Conv2D(32, kernel_size=(2, 2), activation='relu', input_shape=input_shape))
...

2:

- ...

import keras
from keras.models import Sequential
from keras.layers import Lambda
from keras import backend as K
import tensorflow as tf

image = K.placeholder(shape=(), dtype=tf.string)
model = Sequential()
model.add(Lambda(lambda image: tf.image.decode_jpeg(image, channels=3), input_shape=() ))

: TypeError: Input 'contents' of 'DecodeJpeg' Op has type float32 that does not match expected type of string.

Answer 1

tf.placeholder tf.string, , Keras?

Keras Backend ( Tensorflow), :

from keras import backend as K

. , . , Keras backend , . , , Keras docs:

keras.backend.placeholder(shape = None, ndim = None, dtype = None, sparse = False, name = None)

.

:

>>> from keras import backend as K
>>> input_ph = K.placeholder(shape=(2, 4, 5))
>>> input_ph._keras_shape
(2, 4, 5)
>>> input_ph
<tf.Tensor 'Placeholder_4:0' shape=(2, 4, 5) dtype=float32>

, , (2,4,5) dtype float. , , (, Theano). placeholder() , question.

, K ( ), , , K.foo.bar() . , Keras Backend, , .

: . , . , , ( Keras ).

Answer 2

tf.keras, . , , base64 jpeg:

def preprocess_and_decode(img_str, new_shape=[299,299]):
    img = tf.io.decode_base64(img_str)
    img = tf.image.decode_jpeg(img, channels=3)
    img = tf.image.resize_images(img, new_shape, method=tf.image.ResizeMethod.BILINEAR, align_corners=False)
    # if you need to squeeze your input range to [0,1] or [-1,1] do it here
    return img
InputLayer = Input(shape = (1,),dtype="string")
OutputLayer = Lambda(lambda img : tf.map_fn(lambda im : preprocess_and_decode(im[0]), img, dtype="float32"))(InputLayer)
base64_model = tf.keras.Model(InputLayer,OutputLayer)   

, jpeg , 299x299 299x299x3. save_model Cloud ML Engine. , , , - base64 .

(, inception_v3), :

base64_input = base64_model.input
final_output = inception_v3(base64_model.output)
new_model = tf.keras.Model(base64_input,final_output)

_ . base64 jpeg , inception_v3.