def test_prediction_vs_tensorflow_inceptionV3(self):
output_col = "prediction"
image_df = image_utils.getSampleImageDF()
# An example of how a pre-trained keras model can be used with TFImageTransformer
with KSessionWrap() as (sess, g):
with g.as_default():
K.set_learning_phase(0) # this is important but it's on the user to call it.
# nChannels needed for input_tensor in the InceptionV3 call below
image_string = utils.imageInputPlaceholder(nChannels = 3)
resized_images = tf.image.resize_images(image_string,
InceptionV3Constants.INPUT_SHAPE)
preprocessed = preprocess_input(resized_images)
model = InceptionV3(input_tensor=preprocessed, weights="imagenet")
graph = tfx.strip_and_freeze_until([model.output], g, sess, return_graph=True)
transformer = TFImageTransformer(inputCol="image", outputCol=output_col, graph=graph,
inputTensor=image_string, outputTensor=model.output,
outputMode="vector")
transformed_df = transformer.transform(image_df.limit(10))
self.assertDfHasCols(transformed_df, [output_col])
collected = transformed_df.collect()
transformer_values, transformer_topK = self.transformOutputToComparables(collected,
"filePath",
output_col)
tf_values, tf_topK = self._executeTensorflow(graph, image_string.name, model.output.name,
image_df)
self.compareClassSets(tf_topK, transformer_topK)
self.compareClassOrderings(tf_topK, transformer_topK)
self.compareArrays(tf_values, transformer_values)
def test_prediction_vs_tensorflow_inceptionV3(self):
output_col = "prediction"
image_df = image_utils.getSampleImageDF()
# An example of how a pre-trained keras model can be used with TFImageTransformer
with KSessionWrap() as (sess, g):
with g.as_default():
K.set_learning_phase(0) # this is important but it's on the user to call it.
# nChannels needed for input_tensor in the InceptionV3 call below
image_string = utils.imageInputPlaceholder(nChannels=3)
resized_images = tf.image.resize_images(image_string,
InceptionV3Constants.INPUT_SHAPE)
# keras expects array in RGB order, we get it from image schema in BGR => need to flip
preprocessed = preprocess_input(imageIO._reverseChannels(resized_images))
model = InceptionV3(input_tensor=preprocessed, weights="imagenet")
graph = tfx.strip_and_freeze_until([model.output], g, sess, return_graph=True)
transformer = TFImageTransformer(channelOrder='BGR', inputCol="image", outputCol=output_col, graph=graph,
inputTensor=image_string, outputTensor=model.output,
outputMode="vector")
transformed_df = transformer.transform(image_df.limit(10))
self.assertDfHasCols(transformed_df, [output_col])
collected = transformed_df.collect()
transformer_values, transformer_topK = self.transformOutputToComparables(collected,
output_col, lambda row: row['image']['origin'])
tf_values, tf_topK = self._executeTensorflow(graph, image_string.name, model.output.name,
image_df)
self.compareClassSets(tf_topK, transformer_topK)
self.compareClassOrderings(tf_topK, transformer_topK)
self.compareArrays(tf_values, transformer_values)
def test_load_image_vs_keras_RGB(self):
g = tf.Graph()
with g.as_default():
image_arr = utils.imageInputPlaceholder()
# keras expects array in RGB order, we get it from image schema in BGR => need to flip
preprocessed = preprocess_input(image_arr)
output_col = "transformed_image"
transformer = TFImageTransformer(channelOrder='RGB',
inputCol="image",
outputCol=output_col,
graph=g,
inputTensor=image_arr,
outputTensor=preprocessed.name,
outputMode="vector")
image_df = image_utils.getSampleImageDF()
df = transformer.transform(image_df.limit(5))
for row in df.collect():
processed = np.array(row[output_col]).astype(np.float32)
# compare to keras loading
images = self._loadImageViaKeras(row["image"]['origin'])
image = images[0]
image.shape = (1, image.shape[0] * image.shape[1] * image.shape[2])
keras_processed = image[0]
self.assertTrue((processed == keras_processed).all())
def test_load_image_vs_keras(self):
g = tf.Graph()
with g.as_default():
image_arr = utils.imageInputPlaceholder()
preprocessed = preprocess_input(image_arr)
output_col = "transformed_image"
transformer = TFImageTransformer(inputCol="image",
outputCol=output_col,
graph=g,
inputTensor=image_arr,
outputTensor=preprocessed.name,
outputMode="vector")
image_df = image_utils.getSampleImageDF()
df = transformer.transform(image_df.limit(5))
for row in df.collect():
processed = np.array(row[output_col]).astype(np.float32)
# compare to keras loading
images = self._loadImageViaKeras(row["filePath"])
image = images[0]
image.shape = (1, image.shape[0] * image.shape[1] * image.shape[2])
keras_processed = image[0]
self.assertTrue((processed == keras_processed).all())
def getModelData(self, featurize):
sess = tf.Session()
with sess.as_default():
K.set_learning_phase(0)
inputImage = imageInputPlaceholder(nChannels=3)
preprocessed = self.preprocess(inputImage)
model = self.model(preprocessed, featurize)
return dict(inputTensorName=inputImage.name,
outputTensorName=model.output.name,
session=sess,
inputTensorSize=self.inputShape(),
outputMode="vector")
def getModelData(self, featurize):
sess = tf.Session()
with sess.as_default():
K.set_learning_phase(0)
inputImage = imageInputPlaceholder(nChannels=3)
preprocessed = self.preprocess(inputImage)
model = self.model(preprocessed, featurize)
return dict(inputTensorName=inputImage.name,
outputTensorName=model.output.name,
session=sess,
inputTensorSize=self.inputShape(),
outputMode="vector")
def _buildInceptionV3Session(featurize):
sess = tf.Session()
with sess.as_default():
K.set_learning_phase(0)
inputImage = imageInputPlaceholder(nChannels=3)
preprocessed = inception_v3.preprocess_input(inputImage)
model = InceptionV3(input_tensor=preprocessed, weights="imagenet",
include_top=(not featurize))
return dict(inputTensorName=inputImage.name,
outputTensorName=model.output.name,
session=sess,
inputTensorSize=InceptionV3Constants.INPUT_SHAPE,
outputMode="vector")
def _buildInceptionV3Session(featurize):
sess = tf.Session()
with sess.as_default():
K.set_learning_phase(0)
inputImage = imageInputPlaceholder(nChannels=3)
preprocessed = inception_v3.preprocess_input(inputImage)
model = InceptionV3(input_tensor=preprocessed,
weights="imagenet",
include_top=(not featurize))
return dict(inputTensorName=inputImage.name,
outputTensorName=model.output.name,
session=sess,
inputTensorSize=InceptionV3Constants.INPUT_SHAPE,
outputMode="vector")
def _preprocessingInceptionV3Transformed(self, outputMode, outputCol):
g = tf.Graph()
with g.as_default():
image_arr = utils.imageInputPlaceholder()
resized_images = tf.image.resize_images(image_arr, InceptionV3Constants.INPUT_SHAPE)
processed_images = preprocess_input(resized_images)
self.assertEqual(processed_images.shape[1], InceptionV3Constants.INPUT_SHAPE[0])
self.assertEqual(processed_images.shape[2], InceptionV3Constants.INPUT_SHAPE[1])
transformer = TFImageTransformer(inputCol="image", outputCol=outputCol, graph=g,
inputTensor=image_arr.name, outputTensor=processed_images,
outputMode=outputMode)
image_df = image_utils.getSampleImageDF()
return transformer.transform(image_df.limit(5))
def _preprocessingInceptionV3Transformed(self, outputMode, outputCol):
g = tf.Graph()
with g.as_default():
image_arr = utils.imageInputPlaceholder()
resized_images = tf.image.resize_images(image_arr, InceptionV3Constants.INPUT_SHAPE)
# keras expects array in RGB order, we get it from image schema in BGR => need to flip
processed_images = preprocess_input(imageIO._reverseChannels(resized_images))
self.assertEqual(processed_images.shape[1], InceptionV3Constants.INPUT_SHAPE[0])
self.assertEqual(processed_images.shape[2], InceptionV3Constants.INPUT_SHAPE[1])
transformer = TFImageTransformer(channelOrder='BGR', inputCol="image", outputCol=outputCol, graph=g,
inputTensor=image_arr.name, outputTensor=processed_images,
outputMode=outputMode)
image_df = image_utils.getSampleImageDF()
return transformer.transform(image_df.limit(5))
def _preprocessingInceptionV3Transformed(self, outputMode, outputCol):
g = tf.Graph()
with g.as_default():
image_arr = utils.imageInputPlaceholder()
resized_images = tf.image.resize_images(image_arr, InceptionV3Constants.INPUT_SHAPE)
# keras expects array in RGB order, we get it from image schema in BGR => need to flip
processed_images = preprocess_input(imageIO._reverseChannels(resized_images))
self.assertEqual(processed_images.shape[1], InceptionV3Constants.INPUT_SHAPE[0])
self.assertEqual(processed_images.shape[2], InceptionV3Constants.INPUT_SHAPE[1])
transformer = TFImageTransformer(channelOrder='BGR', inputCol="image", outputCol=outputCol, graph=g,
inputTensor=image_arr.name, outputTensor=processed_images,
outputMode=outputMode)
image_df = image_utils.getSampleImageDF()
return transformer.transform(image_df.limit(5))
def test_load_image_vs_keras(self):
g = tf.Graph()
with g.as_default():
image_arr = utils.imageInputPlaceholder()
preprocessed = preprocess_input(image_arr)
output_col = "transformed_image"
transformer = TFImageTransformer(inputCol="image", outputCol=output_col, graph=g,
inputTensor=image_arr, outputTensor=preprocessed.name,
outputMode="vector")
image_df = image_utils.getSampleImageDF()
df = transformer.transform(image_df.limit(5))
for row in df.collect():
processed = np.array(row[output_col]).astype(np.float32)
# compare to keras loading
images = self._loadImageViaKeras(row["filePath"])
image = images[0]
image.shape = (1, image.shape[0] * image.shape[1] * image.shape[2])
keras_processed = image[0]
self.assertTrue( (processed == keras_processed).all() )
def test_load_image_vs_keras_RGB(self):
g = tf.Graph()
with g.as_default():
image_arr = utils.imageInputPlaceholder()
# keras expects array in RGB order, we get it from image schema in BGR => need to flip
preprocessed = preprocess_input(image_arr)
output_col = "transformed_image"
transformer = TFImageTransformer(channelOrder='RGB', inputCol="image", outputCol=output_col, graph=g,
inputTensor=image_arr, outputTensor=preprocessed.name,
outputMode="vector")
image_df = image_utils.getSampleImageDF()
df = transformer.transform(image_df.limit(5))
for row in df.collect():
processed = np.array(row[output_col], dtype = np.float32)
# compare to keras loading
images = self._loadImageViaKeras(row["image"]['origin'])
image = images[0]
image.shape = (1, image.shape[0] * image.shape[1] * image.shape[2])
keras_processed = image[0]
np.testing.assert_array_almost_equal(keras_processed, processed, decimal = 6)
def test_prediction_vs_tensorflow_inceptionV3(self):
output_col = "prediction"
image_df = image_utils.getSampleImageDF()
# An example of how a pre-trained keras model can be used with TFImageTransformer
with KSessionWrap() as (sess, g):
with g.as_default():
K.set_learning_phase(
0) # this is important but it's on the user to call it.
# nChannels needed for input_tensor in the InceptionV3 call below
image_string = utils.imageInputPlaceholder(nChannels=3)
resized_images = tf.image.resize_images(
image_string, InceptionV3Constants.INPUT_SHAPE)
preprocessed = preprocess_input(resized_images)
model = InceptionV3(input_tensor=preprocessed,
weights="imagenet")
graph = utils.stripAndFreezeGraph(
g.as_graph_def(add_shapes=True), sess, [model.output])
transformer = TFImageTransformer(inputCol="image",
outputCol=output_col,
graph=graph,
inputTensor=image_string,
outputTensor=model.output,
outputMode="vector")
transformed_df = transformer.transform(image_df.limit(10))
self.assertDfHasCols(transformed_df, [output_col])
collected = transformed_df.collect()
transformer_values, transformer_topK = self.transformOutputToComparables(
collected, "filePath", output_col)
tf_values, tf_topK = self._executeTensorflow(graph, image_string.name,
model.output.name,
image_df)
self.compareClassSets(tf_topK, transformer_topK)
self.compareClassOrderings(tf_topK, transformer_topK)
self.compareArrays(tf_values, transformer_values)
#dataframe for testing the classification model
test_df = jobs_test.unionAll(zuckerberg_test)
test_df.show()
# model creation
from pyspark.ml.classification import LogisticRegression
from pyspark.ml import Pipeline
from sparkdl import readImages, TFImageTransformer
import sparkdl.graph.utils as tfx # strip_and_freeze_until was moved from sparkdl.transformers to sparkdl.graph.utils in 0.2.0
from sparkdl.transformers import utils
import tensorflow as tf
graph = tf.Graph()
with tf.Session(graph=graph) as sess:
image_arr = utils.imageInputPlaceholder()
resized_images = tf.image.resize_images(image_arr, (299, 299))
# the following step is not necessary for this graph, but can be for graphs with variables, etc
frozen_graph = tfx.strip_and_freeze_until([resized_images],
graph,
sess,
return_graph=True)
transformer = TFImageTransformer(inputCol="image",
outputCol="features",
graph=frozen_graph,
inputTensor=image_arr,
outputTensor=resized_images)
processed_image_df = transformer.transform(test_df)
processed_image_df.show()
