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 _transform(self, dataset):
with KSessionWrap() as (sess, keras_graph):
graph, inputTensorName, outputTensorName = self._loadTFGraph(sess=sess,
graph=keras_graph)
image_df = self.loadImagesInternal(dataset, self.getInputCol())
transformer = TFImageTransformer(channelOrder='RGB', inputCol=self._loadedImageCol(),
outputCol=self.getOutputCol(), graph=graph,
inputTensor=inputTensorName,
outputTensor=outputTensorName,
outputMode=self.getOrDefault(self.outputMode))
return transformer.transform(image_df).drop(self._loadedImageCol())
def _loadTFGraph(self):
with KSessionWrap() as (sess, graph):
assert K.backend() == "tensorflow", \
"Keras backend is not tensorflow but KerasImageTransformer only supports " + \
"tensorflow-backed Keras models."
with graph.as_default():
K.set_learning_phase(0) # Testing phase
model = load_model(self.getModelFile())
out_op_name = tfx.op_name(model.output, graph)
self._inputTensor = model.input.name
self._outputTensor = model.output.name
return tfx.strip_and_freeze_until([out_op_name], graph, sess, return_graph=True)
def _transform(self, dataset):
with KSessionWrap() as (sess, keras_graph):
tfGraph, inputTensorName, outputTensorName = self._loadTFGraph(sess=sess,
graph=keras_graph)
inputGraph = TFInputGraph.fromGraph(graph=tfGraph, sess=sess,
feed_names=[inputTensorName],
fetch_names=[outputTensorName])
# Create TFTransformer & use it to apply the loaded Keras model graph to our dataset
transformer = TFTransformer(tfInputGraph=inputGraph,
inputMapping={self.getInputCol() : inputTensorName},
outputMapping={outputTensorName: self.getOutputCol()})
return transformer.transform(dataset)
def _loadTFGraph(self):
with KSessionWrap() as (sess, g):
assert K.backend() == "tensorflow", \
"Keras backend is not tensorflow but KerasImageTransformer only supports " + \
"tensorflow-backed Keras models."
with g.as_default():
K.set_learning_phase(0) # Testing phase
model = load_model(self.getModelFile())
out_op_name = utils.op_name(model.output)
self._inputTensor = model.input.name
self._outputTensor = model.output.name
return utils.stripAndFreezeGraph(
g.as_graph_def(add_shapes=True), sess, [out_op_name])
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)