def test_DeepImagePredictorNoReshape(self):
"""
Run sparkDL predictor on manually-resized images and compare result to the
keras result.
"""
imageArray = self.imageArray
kerasPredict = self.kerasPredict
def rowWithImage(img):
# return [imageIO.imageArrayToStruct(img.astype('uint8'), imageType.sparkMode)]
row = imageIO.imageArrayToStruct(img.astype('uint8'))
# re-order row to avoid pyspark bug
return [[
getattr(row, field.name)
for field in ImageSchema.imageSchema['image'].dataType
]]
# test: predictor vs keras on resized images
rdd = self.sc.parallelize([rowWithImage(img) for img in imageArray])
dfType = ImageSchema.imageSchema
imageDf = rdd.toDF(dfType)
if self.numPartitionsOverride:
imageDf = imageDf.coalesce(self.numPartitionsOverride)
transformer = DeepImagePredictor(inputCol='image',
modelName=self.name,
outputCol="prediction")
dfPredict = transformer.transform(imageDf).collect()
dfPredict = np.array([i.prediction for i in dfPredict])
self.assertEqual(kerasPredict.shape, dfPredict.shape)
np.testing.assert_array_almost_equal(kerasPredict, dfPredict)
def test_DeepImagePredictorNoReshape(self):
"""
Run sparkDL predictor on manually-resized images and compare result to the
keras result.
"""
imageArray = self.imageArray
kerasPredict = self.kerasPredict
def rowWithImage(img):
# return [imageIO.imageArrayToStruct(img.astype('uint8'), imageType.sparkMode)]
row = imageIO.imageArrayToStruct(img.astype('uint8'), imageIO.SparkMode.RGB)
# re-order row to avoid pyspark bug
return [[getattr(row, field.name) for field in imageIO.imageSchema]]
# test: predictor vs keras on resized images
rdd = self.sc.parallelize([rowWithImage(img) for img in imageArray])
dfType = StructType([StructField("image", imageIO.imageSchema)])
imageDf = rdd.toDF(dfType)
transformer = DeepImagePredictor(inputCol='image', modelName=self.name,
outputCol="prediction")
dfPredict = transformer.transform(imageDf).collect()
dfPredict = np.array([i.prediction for i in dfPredict])
self.assertEqual(kerasPredict.shape, dfPredict.shape)
np.testing.assert_array_almost_equal(kerasPredict, dfPredict)
def test_DeepImagePredictor(self):
"""
Tests that predictor returns (almost) the same values as Keras.
"""
kerasPredict = self.kerasPredict
transformer = DeepImagePredictor(inputCol='image', modelName=self.name,
outputCol="prediction",)
fullPredict = transformer.transform(self.imageDF).collect()
fullPredict = np.array([i.prediction for i in fullPredict])
self.assertEqual(kerasPredict.shape, fullPredict.shape)
np.testing.assert_array_almost_equal(kerasPredict, fullPredict, decimal=6)
def test_DeepImagePredictor(self):
"""
Tests that predictor returns (almost) the same values as Keras.
"""
kerasPredict = self.kerasPredict
transformer = DeepImagePredictor(inputCol='image', modelName=self.name,
outputCol="prediction",)
fullPredict = self._sortByFileOrder(transformer.transform(self.imageDF).collect())
fullPredict = np.array([i.prediction for i in fullPredict])
self.assertEqual(kerasPredict.shape, fullPredict.shape)
np.testing.assert_array_almost_equal(kerasPredict,
fullPredict,
decimal=self.featurizerCompareDigitsExact)
def test_inceptionV3_prediction_decoded(self):
output_col = "prediction"
topK = 10
transformer = DeepImagePredictor(inputCol="image", outputCol=output_col,
modelName="InceptionV3", decodePredictions=True, topK=topK)
image_df = getSampleImageDF()
transformed_df = transformer.transform(image_df.limit(5))
collected = transformed_df.collect()
for row in collected:
predictions = row[output_col]
self.assertEqual(len(predictions), topK)
def test_prediction_decoded(self):
"""
Tests that predictor with decoded=true returns reasonable values.
"""
output_col = "prediction"
topK = 10
transformer = DeepImagePredictor(inputCol="image", outputCol=output_col,
modelName=self.name, decodePredictions=True, topK=topK)
transformed_df = transformer.transform(self.imageDF)
collected = transformed_df.collect()
for row in collected:
predictions = row[output_col]
self.assertEqual(len(predictions), topK)
def test_prediction_decoded(self):
"""
Tests that predictor with decoded=true returns reasonable values.
"""
output_col = "prediction"
topK = 10
transformer = DeepImagePredictor(inputCol="image", outputCol=output_col,
modelName=self.name, decodePredictions=True, topK=topK)
transformed_df = transformer.transform(self.imageDF)
collected = transformed_df.collect()
for row in collected:
predictions = row[output_col]
self.assertEqual(len(predictions), topK)
def test_inceptionV3_prediction_decoded(self):
output_col = "prediction"
topK = 10
transformer = DeepImagePredictor(inputCol="image",
outputCol=output_col,
modelName="InceptionV3",
decodePredictions=True,
topK=topK)
image_df = getSampleImageDF()
transformed_df = transformer.transform(image_df.limit(5))
collected = transformed_df.collect()
for row in collected:
predictions = row[output_col]
self.assertEqual(len(predictions), topK)
def test_DeepImagePredictor(self):
"""
Run sparkDL inceptionV3 transformer on raw (original size) images and compare result to
above keras (using keras resizing) result.
"""
kerasPredict = self.kerasPredict
transformer = DeepImagePredictor(inputCol='image', modelName="InceptionV3",
outputCol="prediction",)
origImgDf = getSampleImageDF()
fullPredict = transformer.transform(origImgDf).collect()
fullPredict = np.array([i.prediction for i in fullPredict])
self.assertEqual(kerasPredict.shape, fullPredict.shape)
# We use a large tolerance below because of differences in the resize step
# TODO: match keras resize step to get closer prediction
np.testing.assert_array_almost_equal(kerasPredict, fullPredict, decimal=6)
def test_DeepImagePredictor(self):
"""
Run sparkDL transformer on raw (original size) images and compare result to
above keras (using keras resizing) result.
"""
kerasPredict = self.kerasPredict
transformer = DeepImagePredictor(
inputCol='image',
modelName=self.name,
outputCol="prediction",
)
fullPredict = transformer.transform(self.imageDF).collect()
fullPredict = np.array([i.prediction for i in fullPredict])
self.assertEqual(kerasPredict.shape, fullPredict.shape)
# We use a large tolerance below because of differences in the resize step
# TODO: match keras resize step to get closer prediction
np.testing.assert_array_almost_equal(kerasPredict,
fullPredict,
decimal=6)
def test_DeepImagePredictorNoReshape(self):
"""
Run sparkDL predictor on manually-resized images and compare result to the
keras result.
"""
imageArray = self.imageArray
kerasPredict = self.kerasPredict
# test: predictor vs keras on resized images
rdd = self.sc.parallelize(
[self._rowWithImage(img) for img in imageArray])
dfType = ImageSchema.imageSchema
imageDf = rdd.toDF(dfType)
if self.numPartitionsOverride:
imageDf = imageDf.coalesce(self.numPartitionsOverride)
transformer = DeepImagePredictor(inputCol='image',
modelName=self.name,
outputCol="prediction")
dfPredict = transformer.transform(imageDf).collect()
dfPredict = np.array([i.prediction for i in dfPredict])
self.assertEqual(kerasPredict.shape, dfPredict.shape)
np.testing.assert_array_almost_equal(kerasPredict, dfPredict)
def test_inceptionV3_prediction(self):
"""
Test inceptionV3 using keras, tensorflow and sparkDL
We run the sparkDL test with and without resizing beforehand
"""
imgFiles, images = getSampleImageList()
imageArray = np.empty((len(images), 299, 299, 3), 'uint8')
for i, img in enumerate(images):
assert img is not None and img.mode == "RGB"
imageArray[i] = np.array(img.resize((299, 299)))
# Basic keras flow
# We predict the class probabilities for the images in our test library using keras API.
prepedImaged = inception_v3.preprocess_input(
imageArray.astype('float32'))
model = inception_v3.InceptionV3()
kerasPredict = model.predict(prepedImaged)
# test: _buildTfGraphForName
# Run the graph produced by _buildTfGraphForName and compare the result to above keras
# result.
modelGraphInfo = _buildTFGraphForName("InceptionV3", False)
graph = modelGraphInfo["graph"]
sess = tf.Session(graph=graph)
with sess.as_default():
inputTensor = graph.get_tensor_by_name(
modelGraphInfo["inputTensorName"])
outputTensor = graph.get_tensor_by_name(
modelGraphInfo["outputTensorName"])
tfPredict = sess.run(outputTensor, {inputTensor: imageArray})
self.assertEqual(kerasPredict.shape, tfPredict.shape)
np.testing.assert_array_almost_equal(kerasPredict, tfPredict)
imageType = imageIO.pilModeLookup["RGB"]
def rowWithImage(img):
# return [imageIO.imageArrayToStruct(img.astype('uint8'), imageType.sparkMode)]
row = imageIO.imageArrayToStruct(img.astype('uint8'),
imageType.sparkMode)
# re-order row to avoid pyspark bug
return [[
getattr(row, field.name) for field in imageIO.imageSchema
]]
# test: predictor vs keras on resized images
# Run sparkDL inceptionV3 transformer on resized images and compare result to above keras
# result.
rdd = self.sc.parallelize([rowWithImage(img) for img in imageArray])
dfType = StructType([StructField("image", imageIO.imageSchema)])
imageDf = rdd.toDF(dfType)
transformer = DeepImagePredictor(
inputCol='image',
modelName="InceptionV3",
outputCol="prediction",
)
dfPredict = transformer.transform(imageDf).collect()
dfPredict = np.array([i.prediction for i in dfPredict])
self.assertEqual(kerasPredict.shape, dfPredict.shape)
np.testing.assert_array_almost_equal(kerasPredict, dfPredict)
# test: predictor vs keras on raw images
# Run sparkDL inceptionV3 transformer on raw (original size) images and compare result to
# above keras (using keras resizing) result.
origImgDf = getSampleImageDF()
fullPredict = transformer.transform(origImgDf).collect()
fullPredict = np.array([i.prediction for i in fullPredict])
self.assertEqual(kerasPredict.shape, fullPredict.shape)
# We use a large tolerance below because of differences in the resize step
# TODO: match keras resize step to get closer prediction
np.testing.assert_array_almost_equal(kerasPredict,
fullPredict,
decimal=6)
