def predictor_from_cntk_model(modelFile, plotModel=False):
"""Loads a CNTK model and returns an ELL.NeuralNetworkPredictor"""
print("Loading...")
z = load_model(modelFile)
print("\nFinished loading.")
if plotModel:
filename = os.path.join(os.path.dirname(modelFile),
os.path.basename(modelFile) + ".png")
cntk_utilities.plot_model(z, filename)
print("Pre-processing...")
modelLayers = cntk_utilities.get_model_layers(z)
# Get the relevant CNTK layers that we will convert to ELL
layersToConvert = cntk_layers.get_filtered_layers_list(modelLayers)
print("\nFinished pre-processing.")
predictor = None
try:
# Create a list of ELL layers from the CNTK layers
ellLayers = cntk_layers.convert_cntk_layers_to_ell_layers(
layersToConvert)
# Create an ELL neural network predictor from the layers
predictor = ELL.FloatNeuralNetworkPredictor(ellLayers)
except BaseException as exception:
print("Error occurred attempting to convert cntk layers to ELL layers")
raise exception
return predictor
def model_test_impl(self, model):
self.reset()
with self.subTest(model=model):
self.cntk_model = load_model(model + '.cntk')
modelLayers = cntk_utilities.get_model_layers(self.cntk_model)
# Get the relevant CNTK layers that we will convert to ELL
layersToConvert = cntk_layers.get_filtered_layers_list(modelLayers)
self.compare_model(layersToConvert)
self.print_top_result()
def run(self):
self.report = open("report.md", "w")
self.report.write("# Comparison Results\n")
self.report.write("**model**: %s\n\n" % (self.model_file))
if self.image_file != None:
self.image = self.load_image(self.image_file)
self.report.write("**image**: %s\n\n" % (self.image_file))
self.cntk_model = cntk.load_model(self.model_file)
modelLayers = cntk_utilities.get_model_layers(self.cntk_model)
# Get the relevant CNTK layers that we will convert to ELL
layersToConvert = cntk_layers.get_filtered_layers_list(modelLayers)
_logger.info(
"----------------------------------------------------------------------------------"
)
if self.layers:
for layer in layersToConvert:
self.compare_layer(layer)
else:
self.compare_model(layersToConvert)
self.print_top_result()
self.report.close()
def compare_predictor_output(modelFile,
labels,
modelTestInput=None,
maxLayers=None):
"""Compares an ell.NeuralNetworkPredictor against its equivalent CNTK
model.
Parameters:
modelFile -- path to the CNTK model file
labels -- array of labels
modelTestInput -- input data in row, column, channel ordering
maxLayers -- integer to indicate how many layers to run before stopping.
Setting to None will run all layers and compare against the
original model.
"""
z = load_model(modelFile)
modelLayers = cntk_utilities.get_model_layers(z)
# Get the relevant CNTK layers that we will convert to ELL
layersToConvert = cntk_layers.get_filtered_layers_list(
modelLayers, maxLayers)
if not layersToConvert:
raise RuntimeError("No layers are converted, nothing to test")
# Create a list of ELL layers from the relevant CNTK layers
_logger.info("\nCreating ELL predictor...")
ellLayers = cntk_layers.convert_cntk_layers_to_ell_layers(layersToConvert)
# Create an ELL neural network predictor from the relevant CNTK layers
predictor = ell.neural.FloatNeuralNetworkPredictor(ellLayers)
if not modelTestInput:
inputShape = predictor.GetInputShape()
modelTestInput = np.random.uniform(
low=0,
high=255,
size=(inputShape.rows, inputShape.columns,
inputShape.channels)).astype(np.float_)
ellTestInput = modelTestInput.ravel() # rows, columns, channels
ellResults = predictor.Predict(ellTestInput)
# rows, columns, channels => channels, rows, columns
cntkTestInput = np.moveaxis(modelTestInput, -1, 0).astype(np.float32)
cntkTestInput = np.ascontiguousarray(cntkTestInput)
# Get the equivalent CNTK model
if not maxLayers:
_logger.info("\nRunning original CNTK model...")
_, out = z.forward({
z.arguments[0]: [cntkTestInput],
z.arguments[1]: [list(range(len(labels)))]
})
for output in z.outputs:
if (output.shape == (len(labels), )):
out = out[output]
cntkResults = softmax(out[0]).eval()
# For the full model, we compare prediction output instead of layers
np.testing.assert_array_almost_equal(
cntkResults, ellResults, 5,
'prediction outputs do not match! (for model ' + modelFile + ')')
else:
_logger.info("\nRunning partial CNTK model...")
if (layersToConvert[-1].layer.op_name == 'CrossEntropyWithSoftmax'
and len(layersToConvert) > 2):
# ugly hack for CrossEntropyWithSoftmax
zz = as_composite(layersToConvert[-2].layer)
zz = softmax(zz)
else:
zz = as_composite(layersToConvert[-1].layer)
zz = softmax(zz)
out = zz(cntkTestInput)
orderedCntkModelResults = cntk_converters.\
get_float_vector_from_cntk_array(out)
np.testing.assert_array_almost_equal(
orderedCntkModelResults, ellResults, 5,
('prediction outputs do not match! (for partial model ' +
modelFile + ')'))
