def test_simple_xor_model(self):
path = os.path.join(find_ell.find_ell_build(),
"tools/importers/CNTK/test/xorModel1.dnn")
predictor = cntk_to_ell.predictor_from_cntk_model(path)
result = predictor.Predict([0, 0])
self.assertAlmostEqual(result[0],
0,
msg='incorrect prediction for [0, 0]')
result = predictor.Predict([0, 1])
self.assertAlmostEqual(result[0],
1,
msg='incorrect prediction for [0, 1]')
result = predictor.Predict([1, 0])
self.assertAlmostEqual(result[0],
1,
msg='incorrect prediction for [1, 0]')
result = predictor.Predict([1, 1])
self.assertAlmostEqual(result[0],
0,
msg='incorrect prediction for [1, 1]')
# create a map and save to file
ell_map = ell.neural.utilities.ell_map_from_predictor(predictor)
ell_map.Save("xor_test.map")
# create a map and save to file
ell_map = ell.neural.utilities.ell_map_from_predictor(
predictor,
step_interval_msec=500,
lag_threshold_msec=750,
function_prefix="XorTest")
ell_map.Save("xor_test_steppable.map")
def test_simple_xor_model(self):
predictor = cntk_to_ell.predictor_from_cntk_model('xorModel1.dnn')
result = predictor.Predict([0, 0])
self.assertAlmostEqual(result[0],
0,
msg='incorrect prediction for [0, 0]')
result = predictor.Predict([0, 1])
self.assertAlmostEqual(result[0],
1,
msg='incorrect prediction for [0, 1]')
result = predictor.Predict([1, 0])
self.assertAlmostEqual(result[0],
1,
msg='incorrect prediction for [1, 0]')
result = predictor.Predict([1, 1])
self.assertAlmostEqual(result[0],
0,
msg='incorrect prediction for [1, 1]')
# create a map and save to file
ell_map = ell_utilities.ell_map_from_float_predictor(predictor)
ell_map.Save("xor_test.map")
# create a map and save to file
ell_map = ell_utilities.ell_map_from_float_predictor(
predictor,
step_interval_msec=500,
lag_threshold_msec=750,
function_prefix="XorTest")
ell_map.Save("xor_test_steppable.map")
def test_simple_xor_model(self):
predictor = cntk_to_ell.predictor_from_cntk_model('xorModel1.dnn')
result = predictor.Predict([0, 0])
self.assertAlmostEqual(
result[0], 0, msg='incorrect prediction for [0, 0]')
result = predictor.Predict([0, 1])
self.assertAlmostEqual(
result[0], 1, msg='incorrect prediction for [0, 1]')
result = predictor.Predict([1, 0])
self.assertAlmostEqual(
result[0], 1, msg='incorrect prediction for [1, 0]')
result = predictor.Predict([1, 1])
self.assertAlmostEqual(
result[0], 0, msg='incorrect prediction for [1, 1]')
# create a map and save to file
ell_map = ell_utilities.ell_map_from_float_predictor(predictor)
ell_map.Save("xor_test.map")
# create a steppable map and save to file
ell_steppable_map = ell_utilities.ell_steppable_map_from_float_predictor(
predictor, 100, "XorInputCallback", "XorOutputCallback")
ell_steppable_map.Save("xor_steppable_test.map")
return
def test_simple_xor_model(self):
predictor = cntk_to_ell.predictor_from_cntk_model('xorModel1.dnn')
result = predictor.Predict([0, 0])
self.assertAlmostEqual(result[0],
0,
msg='incorrect prediction for [0, 0]')
result = predictor.Predict([0, 1])
self.assertAlmostEqual(result[0],
1,
msg='incorrect prediction for [0, 1]')
result = predictor.Predict([1, 0])
self.assertAlmostEqual(result[0],
1,
msg='incorrect prediction for [1, 0]')
result = predictor.Predict([1, 1])
self.assertAlmostEqual(result[0],
0,
msg='incorrect prediction for [1, 1]')
# create a map and save to file
ell_map = ell_utilities.ell_map_from_float_predictor(predictor)
ell_map.Save("xor_test.map")
# create a steppable map and save to file
ell_steppable_map = ell_utilities.\
ell_steppable_map_from_float_predictor(
predictor, 100, "XorInputCallback", "XorOutputCallback")
ell_steppable_map.Save("xor_steppable_test.map")
def main(argv):
arg_parser = argparse.ArgumentParser(
"Converts CNTK model to ELL model\n"
"Example:\n"
" cntk_import.py VGG16_ImageNet_Caffe.model\n"
"This outputs 'VGG16_ImageNet_Caffe.ell' and 'VGG16_ImageNet_Caffe_config.json'\n"
)
arg_parser.add_argument(
"cntk_model_file",
help="path to a CNTK model file, or a zip archive of a CNTK model file"
)
arg_parser.add_argument("--zip_ell_model",
help="zips the output ELL model if set",
action="store_true")
model_options = arg_parser.add_argument_group('model_options')
model_options.add_argument(
"--step_interval",
help="produce a steppable ELL model for a millisecond interval",
default=0)
model_options.add_argument(
"--lag_threshold",
help=
"number of step intervals to fall behind before notifying the caller.\n"
"used when step_interval is set\n",
default=5)
args = vars(arg_parser.parse_args(argv))
model_options = args.get('model_options', {})
step_interval = model_options.get('step_interval')
lag_threshold = model_options.get('lag_threshold')
# extract the model if it's in an archive
unzip = ziptools.Extractor(args['cntk_model_file'])
success, filename = unzip.extract_file(".cntk")
if success:
print("extracted: " + filename)
else:
# not a zip archive
filename = args['cntk_model_file']
predictor = cntk_to_ell.predictor_from_cntk_model(filename)
model_file_name = os.path.splitext(filename)[0] + '.ell'
ell_map = ell_utilities.ell_map_from_float_predictor(
predictor, step_interval, lag_threshold)
print("Saving model file: '" + model_file_name + "'")
ell_map.Save(model_file_name)
if args['zip_ell_model']:
print("Zipping model file: '" + model_file_name + ".zip'")
zipper = ziptools.Zipper()
zipper.zip_file(model_file_name, model_file_name + ".zip")
os.remove(model_file_name)
def get_ell_predictor(modelConfig):
"""Imports a model and returns an ELL.Predictor."""
predictor = None
if (modelConfig.import_from == ImportFrom.darknet):
# Import a pretrained Darknet model
predictor = darknet_to_ell.predictor_from_darknet_model(modelConfig.model_files[0], modelConfig.model_files[1])
else:
# Import a pretrained CNTK model
predictor = cntk_to_ell.predictor_from_cntk_model(modelConfig.model_files[0])
return predictor
def main(argv):
arg_parser = argparse.ArgumentParser(
"Converts CNTK model to ELL model\n"
"Example:\n"
" cntk_import.py VGG16_ImageNet_Caffe.model\n"
"This outputs 'VGG16_ImageNet_Caffe.ell' and 'VGG16_ImageNet_Caffe_config.json'\n"
)
arg_parser.add_argument(
"cntk_model_file",
help="path to a CNTK model file, or a zip archive of a CNTK model file"
)
arg_parser.add_argument("--zip_ell_model",
help="zips the output ELL model if set",
action="store_true")
args = arg_parser.parse_args(argv)
# extract the model if it's in an archive
unzip = ziptools.Extractor(args.cntk_model_file)
success, filename = unzip.extract_file(".cntk")
if (success):
print("extracted: " + filename)
else:
# not a zip archive
filename = args.cntk_model_file
predictor = cntk_to_ell.predictor_from_cntk_model(filename)
input_shape = predictor.GetInputShape()
output_shape = predictor.GetOutputShape()
model_file_name = os.path.splitext(filename)[0] + '.ell'
head, tail = os.path.split(model_file_name)
ell_map = ell_utilities.ell_map_from_float_predictor(predictor)
print("Saving model file: '" + model_file_name + "'")
ell_map.Save(model_file_name)
if (args.zip_ell_model):
print("Zipping model file: '" + model_file_name + ".zip'")
zipper = ziptools.Zipper()
zipper.zip_file(model_file_name, model_file_name + ".zip")
os.remove(model_file_name)
def test_simple_xor_model(self):
predictor = cntk_to_ell.predictor_from_cntk_model('xorModel1.dnn')
result = predictor.Predict([0, 0])
self.assertAlmostEqual(result[0],
0,
msg='incorrect prediction for [0, 0]')
result = predictor.Predict([0, 1])
self.assertAlmostEqual(result[0],
1,
msg='incorrect prediction for [0, 1]')
result = predictor.Predict([1, 0])
self.assertAlmostEqual(result[0],
1,
msg='incorrect prediction for [1, 0]')
result = predictor.Predict([1, 1])
self.assertAlmostEqual(result[0],
0,
msg='incorrect prediction for [1, 1]')
return
def model_test_impl(self, modelName):
with self.subTest(modelName=modelName):
_logger.info('Testing {0}.cntk vs ELL ({0})'.format(modelName))
# Load the cntk model
cntkModel = load_model(modelName + '.cntk')
# Import the model into an ELL map live, without unarchiving
predictor = cntk_to_ell.predictor_from_cntk_model(modelName +
'.cntk')
ellMap = ell_utilities.ell_map_from_float_predictor(predictor)
# Load the map from archive
ellMapFromArchive = ell.model.Map(modelName + '.ell')
inputShape = ellMap.GetInputShape()
outputShape = ellMap.GetOutputShape()
# Compile the live map
# Note: for testing purposes, callback functions assume the "model" namespace
ellCompiledMap = ellMap.Compile('host',
'model',
'predict',
False,
dtype=np.float32)
# Compile the unarchived map
# Note: for testing purposes, callback functions assume the "model" namespace
ellCompiledMapFromArchive = ellMapFromArchive.Compile(
'host', 'model', 'predict', False, dtype=np.float32)
cntkInput = np.random.uniform(
high=255,
size=(inputShape.channels, inputShape.rows,
inputShape.columns)).astype(np.float)
ellOrderedInput = cntk_converters.\
get_float_vector_from_cntk_array(cntkInput)
cntkInput = np.ascontiguousarray(cntkInput)
# Get the CNTK results
_, out = cntkModel.forward({
cntkModel.arguments[0]: [cntkInput],
cntkModel.arguments[1]: [list(range(len(self.categories)))]
})
for output in cntkModel.outputs:
if (output.shape == (len(self.categories), )):
out = out[output]
cntkResults = softmax(out[0]).eval()
_logger.info('Comparing predictor output (reference)')
sys.stdout.flush()
ellPredictorResults = predictor.Predict(ellOrderedInput)
# Verify CNTK results and predictor results match
np.testing.assert_array_almost_equal(
cntkResults,
ellPredictorResults,
decimal=5,
err_msg=('results for CNTK and ELL predictor (' + modelName +
') do not match!'))
_logger.info('Comparing map output (reference)')
sys.stdout.flush()
ellMapResults = ellMap.Compute(ellOrderedInput, dtype=np.float32)
# Verify CNTK results and ELL map results match
np.testing.assert_array_almost_equal(
cntkResults,
ellMapResults,
decimal=5,
err_msg=('results for CNTK and ELL map reference (' +
modelName + ') do not match!'))
_logger.info('Comparing unarchived map output (reference)')
sys.stdout.flush()
ellMapFromArchiveResults = self.compute_ell_map(
ellMapFromArchive, ellOrderedInput, cntkResults, modelName)
_logger.info('Comparing map output (compiled)')
sys.stdout.flush()
ellCompiledMapResults = ellCompiledMap.Compute(ellOrderedInput,
dtype=np.float32)
# Verify CNTK results and unarchived ELL model results match
np.testing.assert_array_almost_equal(
cntkResults,
ellCompiledMapResults,
decimal=5,
err_msg=('results for CNTK and ELL map compiled (' +
modelName + ') do not match!'))
_logger.info('Comparing unarchived map output (compiled)')
sys.stdout.flush()
ellCompiledMapFromArchiveResults = ellCompiledMapFromArchive.\
Compute(ellOrderedInput, dtype=np.float32)
# Verify CNTK results and unarchived ELL model results match
np.testing.assert_array_almost_equal(
cntkResults,
ellCompiledMapFromArchiveResults,
decimal=5,
err_msg=('results for CNTK and ELL unarchived map compiled (' +
modelName + ') do not match!'))
_logger.info(('Testing output of {0}.cntk vs ELL for model {0}'
' passed!').format(modelName))
def get_ell_predictor(modelConfig):
"""Imports a model and returns an ELL.Predictor."""
return cntk_to_ell.predictor_from_cntk_model(modelConfig.model_files[0])
def main(argv):
arg_parser = argparse.ArgumentParser(
description="Converts CNTK model to ELL model\n"
"Example:\n"
" cntk_import.py model.cntk\n"
"This outputs 'model.ell' which can be compiled with ELL's 'wrap' tool\n"
)
arg_parser.add_argument(
"cntk_model_file",
help="path to a CNTK model file, or a zip archive of a CNTK model file"
)
arg_parser.add_argument("--zip_ell_model",
help="zips the output ELL model if set",
action="store_true")
arg_parser.add_argument(
"--use_legacy_importer",
help=
"specifies whether to use the new importer engine or the legacy importer",
action="store_true")
arg_parser.add_argument(
"--plot_model",
help=
"specifies whether to plot the model using SVG to cntk_model_file.svg",
action="store_true")
arg_parser.add_argument(
"--verify_vision_model",
help=
"verifies the imported vision ELL model produces the same output as the original CNTK model",
action="store_true")
arg_parser.add_argument(
"--verify_audio_model",
help=
"verifies the imported audio ELL model produces the same output as the original CNTK model",
action="store_true")
model_options = arg_parser.add_argument_group('model_options')
model_options.add_argument(
"--step_interval",
help="produce a steppable ELL model for a millisecond interval",
default=0)
model_options.add_argument(
"--lag_threshold",
help="millisecond time lag before notifying the caller.\n"
"used when step_interval is set\n",
default=5)
args = vars(arg_parser.parse_args(argv))
model_options = args.get('model_options', {})
step_interval = model_options.get('step_interval', 0)
lag_threshold = model_options.get('lag_threshold', 0)
plot_model = args["plot_model"]
verify_model = {
"vision": args["verify_vision_model"],
"audio": args["verify_audio_model"]
}
# extract the model if it's in an archive
unzip = ziptools.Extractor(args['cntk_model_file'])
success, filename = unzip.extract_file(".cntk")
if success:
_logger.info("Extracted: " + filename)
else:
# not a zip archive
filename = args['cntk_model_file']
if not args["use_legacy_importer"]:
_logger.info("-- Using new importer engine --")
ell_map = cntk_to_ell.map_from_cntk_model_using_new_engine(
filename, step_interval, lag_threshold, plot_model, verify_model)
else:
_logger.info("-- Using legacy importer --")
predictor = cntk_to_ell.predictor_from_cntk_model(filename)
ell_map = ell.neural.utilities.ell_map_from_float_predictor(
predictor, step_interval, lag_threshold)
model_file_name = os.path.splitext(filename)[0] + ".ell"
_logger.info("\nSaving model file: '" + model_file_name + "'")
ell_map.Save(model_file_name)
if args["zip_ell_model"]:
_logger.info("Zipping model file: '" + model_file_name + ".zip'")
zipper = ziptools.Zipper()
zipper.zip_file(model_file_name, model_file_name + ".zip")
os.remove(model_file_name)
def get_ell_predictor(modelConfig):
"""Imports a model and returns an ELL.Predictor."""
return cntk_to_ell.predictor_from_cntk_model(modelConfig.model_files[0])
