def main():
np.set_printoptions(precision=3,
suppress=True,
floatmode='fixed',
threshold=sys.maxsize)
args = get_args()
if args.tensor_path is None:
utils.set_stdin_to_binary()
if sys.stdin.isatty():
print("No input provided!", file=sys.stderr)
exit(1)
tensor = nnef.read_tensor(sys.stdin)
else:
tensor = read_nnef_tensor(args.tensor_path)
print('Shape:', list(tensor.shape))
if int(args.k) <= 0:
print(tensor)
else:
axis = int(args.axis)
k = min(int(args.k), tensor.shape[axis])
if axis >= len(tensor.shape) or axis < -len(tensor.shape):
print("axis={} is outside the supported range for this tensor.".
format(axis))
exit(1)
values, indices = topk(tensor, axis=axis, k=k)
values = np.squeeze(values)
indices = np.squeeze(indices)
print("TopK({}, k={}, axis={}):\nValues:\n{}\nIndices:\n{}".format(
tensor_name(args.tensor_path) if args.tensor_path is not None else
"stdin", k, axis, values, indices))
def _are_activations_close(activation_pair,
verbose=False,
allowed_bad_pixel_ratio=0.0):
# type: (_ActivationPair, bool, float)->bool
arr1 = read_nnef_tensor(activation_pair.from_) # type:np.ndarray
arr2 = read_nnef_tensor(activation_pair.to) # type: np.ndarray
for transform in activation_pair.transforms:
arr1 = transform.apply_np(arr1)
if arr1.dtype != arr2.dtype:
print("Warning: different dtypes: {} != {} for {}, {}".format(
arr1.dtype.name, arr2.dtype.name, activation_pair.short_from,
activation_pair.short_to))
if not _are_np_dtypes_compatible_in_nnef(arr1.dtype, arr2.dtype):
print("Error: incompatible dtypes: {} != {} for {}, {}".format(
arr1.dtype.name, arr2.dtype.name, activation_pair.short_from,
activation_pair.short_to))
return False
elif arr1.shape != arr2.shape:
print("Error: shape error {} != {} for {}, {}".format(
arr1.shape, arr2.shape, activation_pair.short_from,
activation_pair.short_to))
return False
else:
if arr1.dtype == np.dtype(np.bool_):
differences = (arr1 != arr2).astype(np.int8).sum(dtype=np.int64)
if differences > 0: # Maybe too strict
print("Error: Bool tensors different at {} places: {}, {}".
format(differences, activation_pair.short_from,
activation_pair.short_to))
return False
return True
else:
error_rate1 = np.abs(arr2 - arr1) / np.maximum(np.abs(arr1), 1e-32)
error_rate2 = np.abs(arr2 - arr1) / np.maximum(np.abs(arr2), 1e-32)
error_rate = np.maximum(error_rate1, error_rate2)
max_error_rate1 = np.max(error_rate1)
max_error_rate2 = np.max(error_rate2)
max_error_rate = max(max_error_rate1, max_error_rate2)
max_diff = np.max(np.abs(arr2 - arr1))
max_value = min(np.max(np.abs(arr1)), np.max(np.abs(arr2)))
err_thresh = 1e-4
if max_value < err_thresh:
print("Info: max value: {} for {}, {}".format(
max_value, activation_pair.short_from,
activation_pair.short_to))
bad_pixel_ratio = np.count_nonzero(
error_rate > err_thresh) / error_rate.size
if max_error_rate > err_thresh and max_diff > err_thresh:
if bad_pixel_ratio > allowed_bad_pixel_ratio:
print("Error: max error rate: {} max diff: {} for {}, {}".
format(max_error_rate, max_diff,
activation_pair.short_from,
activation_pair.short_to))
print("Info: Bad pixel ratio: {}%".format(100 *
bad_pixel_ratio))
# print(arr1, arr2)
return False
else:
print(
"Warning: max error rate: {} max diff: {} for {}, {}".
format(max_error_rate, max_diff,
activation_pair.short_from,
activation_pair.short_to))
print("Info: Bad pixel ratio: {}%".format(100 *
bad_pixel_ratio))
# print(arr1, arr2)
return True
elif max_diff != 0 or verbose:
print(
"Info: max error rate: {} max diff: {} for {}, {}".format(
max_error_rate, max_diff, activation_pair.short_from,
activation_pair.short_to))
return True
def run_using_argv(argv):
try:
args = get_args(argv)
write_outputs = args.output_names is None or args.output_names
if args.input is None:
if sys.stdin.isatty():
raise utils.NNEFToolsException("No input provided!")
utils.set_stdin_to_binary()
if write_outputs:
if args.output is None:
if sys.stdout.isatty():
raise utils.NNEFToolsException("No output provided!")
utils.set_stdout_to_binary()
parent_dir_of_input_model = os.path.dirname(
utils.path_without_trailing_separator(args.network))
tmp_dir = None
if args.network.endswith('.tgz'):
nnef_path = tmp_dir = tempfile.mkdtemp(
prefix="nnef_", dir=parent_dir_of_input_model)
utils.tgz_extract(args.network, nnef_path)
else:
nnef_path = args.network
try:
parser_configs = NNEFParserConfig.load_configs(
args.custom_operations, load_standard=True)
# read without weights
reader = nnef_io.Reader(parser_configs=parser_configs,
infer_shapes=False)
graph = reader(
os.path.join(nnef_path, 'graph.nnef') if os.path.
isdir(nnef_path) else nnef_path)
if args.input is None:
inputs = tuple(
nnef.read_tensor(sys.stdin)
for _ in range(len(graph.inputs)))
elif len(args.input) == 1 and os.path.isdir(args.input[0]):
inputs = tuple(
nnef_io.read_nnef_tensor(
os.path.join(args.input[0], tensor.name + '.dat'))
for tensor in graph.inputs)
else:
inputs = tuple(
nnef_io.read_nnef_tensor(path) for path in args.input)
reader = nnef_io.Reader(parser_configs=parser_configs,
input_shape=tuple(
list(input.shape) for input in inputs))
graph = reader(nnef_path)
tensor_hooks = []
stats_hook = None
if args.stats:
stats_hook = backend.StatisticsHook()
tensor_hooks.append(stats_hook)
if write_outputs and args.output_names is not None:
if '*' in args.output_names:
tensor_hooks.append(
backend.ActivationExportHook(
tensor_names=[
t.name for t in graph.tensors
if not t.is_constant and not t.is_variable
],
output_directory=args.output))
else:
tensor_hooks.append(
backend.ActivationExportHook(
tensor_names=args.output_names,
output_directory=args.output))
if args.permissive:
backend.try_to_fix_unsupported_attributes(graph)
outputs = backend.run(nnef_graph=graph,
inputs=inputs,
device=args.device,
custom_operations=get_custom_runners(
args.custom_operations),
tensor_hooks=tensor_hooks)
if write_outputs and args.output_names is None:
if args.output is None:
for array in outputs:
nnef.write_tensor(sys.stdout, array)
else:
for tensor, array in zip(graph.outputs, outputs):
nnef_io.write_nnef_tensor(
os.path.join(args.output, tensor.name + '.dat'),
array)
if stats_hook:
if args.stats.endswith('/') or args.stats.endswith('\\'):
stats_path = os.path.join(nnef_path, args.stats,
'graph.stats')
else:
stats_path = os.path.join(nnef_path, args.stats)
stats_hook.save_statistics(stats_path)
if tmp_dir and (args.stats and _is_inside(nnef_path, args.stats)):
if args.network.endswith('.tgz'):
print("Info: Changing input archive", file=sys.stderr)
shutil.move(args.network,
args.network + '.nnef-tools-backup')
utils.tgz_compress(dir_path=nnef_path,
file_path=args.network)
os.remove(args.network + '.nnef-tools-backup')
else:
output_path = args.network.rsplit('.', 1)[0] + '.nnef.tgz'
backup_path = output_path + '.nnef-tools-backup'
if os.path.exists(output_path):
shutil.move(output_path, backup_path)
utils.tgz_compress(dir_path=nnef_path,
file_path=output_path)
if os.path.exists(backup_path):
os.remove(backup_path)
finally:
if tmp_dir:
shutil.rmtree(tmp_dir)
except utils.NNEFToolsException as e:
print("Error: " + str(e), file=sys.stderr)
exit(1)
except nnef.Error as e:
print("Error: " + str(e), file=sys.stderr)
exit(1)