scripts/to_fp16.py

import sys
from collections import Counter

import onnx
from onnxconverter_common import float16

source, target = sys.argv[1], sys.argv[2]
model = float16.convert_float_to_float16(onnx.load(source), keep_io_types=True, disable_shape_infer=False)
onnx.checker.check_model(model)
onnx.save(model, target)
graph = model.graph
float_inits = Counter(onnx.TensorProto.DataType.Name(i.data_type) for i in graph.initializer)
print("initializer types", dict(float_inits))
print("casts", sum(1 for n in graph.node if n.op_type == "Cast"), "of", len(graph.node), "nodes")